DeepNLP CVPR2022 Accepted Paper List AI Robotic and STEM Top Conference & Journal Papers
-
Physically rearranging objects is an important capability for embodied agents. Visual room rearrangement evaluates an agent's ability to rearrange objects in a room to a desired goal based solely on visual input. We propose a simple yet effective method for this problem: (1) search for and map which objects need to be rearranged, and (2) rearrange each object until the task is complete. Our approach consists of an off-the-shelf semantic segmentation model, voxel-based semantic map, and semantic search policy to efficiently find objects that need to be rearranged. Our method was the winning submission to the AI2-THOR Rearrangement Challenge in the 2022 Embodied AI Workshop at CVPR 2022, and improves on current state-of-the-art end-to-end reinforcement learning-based methods that learn visual room rearrangement policies from 0.53% correct rearrangement to 16.56%, using only 2.7% as many samples from the environment.
-
Recently, self-attention mechanisms have shown impressive performance in various NLP and CV tasks, which can help capture sequential characteristics and derive global information. In this work, we explore how to extend self-attention modules to better learn subtle feature embeddings for recognizing fine-grained objects, e.g., different bird species or person identities. To this end, we propose a dual cross-attention learning (DCAL) algorithm to coordinate with self-attention learning. First, we propose global-local cross-attention (GLCA) to enhance the interactions between global images and local high-response regions, which can help reinforce the spatial-wise discriminative clues for recognition. Second, we propose pair-wise cross-attention (PWCA) to establish the interactions between image pairs. PWCA can regularize the attention learning of an image by treating another image as distractor and will be removed during inference. We observe that DCAL can reduce misleading attentions and diffuse the attention response to discover more complementary parts for recognition. We conduct extensive evaluations on fine-grained visual categorization and object re-identification. Experiments demonstrate that DCAL performs on par with state-of-the-art methods and consistently improves multiple self-attention baselines, e.g., surpassing DeiT-Tiny and ViT-Base by 2.8% and 2.4% mAP on MSMT17, respectively.
-
Recently self-supervised representation learning has drawn considerable attention from the scene text recognition community. Different from previous studies using contrastive learning, we tackle the issue from an alternative perspective, i.e., by formulating the representation learning scheme in a generative manner. Typically, the neighboring image patches among one text line tend to have similar styles, including the strokes, textures, colors, etc. Motivated by this common sense, we augment one image patch and use its neighboring patch as guidance to recover itself. Specifically, we propose a Similarity-Aware Normalization (SimAN) module to identify the different patterns and align the corresponding styles from the guiding patch. In this way, the network gains representation capability for distinguishing complex patterns such as messy strokes and cluttered backgrounds. Experiments show that the proposed SimAN significantly improves the representation quality and achieves promising performance. Moreover, we surprisingly find that our self-supervised generative network has impressive potential for data synthesis, text image editing, and font interpolation, which suggests that the proposed SimAN has a wide range of practical applications.
-
We propose a theoretical framework that generalizes simple and fast algorithms for hierarchical agglomerative clustering to weighted graphs with both attractive and repulsive interactions between the nodes. This framework defines GASP, a Generalized Algorithm for Signed graph Partitioning, and allows us to explore many combinations of different linkage criteria and cannot-link constraints. We prove the equivalence of existing clustering methods to some of those combinations and introduce new algorithms for combinations that have not been studied before. We study both theoretical and empirical properties of these combinations and prove that some of these define an ultrametric on the graph. We conduct a systematic comparison of various instantiations of GASP on a large variety of both synthetic and existing signed clustering problems, in terms of accuracy but also efficiency and robustness to noise. Lastly, we show that some of the algorithms included in our framework, when combined with the predictions from a CNN model, result in a simple bottom-up instance segmentation pipeline. Going all the way from pixels to final segments with a simple procedure, we achieve state-of-the-art accuracy on the CREMI 2016 EM segmentation benchmark without requiring domain-specific superpixels.
-
In machine learning, a question of great interest is understanding what examples are challenging for a model to classify. Identifying atypical examples ensures the safe deployment of models, isolates samples that require further human inspection, and provides interpretability into model behavior. In this work, we propose Variance of Gradients (VoG) as a valuable and efficient metric to rank data by difficulty and to surface a tractable subset of the most challenging examples for human-in-the-loop auditing. We show that data points with high VoG scores are far more difficult for the model to learn and over-index on corrupted or memorized examples. Further, restricting the evaluation to the test set instances with the lowest VoG improves the model's generalization performance. Finally, we show that VoG is a valuable and efficient ranking for out-of-distribution detection
-
Image hashing is a principled approximate nearest neighbor approach to find similar items to a query in a large collection of images. Hashing aims to learn a binary-output function that maps an image to a binary vector. For optimal retrieval performance, producing balanced hash codes with low-quantization error to bridge the gap between the learning stage's continuous relaxation and the inference stage's discrete quantization is important. However, in the existing deep supervised hashing methods, coding balance and low-quantization error are difficult to achieve and involve several losses. We argue that this is because the existing quantization approaches in these methods are heuristically constructed and not effective to achieve these objectives. This paper considers an alternative approach to learning the quantization constraints. The task of learning balanced codes with low quantization error is re-formulated as matching the learned distribution of the continuous codes to a pre-defined discrete, uniform distribution. This is equivalent to minimizing the distance between two distributions. We then propose a computationally efficient distributional distance by leveraging the discrete property of the hash functions. This distributional distance is a valid distance and enjoys lower time and sample complexities. The proposed single-loss quantization objective can be integrated into any existing supervised hashing method to improve code balance and quantization error. Experiments confirm that the proposed approach substantially improves the performance of several representative hashing methods.
-
Blind deblurring has attracted much interest with its wide applications in reality. The blind deblurring problem is usually solved by estimating the intermediate kernel and the intermediate image alternatively, which will finally converge to the blurring kernel of the observed image. Numerous works have been proposed to obtain intermediate images with fewer undesirable artifacts by designing delicate regularization on the latent solution. However, these methods still fail while dealing with images containing saturations and large blurs. To address this problem, we propose an intermediate image correction method which utilizes Bayes posterior estimation to screen through the intermediate image and exclude those unfavorable pixels to reduce their influence for kernel estimation. Extensive experiments have proved that the proposed method can effectively improve the accuracy of the final derived kernel against the state-of-the-art methods on benchmark datasets by both quantitative and qualitative comparisons.
-
Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to generate more complete and precise pseudo masks for segmentation. In this study, we propose weakly-supervised pixel-to-prototype contrast that can provide pixel-level supervisory signals to narrow the gap. Guided by two intuitive priors, our method is executed across different views and within per single view of an image, aiming to impose cross-view feature semantic consistency regularization and facilitate intra(inter)-class compactness(dispersion) of the feature space. Our method can be seamlessly incorporated into existing WSSS models without any changes to the base networks and does not incur any extra inference burden. Extensive experiments manifest that our method consistently improves two strong baselines by large margins, demonstrating the effectiveness. Specifically, built on top of SEAM, we improve the initial seed mIoU on PASCAL VOC 2012 from 55.4% to 61.5%. Moreover, armed with our method, we increase the segmentation mIoU of EPS from 70.8% to 73.6%, achieving new state-of-the-art.
-
We propose a method to interactively control the animation of fluid elements in still images to generate cinemagraphs. Specifically, we focus on the animation of fluid elements like water, smoke, fire, which have the properties of repeating textures and continuous fluid motion. Taking inspiration from prior works, we represent the motion of such fluid elements in the image in the form of a constant 2D optical flow map. To this end, we allow the user to provide any number of arrow directions and their associated speeds along with a mask of the regions the user wants to animate. The user-provided input arrow directions, their corresponding speed values, and the mask are then converted into a dense flow map representing a constant optical flow map (F_D). We observe that F_D, obtained using simple exponential operations can closely approximate the plausible motion of elements in the image. We further refine computed dense optical flow map F_D using a generative-adversarial network (GAN) to obtain a more realistic flow map. We devise a novel UNet based architecture to autoregressively generate future frames using the refined optical flow map by forward-warping the input image features at different resolutions. We conduct extensive experiments on a publicly available dataset and show that our method is superior to the baselines in terms of qualitative and quantitative metrics. In addition, we show the qualitative animations of the objects in directions that did not exist in the training set and provide a way to synthesize videos that otherwise would not exist in the real world. Project url: https://controllable-cinemagraphs.github.io/
-
Light curtain systems are designed for detecting the presence of objects within a user-defined 3D region of space, which has many applications across vision and robotics. However, the shape of light curtains have so far been limited to ruled surfaces, i.e., surfaces composed of straight lines. In this work, we propose Holocurtains: a light-efficient approach to producing light curtains of arbitrary shape. The key idea is to synchronize a rolling-shutter camera with a 2D holographic projector, which steers (rather than block) light to generate bright structured light patterns. Our prototype projector uses a binary digital micromirror device (DMD) to generate the holographic interference patterns at high speeds. Our system produces 3D light curtains that cannot be achieved with traditional light curtain setups and thus enables all-new applications, including the ability to simultaneously capture multiple light curtains in a single frame, detect subtle changes in scene geometry, and transform any 3D surface into an optical touch interface.
-
Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the hardware cannot withstand the ever-increasing memory requirements as the video length increases. 2) Storing lots of information inevitably introduces lots of noise, which is not conducive to reading the most important information from the memory bank. In this paper, we propose a Recurrent Dynamic Embedding (RDE) to build a memory bank of constant size. Specifically, we explicitly generate and update RDE by the proposed Spatio-temporal Aggregation Module (SAM), which exploits the cue of historical information. To avoid error accumulation owing to the recurrent usage of SAM, we propose an unbiased guidance loss during the training stage, which makes SAM more robust in long videos. Moreover, the predicted masks in the memory bank are inaccurate due to the inaccurate network inference, which affects the segmentation of the query frame. To address this problem, we design a novel self-correction strategy so that the network can repair the embeddings of masks with different qualities in the memory bank. Extensive experiments show our method achieves the best tradeoff between performance and speed.
-
Humans are able to recognize structured relations in observation, allowing us to decompose complex scenes into simpler parts and abstract the visual world in multiple levels. However, such hierarchical reasoning ability of human perception remains largely unexplored in current literature of semantic segmentation. Existing work is often aware of flatten labels and predicts target classes exclusively for each pixel. In this paper, we instead address hierarchical semantic segmentation (HSS), which aims at structured, pixel-wise description of visual observation in terms of a class hierarchy. We devise HSSN, a general HSS framework that tackles two critical issues in this task: i) how to efficiently adapt existing hierarchy-agnostic segmentation networks to the HSS setting, and ii) how to leverage the hierarchy information to regularize HSS network learning. To address i), HSSN directly casts HSS as a pixel-wise multi-label classification task, only bringing minimal architecture change to current segmentation models. To solve ii), HSSN first explores inherent properties of the hierarchy as a training objective, which enforces segmentation predictions to obey the hierarchy structure. Further, with hierarchy-induced margin constraints, HSSN reshapes the pixel embedding space, so as to generate well-structured pixel representations and improve segmentation eventually. We conduct experiments on four semantic segmentation datasets (i.e., Mapillary Vistas 2.0, Cityscapes, LIP, and PASCAL-Person-Part), with different class hierarchies, segmentation network architectures and backbones, showing the generalization and superiority of HSSN.
-
Shape-from-Template (SfT) methods estimate 3D surface deformations from a single monocular RGB camera while assuming a 3D state known in advance (a template). This is an important yet challenging problem due to the under-constrained nature of the monocular setting. Existing SfT techniques predominantly use geometric and simplified deformation models, which often limits their reconstruction abilities. In contrast to previous works, this paper proposes a new SfT approach explaining 2D observations through physical simulations accounting for forces and material properties. Our differentiable physics simulator regularises the surface evolution and optimises the material elastic properties such as bending coefficients, stretching stiffness and density. We use a differentiable renderer to minimise the dense reprojection error between the estimated 3D states and the input images and recover the deformation parameters using an adaptive gradient-based optimisation. For the evaluation, we record with an RGB-D camera challenging real surfaces exposed to physical forces with various material properties and textures. Our approach significantly reduces the 3D reconstruction error compared to multiple competing methods. For the source code and data, see https://4dqv.mpi-inf.mpg.de/phi-SfT/.
-
Continual learning is a challenging real-world problem for constructing a mature AI system when data are provided in a streaming fashion. Despite recent progress in continual classification, the researches of continual object detection are impeded by the diverse sizes and numbers of objects in each image. Different from previous works that tune the whole network for all tasks, in this work, we present a simple and flexible framework for continual object detection via pRotOtypical taSk corrElaTion guided gaTing mechAnism (ROSETTA). Concretely, a unified framework is shared by all tasks while task-aware gates are introduced to automatically select sub-models for specific tasks. In this way, various knowledge can be successively memorized by storing their corresponding sub-model weights in this system. To make ROSETTA automatically determine which experience is available and useful, a prototypical task correlation guided Gating Diversity Controller (GDC) is introduced to adaptively adjust the diversity of gates for the new task based on class-specific prototypes. GDC module computes class-to-class correlation matrix to depict the cross-task correlation, and hereby activates more exclusive gates for the new task if a significant domain gap is observed. Comprehensive experiments on COCO-VOC, KITTI-Kitchen, class-incremental detection on VOC and sequential learning of four tasks show that ROSETTA yields state-of-the-art performance on both task-based and class-based continual object detection.
-
The paradigm of training models on massive data without label through self-supervised learning (SSL) and finetuning on many downstream tasks has become a trend recently. However, due to the high training costs and the unconsciousness of downstream usages, most self-supervised learning methods lack the capability to correspond to the diversities of downstream scenarios, as there are various data domains, latency constraints and etc. Neural architecture search (NAS) is one universally acknowledged fashion to conquer the issues above, but applying NAS on SSL seems impossible as there is no label or metric provided for judging model selection. In this paper, we present DATA, a simple yet effective NAS approach specialized for SSL that provides Domain-Aware and Task-Aware pre-training. Specifically, we (i) train a supernet which could be deemed as a set of millions of networks covering a wide range of model scales without any label, (ii) propose a flexible searching mechanism compatible with SSL that enables finding networks of different computation costs, for various downstream vision tasks and data domains without explicit metric provided. Instantiated With MoCov2, our method achieves promising results across a wide range of computation costs on downstream tasks, including image classification, object detection and semantic segmentation. DATA is orthogonal to most existing SSL methods and endows them the ability of customization on downstream needs. Extensive experiments on other SSL methods, including BYOL, ReSSL and DenseCL demonstrate the generalizability of the proposed method. Code would be made available soon.
-
We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation. To leverage the unlabeled data to boost model performance, we present a novel Two-Way Inter-label Self-Training framework named TWIST. It exploits inherent correlations between semantic understanding and instance information of a scene. Specifically, we consider two kinds of pseudo labels for semantic- and instance-level supervision. Our key design is to provide object-level information for denoising pseudo labels and make use of their correlation for two-way mutual enhancement, thereby iteratively promoting the pseudo-label qualities. TWIST attains leading performance on both ScanNet and S3DIS, compared to recent 3D pre-training approaches, and can cooperate with them to further enhance performance, e.g., +4.4% AP50 on 1%-label ScanNet data-efficient benchmark. Code is available at https://github.com/dvlab-research/TWIST.
-
Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to apply the self-attention underlying transformer on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space. To solve this issue, existing methods usually compute self-attention locally by grouping the points into clusters of the same size, or perform convolutional self-attention on a discretized representation. However, the former results in stochastic point dropout, while the latter typically has narrow attention field. In this paper, we propose a novel voxel-based architecture, namely Voxel Set Transformer (VoxSeT), to detect 3D objects from point clouds by means of set-to-set translation. VoxSeT is built upon a voxel-based set attention (VSA) module, which reduces the self-attention in each voxel by two cross-attentions and models features in a hidden space induced by a group of latent codes. With the VSA module, VoxSeT can manage voxelized point clusters with arbitrary size in a wide range, and process them in parallel with linear complexity. The proposed VoxSeT integrates the high performance of transformer with the efficiency of voxel-based model, which can be used as a good alternative to the convolutional and point-based backbones. VoxSeT reports competitive results on the KITTI and Waymo detection benchmarks. The source code of VoxSeT will be released.
-
This paper proposes a real-world rolling shutter (RS) correction dataset, BS-RSC, and a corresponding model to correct the RS frames in a distorted video. Mobile devices in the consumer market with CMOS-based sensors for video capture often result in rolling shutter effects when relative movements occur during the video acquisition process, calling for RS effect removal techniques. However, current state-of-the-art RS correction methods often fail to remove RS effects in real scenarios since the motions are various and hard to model. To address this issue, we propose a real-world RS correction dataset BS-RSC. Real distorted videos with corresponding ground truth are recorded simultaneously via a well-designed beam-splitter-based acquisition system. BS-RSC contains various motions of both camera and objects in dynamic scenes. Further, an RS correction model with adaptive warping is proposed. Our model can warp the learned RS features into global shutter counterparts adaptively with predicted multiple displacement fields. These warped features are aggregated and then reconstructed into high-quality global shutter frames in a coarse-to-fine strategy. Experimental results demonstrate the effectiveness of the proposed method, and our dataset can improve the model's ability to remove the RS effects in the real world.
-
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions formed from seen state and object during training. Since the same state may be various in the visual appearance while entangled with different objects, CZSL is still a challenging task. Some methods recognize state and object with two trained classifiers, ignoring the impact of the interaction between object and state; the other methods try to learn the joint representation of the state-object compositions, leading to the domain gap between seen and unseen composition sets. In this paper, we propose a novel Siamese Contrastive Embedding Network (SCEN) for unseen composition recognition. Considering the entanglement between state and object, we embed the visual feature into a Siamese Contrastive Space to capture prototypes of them separately, alleviating the interaction between state and object. In addition, we design a State Transition Module (STM) to increase the diversity of training compositions, improving the robustness of the recognition model. Extensive experiments indicate that our method significantly outperforms the state-of-the-art approaches on three challenging benchmark datasets, including the recent proposed C-QGA dataset.
-
A significant gap remains between today's visual pattern recognition models and human-level visual cognition especially when it comes to few-shot learning and compositional reasoning of novel concepts. We introduce Bongard-HOI, a new visual reasoning benchmark that focuses on compositional learning of human-object interactions (HOIs) from natural images. It is inspired by two desirable characteristics from the classical Bongard problems (BPs): 1) few-shot concept learning, and 2) context-dependent reasoning. We carefully curate the few-shot instances with hard negatives, where positive and negative images only disagree on action labels, making mere recognition of object categories insufficient to complete our benchmarks. We also design multiple test sets to systematically study the generalization of visual learning models, where we vary the overlap of the HOI concepts between the training and test sets of few- shot instances, from partial to no overlaps. Bongard-HOI presents a substantial challenge to today's visual recognition models. The state-of-the-art HOI detection model achieves only 62% accuracy on few-shot binary prediction while even amateur human testers on MTurk have 91% accuracy. With the Bongard-HOI benchmark, we hope to further advance research efforts in visual reasoning, especially in holistic perception-reasoning systems and better representation learning.
-
We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an input 3D shape into two parts, resulting in a binary tree hierarchy. Each level of the tree corresponds to an assembly of shape parts, represented as implicit functions, to reconstruct the input shape. At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level. As an implicit field decoder, the part decoder is designed to decompose a sub-shape, via a two-way branched reconstruction, where each branch predicts a set of parameters defining a Gaussian to serve as a local point distribution for shape reconstruction. With reconstruction losses accounted for at each hierarchy level and a decomposition loss at each node, our network training does not require any ground-truth segmentations, let alone hierarchies. Through extensive experiments and comparisons to state-of-the-art alternatives, we demonstrate the quality, consistency, and interpretability of hierarchical structural inference by RIM-Net.
-
Data often has many semantic attributes that are causally associated with each other. But do attribute-specific learned representations of data also respect the same causal relations? We answer this question in three steps. First, we introduce NCINet, an approach for observational causal discovery from high-dimensional data. It is trained purely on synthetically generated representations and can be applied to real representations, and is specifically designed to mitigate the domain gap between the two. Second, we apply NCINet to identify the causal relations between image representations of different pairs of attributes with known and unknown causal relations between the labels. For this purpose, we consider image representations learned for predicting attributes on the 3D Shapes, CelebA, and the CASIA-WebFace datasets, which we annotate with multiple multi-class attributes. Third, we analyze the effect on the underlying causal relation between learned representations induced by various design choices in representation learning. Our experiments indicate that (1) NCINet significantly outperforms existing observational causal discovery approaches for estimating the causal relation between pairs of random samples, both in the presence and absence of an unobserved confounder, (2) under controlled scenarios, learned representations can indeed satisfy the underlying causal relations between their respective labels, and (3) the causal relations are positively correlated with the predictive capability of the representations. Code and annotations are available at: https://github.com/human-analysis/causal-relations-between-representations.
-
Establishing correspondences from image to 3D has been a key task of 6DoF object pose estimation for a long time. To predict pose more accurately, deeply learned dense maps replaced sparse templates. Dense methods also improved pose estimation in the presence of occlusion. More recently researchers have shown improvements by learning object fragments as segmentation. In this work, we present a discrete descriptor, which can represent the object surface densely. By incorporating a hierarchical binary grouping, we can encode the object surface very efficiently. Moreover, we propose a coarse to fine training strategy, which enables fine-grained correspondence prediction. Finally, by matching predicted codes with object surface and using a PnP solver, we estimate the 6DoF pose. Results on the public LM-O and YCB-V datasets show major improvement over the state of the art w.r.t. ADD(-S) metric, even surpassing RGB-D based methods in some cases.
-
Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of generating caption given an image. In this work, we repurpose such models to generate a descriptive text given an image at inference time, without any further training or tuning step. This is done by combining the visual-semantic model with a large language model, benefiting from the knowledge in both web-scale models. The resulting captions are much less restrictive than those obtained by supervised captioning methods. Moreover, as a zero-shot learning method, it is extremely flexible and we demonstrate its ability to perform image arithmetic in which the inputs can be either images or text and the output is a sentence. This enables novel high-level vision capabilities such as comparing two images or solving visual analogy tests. Our code is available at: https://github.com/YoadTew/zero-shot-image-to-text.
-
Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks, given only a few examples. To handle the limited-data in few-shot regimes, recent methods tend to collectively use a set of local features to densely represent an image instead of using a mixed global feature. They generally explore a unidirectional paradigm, e.g., find the nearest support feature for every query feature and aggregate these local matches for a joint classification. In this paper, we propose a novel Mutual Centralized Learning (MCL) to fully affiliate these two disjoint dense features sets in a bidirectional paradigm. We first associate each local feature with a particle that can bidirectionally random walk in a discrete feature space. To estimate the class probability, we propose the dense features' accessibility that measures the expected number of visits to the dense features of that class in a Markov process. We relate our method to learning a centrality on an affiliation network and demonstrate its capability to be plugged in existing methods by highlighting centralized local features. Experiments show that our method achieves the new state-of-the-art.
-
We introduce CAPRI-Net, a self-supervised neural network for learning compact and interpretable implicit representations of 3D computer-aided design (CAD) models, in the form of adaptive primitive assemblies. Given an input 3D shape, our network reconstructs it by an assembly of quadric surface primitives via constructive solid geometry (CSG) operations. Without any ground-truth shape assemblies, our self-supervised network is trained with a reconstruction loss, leading to faithful 3D reconstructions with sharp edges and plausible CSG trees. While the parametric nature of CAD models does make them more predictable locally, at the shape level, there is much structural and topological variation, which presents a significant generalizability challenge to state-of-the-art neural models for 3D shapes. Our network addresses this challenge by adaptive training with respect to each test shape, with which we fine-tune the network that was pre-trained on a model collection. We evaluate our learning framework on both ShapeNet and ABC, the largest and most diverse CAD dataset to date, in terms of reconstruction quality, sharp edges, compactness, and interpretability, to demonstrate superiority over current alternatives for neural CAD reconstruction.
-
Although the Trajectory Prediction (TP) model has achieved great success in computer vision and robotics fields, its architecture and training scheme design rely on heavy manual work and domain knowledge, which is not friendly to common users. Besides, the existing works ignore Federated Learning (FL) scenarios, failing to make full use of distributed multi-source datasets with rich actual scenes to learn more a powerful TP model. In this paper, we make up for the above defects and propose ATPFL to help users federate multi-source trajectory datasets to automatically design and train a powerful TP model. In ATPFL, we build an effective TP search space by analyzing and summarizing the existing works. Then, based on the characters of this search space, we design a relation-sequence-aware search strategy, realizing the automatic design of the TP model. Finally, we find appropriate federated training methods to respectively support the TP model search and final model training under the FL framework, ensuring both the search efficiency and the final model performance. Extensive experimental results show that ATPFL can help users gain well-performed TP models, achieving better results than the existing TP models trained on the single-source dataset.
-
Batch Normalization is a staple of computer vision models, including those employed in few-shot learning. Batch Normalization layers in convolutional neural networks are composed of a normalization step, followed by a shift and scale of these normalized features applied via the per-channel trainable affine parameters gamma and beta. These affine parameters were introduced to maintain the expressive powers of the model following normalization. While this hypothesis holds true for classification within the same domain, this work illustrates that these parameters are detrimental to downstream performance on common few-shot transfer tasks. This effect is studied with multiple methods on well-known benchmarks such as few-shot classification on miniImageNet and cross-domain few-shot learning (CD-FSL). Experiments reveal consistent performance improvements on CNNs with affine unaccompanied Batch Normalization layers; particularly in large domain-shift few-shot transfer settings. As opposed to common practices in few-shot transfer learning where the affine parameters are fixed during the adaptation phase, we show fine-tuning them can lead to improved performance.
-
Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class activation map (CAM) to generate a localization map; however, a CAM identifies only the most discriminative parts of a target object rather than the entire object region. In this work, we find the gap between classification and localization in terms of the misalignment of the directions between an input feature and a class-specific weight. We demonstrate that the misalignment suppresses the activation of CAM in areas that are less discriminative but belong to the target object. To bridge the gap, we propose a method to align feature directions with a class-specific weight. The proposed method achieves a state-of-the-art localization performance on the CUB-200-2011 and ImageNet-1K benchmarks.
-
This paper proposes a new transformer-based framework to learn class-specific object localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to form a class-agnostic localization map, we investigate if the transformer model can also effectively capture class-specific attention for more discriminative object localization by learning multiple class tokens within the transformer. To this end, we propose a Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens. The proposed MCTformer can successfully produce class-discriminative object localization maps from the class-to-patch attentions corresponding to different class tokens. We also propose to use a patch-level pairwise affinity, which is extracted from the patch-to-patch transformer attention, to further refine the localization maps. Moreover, the proposed framework is shown to fully complement the Class Activation Mapping (CAM) method, leading to remarkably superior WSSS results on the PASCAL VOC and MS COCO datasets. These results underline the importance of the class token for WSSS.
-
We introduce 3D Moments, a new computational photography effect. As input we take a pair of near-duplicate photos, i.e., photos of moving subjects from similar viewpoints, common in people's photo collections. As output, we produce a video that smoothly interpolates the scene motion from the first photo to the second, while also producing camera motion with parallax that gives a heightened sense of 3D. To achieve this effect, we represent the scene as a pair of feature-based layered depth images augmented with scene flow. This representation enables motion interpolation along with independent control of the camera viewpoint. Our system produces photorealistic space-time videos with motion parallax and scene dynamics, while plausibly recovering regions occluded in the original views. We conduct extensive experiments demonstrating superior performance over baselines on public datasets and in-the-wild photos. Project page: https://3d-moments.github.io/.
-
Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging visual learning tasks, which can be cast as a feature distribution matching problem. With the assumption of Gaussian feature distribution, conventional feature distribution matching methods usually match the mean and standard deviation of features. However, the feature distributions of real-world data are usually much more complicated than Gaussian, which cannot be accurately matched by using only the first-order and second-order statistics, while it is computationally prohibitive to use high-order statistics for distribution matching. In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space. Particularly, a fast EHM algorithm, named Sort-Matching, is employed to perform EFDM in a plug-and-play manner with minimal cost. The effectiveness of our proposed EFDM method is verified on a variety of AST and DG tasks, demonstrating new state-of-the-art results. Codes are available at https://github.com/YBZh/EFDM.
-
Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile, supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised denoisers, which learn only from single noisy images, solve the data collection problem. However, self-supervised denoising methods, especially blindspot-driven ones, suffer sizable information loss during input or network design. The absence of valuable information dramatically reduces the upper bound of denoising performance. In this paper, we propose a simple yet efficient approach called Blind2Unblind to overcome the information loss in blindspot-driven denoising methods. First, we introduce a global-aware mask mapper that enables global perception and accelerates training. The mask mapper samples all pixels at blind spots on denoised volumes and maps them to the same channel, allowing the loss function to optimize all blind spots at once. Second, we propose a re-visible loss to train the denoising network and make blind spots visible. The denoiser can learn directly from raw noise images without losing information or being trapped in identity mapping. We also theoretically analyze the convergence of the re-visible loss. Extensive experiments on synthetic and real-world datasets demonstrate the superior performance of our approach compared to previous work. Code is available at https://github.com/demonsjin/Blind2Unblind.
-
Instance-level feature matching is significantly important to the success of modern one-shot object detectors. Recently, the methods based on the metric-learning paradigm have achieved an impressive process. Most of these works only measure the relations between query and target objects on a single level, resulting in suboptimal performance overall. In this paper, we introduce the balanced and hierarchical learning for our detector. The contributions are two-fold: firstly, a novel Instance-level Hierarchical Relation (IHR) module is proposed to encode the contrastive-level, salient-level, and attention-level relations simultaneously to enhance the query-relevant similarity representation. Secondly, we notice that the batch training of the IHR module is substantially hindered by the positive-negative sample imbalance in the one-shot scenario. We then introduce a simple but effective Ratio-Preserving Loss (RPL) to protect the learning of rare positive samples and suppress the effects of negative samples. Our loss can adjust the weight for each sample adaptively, ensuring the desired positive-negative ratio consistency and boosting query-related IHR learning. Extensive experiments show that our method outperforms the state-of-the-art method by 1.6% and 1.3% on PASCAL VOC and MS COCO datasets for unseen classes, respectively. The code will be available at https://github.com/hero-y/BHRL.
-
Recent video and language pretraining frameworks lack the ability to generate sentences. We present Multimodal Video Generative Pretraining (MV-GPT), a new pretraining framework for learning from unlabelled videos which can be effectively used for generative tasks such as multimodal video captioning. Unlike recent video-language pretraining frameworks, our framework trains both a multimodal video encoder and a sentence decoder jointly. To overcome the lack of captions in unlabelled videos, we leverage the future utterance as an additional text source and propose a bidirectional generation objective -- we generate future utterances given the present mulitmodal context, and also the present utterance given future observations. With this objective, we train an encoder-decoder model end-to-end to generate a caption from raw pixels and transcribed speech directly. Our model achieves state-of-the-art performance for multimodal video captioning on four standard benchmarks, as well as for other video understanding tasks such as generative and discriminative VideoQA, video retrieval and action classification.
-
Recently, Vision Transformers have achieved impressive results on various Vision tasks. Yet, their generalization ability under different distribution shifts is poorly understood. In this work, we provide a comprehensive study on the out-of-distribution generalization of Vision Transformers. To support a systematic investigation, we first present a taxonomy of distribution shifts by categorizing them into five conceptual levels: corruption shift, background shift, texture shift, destruction shift, and style shift. Then we perform extensive evaluations of Vision Transformer variants under different levels of distribution shifts and compare their generalization ability with Convolutional Neural Network (CNN) models. Several important observations are obtained: 1) Vision Transformers generalize better than CNNs under multiple distribution shifts. With the same or less amount of parameters, Vision Transformers are ahead of corresponding CNNs by more than 5% in top-1 accuracy under most types of distribution shift. In particular, Vision Transformers lead by more than 10% under the corruption shifts. 2) larger Vision Transformers gradually narrow the in-distribution (ID) and out-of-distribution (OOD) performance gap. To further improve the generalization of Vision Transformers, we design the enhanced Vision Transformers through self-supervised learning, information theory, and adversarial learning. By investigating these three types of generalization-enhanced Transformers, we observe the gradient-sensitivity of Vision Transformers and design a smoother learning strategy to achieve a stable training process. With modified training schemes, we achieve improvements on performance towards out-of-distribution data by 4% from vanilla Vision Transformers. We comprehensively compare these three types of generalization-enhanced Vision Transformers with their corresponding CNN models and observe that: 1) For the enhanced model, larger Vision Transformers still benefit more from the out-of-distribution generalization. 2) generalization-enhanced Vision Transformers are more sensitive to the hyper-parameters than their corresponding CNN models. We hope our comprehensive study could shed light on the design of more generalizable learning systems.
-
Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over-smoothed scene reconstructions and have difficulty scaling up to large scenes. These limitations are mainly due to their simple fully-connected network architecture that does not incorporate local information in the observations. In this paper, we present NICE-SLAM, a dense SLAM system that incorporates multi-level local information by introducing a hierarchical scene representation. Optimizing this representation with pre-trained geometric priors enables detailed reconstruction on large indoor scenes. Compared to recent neural implicit SLAM systems, our approach is more scalable, efficient, and robust. Experiments on five challenging datasets demonstrate competitive results of NICE-SLAM in both mapping and tracking quality. Project page: https://pengsongyou.github.io/nice-slam
-
A bathtub in a library, a sink in an office, a bed in a laundry room - the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects. In this paper, we propose HyperDet3D to explore scene-conditioned prior knowledge for 3D object detection. Existing methods strive for better representation of local elements and their relations without sceneconditioned knowledge, which may cause ambiguity merely based on the understanding of individual points and object candidates. Instead, HyperDet3D simultaneously learns scene-agnostic embeddings and scene-specific knowledge through scene-conditioned hypernetworks. More specifically, our HyperDet3D not only explores the sharable abstracts from various 3D scenes, but also adapts the detector to the given scene at test time. We propose a discriminative Multi-head Scene-specific Attention (MSA) module to dynamically control the layer parameters of the detector conditioned on the fusion of scene-conditioned knowledge. Our HyperDet3D achieves state-of-the-art results on the 3D object detection benchmark of the ScanNet and SUN RGB-D datasets. Moreover, through cross-dataset evaluation, we show the acquired scene-conditioned prior knowledge still takes effect when facing 3D scenes with domain gap.
-
Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states. Unlike existing stochastic trajectory prediction methods which usually use a latent variable to represent multi-modality, we explicitly simulate the process of human motion variation from indeterminate to determinate. In this paper, we present a new framework to formulate the trajectory prediction task as a reverse process of motion indeterminacy diffusion (MID), in which we progressively discard indeterminacy from all the walkable areas until reaching the desired trajectory. This process is learned with a parameterized Markov chain conditioned by the observed trajectories. We can adjust the length of the chain to control the degree of indeterminacy and balance the diversity and determinacy of the predictions. Specifically, we encode the history behavior information and the social interactions as a state embedding and devise a Transformer-based diffusion model to capture the temporal dependencies of trajectories. Extensive experiments on the human trajectory prediction benchmarks including the Stanford Drone and ETH/UCY datasets demonstrate the superiority of our method. Code is available at https://github.com/gutianpei/MID.
-
Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a traffic sign with high-level semantics, whereas it owns the specific local pattern which needs detailed low-level features to localize accurately. Using different feature levels is of great importance for accurate lane detection, but it is still under-explored. In this work, we present Cross Layer Refinement Network (CLRNet) aiming at fully utilizing both high-level and low-level features in lane detection. In particular, it first detects lanes with high-level semantic features then performs refinement based on low-level features. In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy. We present ROIGather to gather global context, which further enhances the feature representation of lanes. In addition to our novel network design, we introduce Line IoU loss which regresses the lane line as a whole unit to improve the localization accuracy. Experiments demonstrate that the proposed method greatly outperforms the state-of-the-art lane detection approaches. Code is available at:https://github.com/Turoad/CLRNet.
-
We consider the problem of Vision-and-Language Navigation (VLN). The majority of current methods for VLN are trained end-to-end using either unstructured memory such as LSTM, or using cross-modal attention over the egocentric observations of the agent. In contrast to other works, our key insight is that the association between language and vision is stronger when it occurs in explicit spatial representations. In this work, we propose a cross-modal map learning model for vision-and-language navigation that first learns to predict the top-down semantics on an egocentric map for both observed and unobserved regions, and then predicts a path towards the goal as a set of waypoints. In both cases, the prediction is informed by the language through cross-modal attention mechanisms. We experimentally test the basic hypothesis that language-driven navigation can be solved given a map, and then show competitive results on the full VLN-CE benchmark.
-
In light of the success of contrastive learning in the image domain, current self-supervised video representation learning methods usually employ contrastive loss to facilitate video representation learning. When naively pulling two augmented views of a video closer, the model however tends to learn the common static background as a shortcut but fails to capture the motion information, a phenomenon dubbed as background bias. Such bias makes the model suffer from weak generalization ability, leading to worse performance on downstream tasks such as action recognition. To alleviate such bias, we propose Foreground-background Merging (FAME) to deliberately compose the moving foreground region of the selected video onto the static background of others. Specifically, without any off-the-shelf detector, we extract the moving foreground out of background regions via the frame difference and color statistics, and shuffle the background regions among the videos. By leveraging the semantic consistency between the original clips and the fused ones, the model focuses more on the motion patterns and is debiased from the background shortcut. Extensive experiments demonstrate that FAME can effectively resist background cheating and thus achieve the state-of-the-art performance on downstream tasks across UCF101, HMDB51, and Diving48 datasets. The code and configurations are released at https://github.com/Mark12Ding/FAME.
-
Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures. Some specific methods can only tackle regular textures while losing holistic structures due to the limited receptive fields of convolutional neural networks (CNNs). On the other hand, attention-based models can learn better long-range dependency for the structure recovery, but they are limited by the heavy computation for inference with large image sizes. To address these issues, we propose to leverage an additional structure restorer to facilitate the image inpainting incrementally. The proposed model restores holistic image structures with a powerful attention-based transformer model in a fixed low-resolution sketch space. Such a grayscale space is easy to be upsampled to larger scales to convey correct structural information. Our structure restorer can be integrated with other pretrained inpainting models efficiently with the zero-initialized residual addition. Furthermore, a masking positional encoding strategy is utilized to improve the performance of the proposed model with large irregular masks. Extensive experiments on various datasets validate the efficacy of our model compared with other competitors.
-
We propose an embarrassingly simple point annotation scheme to collect weak supervision for instance segmentation. In addition to bounding boxes, we collect binary labels for a set of points uniformly sampled inside each bounding box. We show that the existing instance segmentation models developed for full mask supervision can be seamlessly trained with point-based supervision collected via our scheme. Remarkably, Mask R-CNN trained on COCO, PASCAL VOC, Cityscapes, and LVIS with only 10 annotated random points per object achieves 94%-98% of its fully-supervised performance, setting a strong baseline for weakly-supervised instance segmentation. The new point annotation scheme is approximately 5 times faster than annotating full object masks, making high-quality instance segmentation more accessible in practice. Inspired by the point-based annotation form, we propose a modification to PointRend instance segmentation module. For each object, the new architecture, called Implicit PointRend, generates parameters for a function that makes the final point-level mask prediction. Implicit PointRend is more straightforward and uses a single point-level mask loss. Our experiments show that the new module is more suitable for the point-based supervision.
-
Automatic generation of ophthalmic reports using data-driven neural networks has great potential in clinical practice. When writing a report, ophthalmologists make inferences with prior clinical knowledge. This knowledge has been neglected in prior medical report generation methods. To endow models with the capability of incorporating expert knowledge, we propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG), in which clinical relation triples are injected into the visual features as prior knowledge to drive the decoding procedure. However, two major common Knowledge Noise (KN) issues may affect models' effectiveness. 1) Existing general biomedical knowledge bases such as the UMLS may not align meaningfully to the specific context and language of the report, limiting their utility for knowledge injection. 2) Incorporating too much knowledge may divert the visual features from their correct meaning. To overcome these limitations, we design an automatic information extraction scheme based on natural language processing to obtain clinical entities and relations directly from in-domain training reports. Given a set of ophthalmic images, our CGT first restores a sub-graph from the clinical graph and injects the restored triples into visual features. Then visible matrix is employed during the encoding procedure to limit the impact of knowledge. Finally, reports are predicted by the encoded cross-modal features via a Transformer decoder. Extensive experiments on the large-scale FFA-IR benchmark demonstrate that the proposed CGT is able to outperform previous benchmark methods and achieve state-of-the-art performances.
-
Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decoder for triplet prediction, or utilize two parallel decoders to detect individual objects and interactions separately, and compose triplets by a matching process. In contrast, we decouple the triplet prediction into human-object pair detection and interaction classification. Our main motivation is that detecting the human-object instances and classifying interactions accurately needs to learn representations that focus on different regions. To this end, we present Disentangled Transformer, where both encoder and decoder are disentangled to facilitate learning of two subtasks. To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder. Extensive experiments show that our method outperforms prior work on two public HOI benchmarks by a sizeable margin. Code will be available.
-
To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target). Despite impressive progress, prior methods always need to access the raw source data and develop data-dependent alignment approaches to recognize the target samples in a transductive learning manner, which may raise privacy concerns from source individuals. Several recent studies resort to an alternative solution by exploiting the well-trained white-box model from the source domain, yet, it may still leak the raw data via generative adversarial learning. This paper studies a practical and interesting setting for UDA, where only black-box source models (i.e., only network predictions are available) are provided during adaptation in the target domain. To solve this problem, we propose a new two-step knowledge adaptation framework called DIstill and fine-tuNE (DINE). Taking into consideration the target data structure, DINE first distills the knowledge from the source predictor to a customized target model, then fine-tunes the distilled model to further fit the target domain. Besides, neural networks are not required to be identical across domains in DINE, even allowing effective adaptation on a low-resource device. Empirical results on three UDA scenarios (i.e., single-source, multi-source, and partial-set) confirm that DINE achieves highly competitive performance compared to state-of-the-art data-dependent approaches. Code is available at https://github.com/tim-learn/DINE/.
-
3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or horizon-depth. We present that using horizon-depth along with room height can obtain omnidirectional-geometry awareness of room layout in both horizontal and vertical directions. In addition, we propose a planar-geometry aware loss function with normals and gradients of normals to supervise the planeness of walls and turning of corners. We propose an efficient network, LGT-Net, for room layout estimation, which contains a novel Transformer architecture called SWG-Transformer to model geometry relations. SWG-Transformer consists of (Shifted) Window Blocks and Global Blocks to combine the local and global geometry relations. Moreover, we design a novel relative position embedding of Transformer to enhance the spatial identification ability for the panorama. Experiments show that the proposed LGT-Net achieves better performance than current state-of-the-arts (SOTA) on benchmark datasets.
-
Referring image segmentation aims to segment a referent via a natural linguistic expression. Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing approaches use pretrained models to facilitate learning, yet separately transfer the language/vision knowledge from pretrained models, ignoring the multi-modal corresponding information. Inspired by the recent advance in Contrastive Language-Image Pretraining (CLIP), in this paper, we propose an end-to-end CLIP-Driven Referring Image Segmentation framework (CRIS). To transfer the multi-modal knowledge effectively, CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. More specifically, we design a vision-language decoder to propagate fine-grained semantic information from textual representations to each pixel-level activation, which promotes consistency between the two modalities. In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances. The experimental results on three benchmark datasets demonstrate that our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
-
We propose an analysis-by-synthesis method for fast multi-view 3D reconstruction of opaque objects with arbitrary materials and illumination. State-of-the-art methods use both neural surface representations and neural rendering. While flexible, neural surface representations are a significant bottleneck in optimization runtime. Instead, we represent surfaces as triangle meshes and build a differentiable rendering pipeline around triangle rasterization and neural shading. The renderer is used in a gradient descent optimization where both a triangle mesh and a neural shader are jointly optimized to reproduce the multi-view images. We evaluate our method on a public 3D reconstruction dataset and show that it can match the reconstruction accuracy of traditional baselines and neural approaches while surpassing them in optimization runtime. Additionally, we investigate the shader and find that it learns an interpretable representation of appearance, enabling applications such as 3D material editing.
-
Recently, significant progress has been made on image denoising with strong supervision from large-scale datasets. However, obtaining well-aligned noisy-clean training image pairs for each specific scenario is complicated and costly in practice. Consequently, applying a conventional supervised denoising network on in-the-wild noisy inputs is not straightforward. Although several studies have challenged this problem without strong supervision, they rely on less practical assumptions and cannot be applied to practical situations directly. To address the aforementioned challenges, we propose a novel and powerful self-supervised denoising method called CVF-SID based on a Cyclic multi-Variate Function (CVF) module and a self-supervised image disentangling (SID) framework. The CVF module can output multiple decomposed variables of the input and take a combination of the outputs back as an input in a cyclic manner. Our CVF-SID can disentangle a clean image and noise maps from the input by leveraging various self-supervised loss terms. Unlike several methods that only consider the signal-independent noise models, we also deal with signal-dependent noise components for real-world applications. Furthermore, we do not rely on any prior assumptions about the underlying noise distribution, making CVF-SID more generalizable toward realistic noise. Extensive experiments on real-world datasets show that CVF-SID achieves state-of-the-art self-supervised image denoising performance and is comparable to other existing approaches. The code is publicly available from this link.
-
Thermal infrared imaging is widely used in body temperature measurement, security monitoring, and so on, but its safety research attracted attention only in recent years. We proposed the infrared adversarial clothing, which could fool infrared pedestrian detectors at different angles. We simulated the process from cloth to clothing in the digital world and then designed the adversarial "QR code" pattern. The core of our method is to design a basic pattern that can be expanded periodically, and make the pattern after random cropping and deformation still have an adversarial effect, then we can process the flat cloth with an adversarial pattern into any 3D clothes. The results showed that the optimized "QR code" pattern lowered the Average Precision (AP) of YOLOv3 by 87.7%, while the random "QR code" pattern and blank pattern lowered the AP of YOLOv3 by 57.9% and 30.1%, respectively, in the digital world. We then manufactured an adversarial shirt with a new material: aerogel. Physical-world experiments showed that the adversarial "QR code" pattern clothing lowered the AP of YOLOv3 by 64.6%, while the random "QR code" pattern clothing and fully heat-insulated clothing lowered the AP of YOLOv3 by 28.3% and 22.8%, respectively. We used the model ensemble technique to improve the attack transferability to unseen models.
-
In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. Different from existing top-down and bottom-up methods, the proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. This leads to a simplified pipeline with enhanced efficiency. In addition, DAS learns the true distribution of body joints for the regression of their positions, rather than making a simple Laplacian or Gaussian assumption as previous works. This provides valuable priors for model prediction and thus boosts the regression-based scheme to achieve competitive performance with volumetric-base ones. Moreover, DAS exploits a recursive update strategy for progressively approaching to regression target, alleviating the optimization difficulty and further lifting the regression performance. DAS is implemented with a fully Convolutional Neural Network and end-to-end learnable. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model, specifically 1.5x speedup over previous best model, and its stat-of-the-art accuracy for multi-person 3D pose estimation.
-
Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with limited context, occasionally resulting in inaccurate lip movements. To tackle this limitation, we propose a Transformer-based autoregressive model, FaceFormer, which encodes the long-term audio context and autoregressively predicts a sequence of animated 3D face meshes. To cope with the data scarcity issue, we integrate the self-supervised pre-trained speech representations. Also, we devise two biased attention mechanisms well suited to this specific task, including the biased cross-modal multi-head (MH) attention and the biased causal MH self-attention with a periodic positional encoding strategy. The former effectively aligns the audio-motion modalities, whereas the latter offers abilities to generalize to longer audio sequences. Extensive experiments and a perceptual user study show that our approach outperforms the existing state-of-the-arts. The code and the video are available at: https://evelynfan.github.io/audio2face/.
-
Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence. However, the methods often ignore the diverse semantic relation within the images. To address this, here we propose a novel semantic relation consistency (SRC) regularization along with the decoupled contrastive learning (DCL), which utilize the diverse semantics by focusing on the heterogeneous semantics between the image patches of a single image. To further improve the performance, we present a hard negative mining by exploiting the semantic relation. We verified our method for three tasks: single-modal and multi-modal image translations, and GAN compression task for image translation. Experimental results confirmed the state-of-art performance of our method in all the three tasks.
-
We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure attributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark-driven structure transfer latent direction. The disentangled latent code produces rich generative features that incorporate feature blending to produce a plausible swapping result. We further extend our method to video face swapping by enforcing two spatio-temporal constraints on the latent space and the image space. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art image/video face swapping methods in terms of hallucination quality and consistency.
-
Customizing Convolution Neural Networks (CNN) for production use has been a challenging task for DL practitioners. This paper intends to expedite the model customization with a model hub that contains the optimized models tiered by their inference latency using Neural Architecture Search (NAS). To achieve this goal, we build a distributed NAS system to search on a novel search space that consists of prominent factors to impact latency and accuracy. Since we target GPU, we name the NAS optimized models as GPUNet, which establishes a new SOTA Pareto frontier in inference latency and accuracy. Within 1ms, GPUNet is 2x faster than EfficientNet-X and FBNetV3 with even better accuracy. We also validate GPUNet on detection tasks, and GPUNet consistently outperforms EfficientNet-X and FBNetV3 on COCO detection tasks in both latency and accuracy. All of these data validate that our NAS system is effective and generic to handle different design tasks. With this NAS system, we expand GPUNet to cover more latency groups to be directly reusable to DL practitioners in various deployment scenarios.
-
Heatmap regression methods have dominated face alignment area in recent years while they ignore the inherent relation between different landmarks. In this paper, we propose a Sparse Local Patch Transformer (SLPT) for learning the inherent relation. The SLPT generates the representation of each single landmark from a local patch and aggregates them by an adaptive inherent relation based on the attention mechanism. The subpixel coordinate of each landmark is predicted independently based on the aggregated feature. Moreover, a coarse-to-fine framework is further introduced to incorporate with the SLPT, which enables the initial landmarks to gradually converge to the target facial landmarks using fine-grained features from dynamically resized local patches. Extensive experiments carried out on three popular benchmarks, including WFLW, 300W and COFW, demonstrate that the proposed method works at the state-of-the-art level with much less computational complexity by learning the inherent relation between facial landmarks. The code is available at the project website.
-
In recent years, with the advances of generative models, many powerful face manipulation systems have been developed based on Deep Neural Networks (DNNs), called DeepFakes. If DeepFakes are not controlled timely and properly, they would become a real threat to both celebrities and ordinary people. Precautions such as adding perturbations to the source inputs will make DeepFake results look distorted from the perspective of human eyes. However, previous method doesn't explore whether the disrupted images can still spoof DeepFake detectors. This is critical for many applications where DeepFake detectors are used to discriminate between DeepFake data and real data due to the huge cost of examining a large amount of data manually. We argue that the detectors do not share a similar perspective as human eyes, which might still be spoofed by the disrupted data. Besides, the existing disruption methods rely on iteration-based perturbation generation algorithms, which is time-consuming. In this paper, we propose a novel DeepFake disruption algorithm called "DeepFake Disrupter". By training a perturbation generator, we can add the human-imperceptible perturbations to source images that need to be protected without any backpropagation update. The DeepFake results of these protected source inputs would not only look unrealistic by the human eye but also can be distinguished by DeepFake detectors easily. For example, experimental results show that by adding our trained perturbations, fake images generated by StarGAN can result in a 10 20% increase in F1-score evaluated by various DeepFake detectors.
-
Rotation equivariance has recently become a strongly desired property in the 3D deep learning community. Yet most existing methods focus on equivariance regarding a global input rotation while ignoring the fact that rotation symmetry has its own spatial support. Specifically, we consider the object detection problem in 3D scenes, where an object bounding box should be equivariant regarding the object pose, independent of the scene motion. This suggests a new desired property we call object-level rotation equivariance. To incorporate object-level rotation equivariance into 3D object detectors, we need a mechanism to extract equivariant features with local object-level spatial support while being able to model cross-object context information. To this end, we propose Equivariant Object detection Network (EON) with a rotation equivariance suspension design to achieve object-level equivariance. EON can be applied to modern point cloud object detectors, such as VoteNet and PointRCNN, enabling them to exploit object rotation symmetry in scene-scale inputs. Our experiments on both indoor scene and autonomous driving datasets show that significant improvements are obtained by plugging our EON design into existing state-of-the-art 3D object detectors. Project website: https://kovenyu.com/EON/.
-
The recently developed DEtection TRansformer (DETR) establishes a new object detection paradigm by eliminating a series of hand-crafted components. However, DETR suffers from extremely slow convergence, which increases the training cost significantly. We observe that the slow convergence is largely attributed to the complication in matching object queries with target features in different feature embedding spaces. This paper presents SAM-DETR, a Semantic-Aligned-Matching DETR that greatly accelerates DETR's convergence without sacrificing its accuracy. SAM-DETR addresses the convergence issue from two perspectives. First, it projects object queries into the same embedding space as encoded image features, where the matching can be accomplished efficiently with aligned semantics. Second, it explicitly searches salient points with the most discriminative features for semantic-aligned matching, which further speeds up the convergence and boosts detection accuracy as well. Being like a plug and play, SAM-DETR complements existing convergence solutions well yet only introduces slight computational overhead. Extensive experiments show that the proposed SAM-DETR achieves superior convergence as well as competitive detection accuracy. The implementation codes are publicly available at https://github.com/ZhangGongjie/SAM-DETR.
-
Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on large-scale image datasets to achieve top performance. In this paper, we empirically demonstrate that self-supervised pretraining of video transformers on video-only datasets can lead to action recognition results that are on par or better than those obtained with supervised pretraining on large-scale image datasets, even massive ones such as ImageNet-21K. Since transformer-based models are effective at capturing dependencies over extended temporal spans, we propose a simple learning procedure that forces the model to match a long-term view to a short-term view of the same video. Our approach, named Long-Short Temporal Contrastive Learning (LSTCL), enables video transformers to learn an effective clip-level representation by predicting temporal context captured from a longer temporal extent. To demonstrate the generality of our findings, we implement and validate our approach under three different self-supervised contrastive learning frameworks (MoCo v3, BYOL, SimSiam) using two distinct video-transformer architectures, including an improved variant of the Swin Transformer augmented with space-time attention. We conduct a thorough ablation study and show that LSTCL achieves competitive performance on multiple video benchmarks and represents a convincing alternative to supervised image-based pretraining.
-
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply enlarging receptive field also gives rise to several concerns. On the one hand, using dense attention e.g., in ViT, leads to excessive memory and computational cost, and features can be influenced by irrelevant parts which are beyond the region of interests. On the other hand, the sparse attention adopted in PVT or Swin Trans-former is data agnostic and may limit the ability to model long range relations. To mitigate these issues, we propose a novel deformable self-attention module, where the positions of key and value pairs in self-attention are selected in a data-dependent way. This flexible scheme enables the self-attention module to focus on relevant regions and cap-ture more informative features. On this basis, we present Deformable Attention Transformer, a general backbone model with deformable attention for both image classifi-cation and dense prediction tasks. Extensive experiments show that our models achieve consistently improved results on comprehensive benchmarks.
-
Computer vision systems today are primarily N-purpose systems, designed and trained for a predefined set of tasks. Adapting such systems to new tasks is challenging and often requires non-trivial modifications to the network architecture (e.g. adding new output heads) or training process (e.g. adding new losses). To reduce the time and expertise required to develop new applications, we would like to create general purpose vision systems that can learn and perform a range of tasks without any modification to the architecture or learning process. In this paper, we propose GPV-1, a task-agnostic vision-language architecture that can learn and perform tasks that involve receiving an image and producing text and/or bounding boxes, including classification, localization, visual question answering, captioning, and more. We also propose evaluations of generality of architecture, skill-concept transfer, and learning efficiency that may inform future work on general purpose vision. Our experiments indicate GPV-1 is effective at multiple tasks, reuses some concept knowledge across tasks, can perform the Referring Expressions task zero-shot, and further improves upon the zero-shot performance using a few training samples.
-
Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here, we address these issues by injecting deep vanishing point detection networks with prior knowledge. This prior knowledge no longer needs to be learned from data, saving valuable annotation efforts and compute, unlocking realistic few-sample scenarios, and reducing the impact of domain changes. Moreover, the interpretability of the priors allows to adapt deep networks to minor problem variations such as switching between Manhattan and non-Manhattan worlds. We seamlessly incorporate two geometric priors: (i) Hough Transform -- mapping image pixels to straight lines, and (ii) Gaussian sphere -- mapping lines to great circles whose intersections denote vanishing points. Experimentally, we ablate our choices and show comparable accuracy to existing models in the large-data setting. We validate our model's improved data efficiency, robustness to domain changes, adaptability to non-Manhattan settings.
-
Unsupervised methods have showed promising results on monocular depth estimation. However, the training data must be captured in scenes without moving objects. To push the envelope of accuracy, recent methods tend to increase their model parameters. In this paper, an unsupervised learning framework is proposed to jointly predict monocular depth and complete 3D motion including the motions of moving objects and camera. (1) Recurrent modulation units are used to adaptively and iteratively fuse encoder and decoder features. This improves the single-image depth inference without overspending model parameters. (2) Instead of using a single set of filters for upsampling, multiple sets of filters are devised for the residual upsampling. This facilitates the learning of edge-preserving filters and leads to the improved performance. (3) A warping-based network is used to estimate a motion field of moving objects without using semantic priors. This breaks down the requirement of scene rigidity and allows to use general videos for the unsupervised learning. The motion field is further regularized by an outlier-aware training loss. Despite the depth model just uses a single image in test time and 2.97M parameters, it achieves state-of-the-art results on the KITTI and Cityscapes benchmarks.
-
This paper presents contrastive-tuning, a simple method employing contrastive training to align image and text models while still taking advantage of their pre-training. In our empirical study we find that locked pre-trained image models with unlocked text models work best. We call this instance of contrastive-tuning "Locked-image Tuning" (LiT), which just teaches a text model to read out good representations from a pre-trained image model for new tasks. A LiT model gains the capability of zero-shot transfer to new vision tasks, such as image classification or retrieval. The proposed LiT is widely applicable; it works reliably with multiple pre-training methods (supervised and unsupervised) and across diverse architectures (ResNet, Vision Transformers and MLP-Mixer) using three different image-text datasets. With the transformer-based pre-trained ViT-g/14 model, the LiT model achieves 84.5% zero-shot transfer accuracy on the ImageNet test set, and 81.1% on the challenging out-of-distribution ObjectNet test set.
-
Recently, large-scale synthetic datasets are shown to be very useful for generalizable person re-identification. However, synthesized persons in existing datasets are mostly cartoon-like and in random dress collocation, which limits their performance. To address this, in this work, an automatic approach is proposed to directly clone the whole outfits from real-world person images to virtual 3D characters, such that any virtual person thus created will appear very similar to its real-world counterpart. Specifically, based on UV texture mapping, two cloning methods are designed, namely registered clothes mapping and homogeneous cloth expansion. Given clothes keypoints detected on person images and labeled on regular UV maps with clear clothes structures, registered mapping applies perspective homography to warp real-world clothes to the counterparts on the UV map. As for invisible clothes parts and irregular UV maps, homogeneous expansion segments a homogeneous area on clothes as a realistic cloth pattern or cell, and expand the cell to fill the UV map. Furthermore, a similarity-diversity expansion strategy is proposed, by clustering person images, sampling images per cluster, and cloning outfits for 3D character generation. This way, virtual persons can be scaled up densely in visual similarity to challenge model learning, and diversely in population to enrich sample distribution. Finally, by rendering the cloned characters in Unity3D scenes, a more realistic virtual dataset called ClonedPerson is created, with 5,621 identities and 887,766 images. Experimental results show that the model trained on ClonedPerson has a better generalization performance, superior to that trained on other popular real-world and synthetic person re-identification datasets. The ClonedPerson project is available at https://github.com/Yanan-Wang-cs/ClonedPerson.
-
We present GeoNeRF, a generalizable photorealistic novel view synthesis method based on neural radiance fields. Our approach consists of two main stages: a geometry reasoner and a renderer. To render a novel view, the geometry reasoner first constructs cascaded cost volumes for each nearby source view. Then, using a Transformer-based attention mechanism and the cascaded cost volumes, the renderer infers geometry and appearance, and renders detailed images via classical volume rendering techniques. This architecture, in particular, allows sophisticated occlusion reasoning, gathering information from consistent source views. Moreover, our method can easily be fine-tuned on a single scene, and renders competitive results with per-scene optimized neural rendering methods with a fraction of computational cost. Experiments show that GeoNeRF outperforms state-of-the-art generalizable neural rendering models on various synthetic and real datasets. Lastly, with a slight modification to the geometry reasoner, we also propose an alternative model that adapts to RGBD images. This model directly exploits the depth information often available thanks to depth sensors. The implementation code is available at https://www.idiap.ch/paper/geonerf.
-
Photo retouching finds many applications in various fields. However, most existing methods are designed for global retouching and seldom pay attention to the local region, while the latter is actually much more tedious and time-consuming in photography pipelines. In this paper, we propose a novel adaptive blend pyramid network, which aims to achieve fast local retouching on ultra high-resolution photos. The network is mainly composed of two components: a context-aware local retouching layer (LRL) and an adaptive blend pyramid layer (BPL). The LRL is designed to implement local retouching on low-resolution images, giving full consideration of the global context and local texture information, and the BPL is then developed to progressively expand the low-resolution results to the higher ones, with the help of the proposed adaptive blend module and refining module. Our method outperforms the existing methods by a large margin on two local photo retouching tasks and exhibits excellent performance in terms of running speed, achieving real-time inference on 4K images with a single NVIDIA Tesla P100 GPU. Moreover, we introduce the first high-definition cloth retouching dataset CRHD-3K to promote the research on local photo retouching. The dataset is available at https://github.com/youngLBW/CRHD-3K.
-
Object pose estimation is crucial for robotic applications and augmented reality. Beyond instance level 6D object pose estimation methods, estimating category-level pose and shape has become a promising trend. As such, a new research field needs to be supported by well-designed datasets. To provide a benchmark with high-quality ground truth annotations to the community, we introduce a multimodal dataset for category-level object pose estimation with photometrically challenging objects termed PhoCaL. PhoCaL comprises 60 high quality 3D models of household objects over 8 categories including highly reflective, transparent and symmetric objects. We developed a novel robot-supported multi-modal (RGB, depth, polarisation) data acquisition and annotation process. It ensures sub-millimeter accuracy of the pose for opaque textured, shiny and transparent objects, no motion blur and perfect camera synchronisation. To set a benchmark for our dataset, state-of-the-art RGB-D and monocular RGB methods are evaluated on the challenging scenes of PhoCaL.
-
Most existing deep learning (DL)-based video restoration methods focus on the network structure design to better extract temporal features but ignore how to utilize these extracted temporal features efficiently. The temporal features usually contain various noisy and irrelative information, and they may interfere with the restoration of the current frame. This paper proposes learning noise-robust feature representations to help video restoration. From information theory, we know the noisy data generally has a high degree of uncertainty, thus we design a neural compression module to filter the noise with large uncertainty and refine the features. Our compression module adopts a spatial-channel-wise quantization mechanism to adaptively filter the noise and purify the features with different content characteristics to achieve robustness to noise. The information entropy loss is used to guide the learning of the compression module and helps it preserve the most useful information. Experiments show that our method can significantly boost the performance on video denoising. Under noise level 50, we obtain 0.13 dB improvement over BasicVSR++ with only 0.23x FLOPs. Meanwhile, our method also achieves SOTA results on video deraining and dehazing.
-
Modern object detectors have achieved impressive progress under the close-set setup. However, open-set object detection (OSOD) remains challenging since objects of unknown categories are often misclassified to existing known classes. In this work, we propose to identify unknown objects by separating high/low-density regions in the latent space, based on the consensus that unknown objects are usually distributed in low-density latent regions. As traditional threshold-based methods only maintain limited low-density regions, which cannot cover all unknown objects, we present a novel Open-set Detector (OpenDet) with expanded low-density regions. To this aim, we equip OpenDet with two learners, Contrastive Feature Learner (CFL) and Unknown Probability Learner (UPL). CFL performs instance-level contrastive learning to encourage compact features of known classes, leaving more low-density regions for unknown classes; UPL optimizes unknown probability based on the uncertainty of predictions, which further divides more low-density regions around the cluster of known classes. Thus, unknown objects in low-density regions can be easily identified with the learned unknown probability. Extensive experiments demonstrate that our method can significantly improve the OSOD performance, e.g., OpenDet reduces the Absolute Open-Set Errors by 25%-35% on six OSOD benchmarks. Code is available at: https://github.com/csuhan/opendet2.
-
Image manipulation dates back long before the deep learning era. The classical prevailing approaches were based on maximizing patch similarity between the input and generated output. Recently, single-image GANs were introduced as a superior and more sophisticated solution to image manipulation tasks. Moreover, they offered the opportunity not only to manipulate a given image, but also to generate a large and diverse set of different outputs from a single natural image. This gave rise to new tasks, which are considered "DL-only". However, despite their impressiveness, single-image GANs require long training time (usually hours) for each image and each task and often suffer from visual artifacts. In this paper we revisit the classical patch-based methods, and show that - unlike previously believed -- classical methods can be adapted to tackle these novel "GAN-only" tasks. Moreover, they do so better and faster than single-image GAN-based methods. More specifically, we show that: (i) by introducing slight modifications, classical patch-based methods are able to unconditionally generate diverse images based on a single natural image; (ii) the generated output visual quality exceeds that of single-image GANs by a large margin (confirmed both quantitatively and qualitatively); (iii) they are orders of magnitude faster (runtime reduced from hours to seconds).
-
In this paper, we present Uformer, an effective and efficient Transformer-based architecture for image restoration, in which we build a hierarchical encoder-decoder network using the Transformer block. In Uformer, there are two core designs. First, we introduce a novel locally-enhanced window (LeWin) Transformer block, which performs non-overlapping window-based self-attention instead of global self-attention. It significantly reduces the computational complexity on high resolution feature map while capturing local context. Second, we propose a learnable multi-scale restoration modulator in the form of a multi-scale spatial bias to adjust features in multiple layers of the Uformer decoder. Our modulator demonstrates superior capability for restoring details for various image restoration tasks while introducing marginal extra parameters and computational cost. Powered by these two designs, Uformer enjoys a high capability for capturing both local and global dependencies for image restoration. To evaluate our approach, extensive experiments are conducted on several image restoration tasks, including image denoising, motion deblurring, defocus deblurring and deraining. Without bells and whistles, our Uformer achieves superior or comparable performance compared with the state-of-the-art algorithms. The code and models are available at https://github.com/ZhendongWang6/Uformer.
-
Pose Guided Person Image Generation (PGPIG) is the task of transforming a person image from the source pose to a given target pose. Most of the existing methods only focus on the ill-posed source-to-target task and fail to capture reasonable texture mapping. To address this problem, we propose a novel Dual-task Pose Transformer Network (DPTN), which introduces an auxiliary task (i.e., source-tosource task) and exploits the dual-task correlation to promote the performance of PGPIG. The DPTN is of a Siamese structure, containing a source-to-source self-reconstruction branch, and a transformation branch for source-to-target generation. By sharing partial weights between them, the knowledge learned by the source-to-source task can effectively assist the source-to-target learning. Furthermore, we bridge the two branches with a proposed Pose Transformer Module (PTM) to adaptively explore the correlation between features from dual tasks. Such correlation can establish the fine-grained mapping of all the pixels between the sources and the targets, and promote the source texture transmission to enhance the details of the generated target images. Extensive experiments show that our DPTN outperforms state-of-the-arts in terms of both PSNR and LPIPS. In addition, our DPTN only contains 9.79 million parameters, which is significantly smaller than other approaches. Our code is available at: https://github.com/PangzeCheung/Dual-task-Pose-Transformer-Network.
-
In portraits, eyeglasses may occlude facial regions and generate cast shadows on faces, which degrades the performance of many techniques like face verification and expression recognition. Portrait eyeglasses removal is critical in handling these problems. However, completely removing the eyeglasses is challenging because the lighting effects (e.g., cast shadows) caused by them are often complex. In this paper, we propose a novel framework to remove eyeglasses as well as their cast shadows from face images. The method works in a detect-then-remove manner, in which eyeglasses and cast shadows are both detected and then removed from images. Due to the lack of paired data for supervised training, we present a new synthetic portrait dataset with both intermediate and final supervisions for both the detection and removal tasks. Furthermore, we apply a cross-domain technique to fill the gap between the synthetic and real data. To the best of our knowledge, the proposed technique is the first to remove eyeglasses and their cast shadows simultaneously. The code and synthetic dataset are available at https://github.com/StoryMY/take-off-eyeglasses.
-
We present a new neural representation, called Neural Ray (NeuRay), for the novel view synthesis task. Recent works construct radiance fields from image features of input views to render novel view images, which enables the generalization to new scenes. However, due to occlusions, a 3D point may be invisible to some input views. On such a 3D point, these generalization methods will include inconsistent image features from invisible views, which interfere with the radiance field construction. To solve this problem, we predict the visibility of 3D points to input views within our NeuRay representation. This visibility enables the radiance field construction to focus on visible image features, which significantly improves its rendering quality. Meanwhile, a novel consistency loss is proposed to refine the visibility in NeuRay when finetuning on a specific scene. Experiments demonstrate that our approach achieves state-of-the-art performance on the novel view synthesis task when generalizing to unseen scenes and outperforms per-scene optimization methods after finetuning.
-
Group re-identification (GReID) attempts to correctly associate groups with the same members under different cameras. The main challenge is how to resist the membership and layout variations. Existing works attempt to incorporate layout modeling on the basis of appearance features to achieve robust group representations. However, layout ambiguity is introduced because these methods only consider the 2D layout on the imaging plane. In this paper, we overcome the above limitations by 3D layout modeling. Specifically, we propose a novel 3D transformer (3DT) that reconstructs the relative 3D layout relationship among members, then applies sampling and quantification to preset a series of layout tokens along three dimensions, and selects the corresponding tokens as layout features for each member. Furthermore, we build a synthetic GReID dataset, City1M, including 1.84M images, 45K persons and 11.5K groups with 3D annotations to alleviate data shortages and poor annotations. To the best of our knowledge, 3DT is the first work to address GReID with 3D perspective, and the City1M is the currently largest dataset. Several experiments show the superiority of our 3DT and City1M. Our project has been released on https://github.com/LinlyAC/City1M-dataset.
-
Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely on explicit class semantics obtained from large labeled datasets, and out-of-domain evaluation performance drops significantly. Here we propose a novel approach for mask proposals, Generic Grouping Networks (GGNs), constructed without semantic supervision. Our approach combines a local measure of pixel affinity with instance-level mask supervision, producing a training regimen designed to make the model as generic as the data diversity allows. We introduce a method for predicting Pairwise Affinities (PA), a learned local relationship between pairs of pixels. PA generalizes very well to unseen categories. From PA we construct a large set of pseudo-ground-truth instance masks; combined with human-annotated instance masks we train GGNs and significantly outperform the SOTA on open-world instance segmentation on various benchmarks including COCO, LVIS, ADE20K, and UVO.
-
Object detection under imperfect data receives great attention recently. Weakly supervised object detection (WSOD) suffers from severe localization issues due to the lack of instance-level annotation, while semi-supervised object detection (SSOD) remains challenging led by the inter-image discrepancy between labeled and unlabeled data. In this study, we propose the Single Instance annotated Object Detection (SIOD), requiring only one instance annotation for each existing category in an image. Degraded from inter-task (WSOD) or inter-image (SSOD) discrepancies to the intra-image discrepancy, SIOD provides more reliable and rich prior knowledge for mining the rest of unlabeled instances and trades off the annotation cost and performance. Under the SIOD setting, we propose a simple yet effective framework, termed Dual-Mining (DMiner), which consists of a Similarity-based Pseudo Label Generating module (SPLG) and a Pixel-level Group Contrastive Learning module (PGCL). SPLG firstly mines latent instances from feature representation space to alleviate the annotation missing problem. To avoid being misled by inaccurate pseudo labels, we propose PGCL to boost the tolerance to false pseudo labels. Extensive experiments on MS COCO verify the feasibility of the SIOD setting and the superiority of the proposed method, which obtains consistent and significant improvements compared to baseline methods and achieves comparable results with fully supervised object detection (FSOD) methods with only 40% instances annotated.
-
Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios. In this paper, we develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. To be specific, we establish a cascaded illumination learning process with weight sharing to handle this task. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage, producing the gains that only use the single basic block for inference (yet has not been exploited in previous works), which drastically diminishes computation cost. We then define the unsupervised training loss to elevate the model capability that can adapt general scenes. Further, we make comprehensive explorations to excavate SCI's inherent properties (lacking in existing works) including operation-insensitive adaptability (acquiring stable performance under the settings of different simple operations) and model-irrelevant generality (can be applied to illumination-based existing works to improve performance). Finally, plenty of experiments and ablation studies fully indicate our superiority in both quality and efficiency. Applications on low-light face detection and nighttime semantic segmentation fully reveal the latent practical values for SCI. The source code is available at https://github.com/vis-opt-group/SCI.
-
In this paper, we present a novel approach to incrementally learn an Abstract Model of an unknown environment, and show how an agent can reuse the learned model for tackling the Object Goal Navigation task. The Abstract Model is a finite state machine in which each state is an abstraction of a state of the environment, as perceived by the agent in a certain position and orientation. The perceptions are high-dimensional sensory data (e.g., RGB-D images), and the abstraction is reached by exploiting image segmentation and the Taskonomy model bank. The learning of the Abstract Model is accomplished by executing actions, observing the reached state, and updating the Abstract Model with the acquired information. The learned models are memorized by the agent, and they are reused whenever it recognizes to be in an environment that corresponds to the stored model. We investigate the effectiveness of the proposed approach for the Object Goal Navigation task, relying on public benchmarks. Our results show that the reuse of learned Abstract Models can boost performance on Object Goal Navigation.
-
Action recognition models have shown a promising capability to classify human actions in short video clips. In a real scenario, multiple correlated human actions commonly occur in particular orders, forming semantically meaningful human activities. Conventional action recognition approaches focus on analyzing single actions. However, they fail to fully reason about the contextual relations between adjacent actions, which provide potential temporal logic for understanding long videos. In this paper, we propose a prompt-based framework, Bridge-Prompt (Br-Prompt), to model the semantics across adjacent actions, so that it simultaneously exploits both out-of-context and contextual information from a series of ordinal actions in instructional videos. More specifically, we reformulate the individual action labels as integrated text prompts for supervision, which bridge the gap between individual action semantics. The generated text prompts are paired with corresponding video clips, and together co-train the text encoder and the video encoder via a contrastive approach. The learned vision encoder has a stronger capability for ordinal-action-related downstream tasks, e.g. action segmentation and human activity recognition. We evaluate the performances of our approach on several video datasets: Georgia Tech Egocentric Activities (GTEA), 50Salads, and the Breakfast dataset. Br-Prompt achieves state-of-the-art on multiple benchmarks. Code is available at: https://github.com/ttlmh/Bridge-Prompt.
-
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers semantic similarity and instance similarity. In SimMatch, the consistency regularization will be applied on both semantic-level and instance-level. The different augmented views of the same instance are encouraged to have the same class prediction and similar similarity relationship respected to other instances. Next, we instantiated a labeled memory buffer to fully leverage the ground truth labels on instance-level and bridge the gaps between the semantic and instance similarities. Finally, we proposed the unfolding and aggregation operation which allows these two similarities be isomorphically transformed with each other. In this way, the semantic and instance pseudo-labels can be mutually propagated to generate more high-quality and reliable matching targets. Extensive experimental results demonstrate that SimMatch improves the performance of semi-supervised learning tasks across different benchmark datasets and different settings. Notably, with 400 epochs of training, SimMatch achieves 67.2%, and 74.4% Top-1 Accuracy with 1% and 10% labeled examples on ImageNet, which significantly outperforms the baseline methods and is better than previous semi-supervised learning frameworks.
-
This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors. Specifically, we construct a distinct generative model and design an objective function that encourages the generative model to produce causal, compact, and faithful explanations. This is achieved by isolating the causal factors in the latent space of graphs by maximizing the information flow measurements. We theoretically analyze the cause-effect relationships in the proposed causal graph, identify node attributes as confounders between graphs and GNN predictions, and circumvent such confounder effect by leveraging the backdoor adjustment formula. Our framework is compatible with any GNNs, and it does not require access to the process by which the target GNN produces its predictions. In addition, it does not rely on the linear-independence assumption of the explained features, nor require prior knowledge on the graph learning tasks. We show a proof-of-concept of OrphicX on canonical classification problems on graph data. In particular, we analyze the explanatory subgraphs obtained from explanations for molecular graphs (i.e., Mutag) and quantitatively evaluate the explanation performance with frequently occurring subgraph patterns. Empirically, we show that OrphicX can effectively identify the causal semantics for generating causal explanations, significantly outperforming its alternatives.
-
Hands are often severely occluded by objects, which makes 3D hand mesh estimation challenging. Previous works often have disregarded information at occluded regions. However, we argue that occluded regions have strong correlations with hands so that they can provide highly beneficial information for complete 3D hand mesh estimation. Thus, in this work, we propose a novel 3D hand mesh estimation network HandOccNet, that can fully exploits the information at occluded regions as a secondary means to enhance image features and make it much richer. To this end, we design two successive Transformer-based modules, called feature injecting transformer (FIT) and self-enhancing transformer (SET). FIT injects hand information into occluded region by considering their correlation. SET refines the output of FIT by using a self-attention mechanism. By injecting the hand information to the occluded region, our HandOccNet reaches the state-of-the-art performance on 3D hand mesh benchmarks that contain challenging hand-object occlusions. The codes are available in: https://github.com/namepllet/HandOccNet.
-
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing time. In this paper, we present EfficientNeRF as an efficient NeRF-based method to represent 3D scene and synthesize novel-view images. Although several ways exist to accelerate the training or testing process, it is still difficult to much reduce time for both phases simultaneously. We analyze the density and weight distribution of the sampled points then propose valid and pivotal sampling at the coarse and fine stage, respectively, to significantly improve sampling efficiency. In addition, we design a novel data structure to cache the whole scene during testing to accelerate the testing speed. Overall, our method can reduce over 88% of training time, reach testing speed of around 200 to 500 FPS, while still achieving competitive accuracy. Experiments prove that our method promotes the practicality of NeRF in the real world and enables many applications.
-
We study societal bias amplification in image captioning. Image captioning models have been shown to perpetuate gender and racial biases, however, metrics to measure, quantify, and evaluate the societal bias in captions are not yet standardized. We provide a comprehensive study on the strengths and limitations of each metric, and propose LIC, a metric to study captioning bias amplification. We argue that, for image captioning, it is not enough to focus on the correct prediction of the protected attribute, and the whole context should be taken into account. We conduct extensive evaluation on traditional and state-of-the-art image captioning models, and surprisingly find that, by only focusing on the protected attribute prediction, bias mitigation models are unexpectedly amplifying bias.
-
Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the learning of interaction between agents and objects. We introduce the task of semantic action-conditional video prediction, which uses semantic action labels to describe those interactions and can be regarded as an inverse problem of action recognition. The challenge of this new task primarily lies in how to effectively inform the model of semantic action information. Inspired by the idea of Mixture of Experts, we embody each abstract label by a structured combination of various visual concept learners and propose a novel video prediction model, Modular Action Concept Network (MAC). Our method is evaluated on two newly designed synthetic datasets, CLEVR-Building-Blocks and Sapien-Kitchen, and one real-world dataset called Tower-Creation. Extensive experiments demonstrate that MAC can correctly condition on given instructions and generate corresponding future frames without need of bounding boxes. We further show that the trained model can make out-of-distribution generalization, be quickly adapted to new object categories and exploit its learnt features for object detection, showing the progression towards higher-level cognitive abilities. More visualizations can be found at http://www.pair.toronto.edu/mac/.
-
Despite the tantalizing success in a broad of vision tasks, transformers have not yet demonstrated on-par ability as ConvNets in high-resolution image generative modeling. In this paper, we seek to explore using pure transformers to build a generative adversarial network for high-resolution image synthesis. To this end, we believe that the local attention is crucial to strike the balance between computational efficiency and modeling capacity. Hence, the proposed generator adopts Swin transformer in a style-based architecture. To achieve larger receptive field, we propose double attention which simultaneously leverages the context of the local and the shifted windows, leading to improved generation quality. Moreover, we show that offering the knowledge of the absolute position that has lost in window-based transformers greatly benefits the generation quality. The proposed StyleSwin is scalable to high resolutions, with both the coarse geometry and fine structures benefit from the strong expressivity of transformers. However, blocking artifacts occur during high-resolution synthesis because performing the local attention in a block-wise manner may break the spatial coherency. To solve this, we empirically investigate various solutions, among which we find that employing a wavelet discriminator to examine the spectral discrepancy effectively suppresses the artifacts. Extensive experiments show the superiority over prior transformer-based GANs, especially on high resolutions, e.g., 1024x1024. The StyleSwin, without complex training strategies, excelling over StyleGAN on CelebA-HQ 1024, and achieves on-par performance on FFHQ-1024, proving the promise of using transformers for high-resolution image generation. The code and pretrained models are available at https://github.com/microsoft/StyleSwin.
-
Vision-and-language Navigation (VLN) task requires an embodied agent to navigate to a remote location following a natural language instruction. Previous methods usually adopt a sequence model (e.g., Transformer and LSTM) as the navigator. In such a paradigm, the sequence model predicts action at each step through a maintained navigation state, which is generally represented as a one-dimensional vector. However, the crucial navigation clues (i.e., object-level environment layout) for embodied navigation task is discarded since the maintained vector is essentially unstructured. In this paper, we propose a novel Structured state-Evolution (SEvol) model to effectively maintain the environment layout clues for VLN. Specifically, we utilise the graph-based feature to represent the navigation state instead of the vector-based state. Accordingly, we devise a Reinforced Layout clues Miner (RLM) to mine and detect the most crucial layout graph for long-term navigation via a customised reinforcement learning strategy. Moreover, the Structured Evolving Module (SEM) is proposed to maintain the structured graph-based state during navigation, where the state is gradually evolved to learn the object-level spatial-temporal relationship. The experiments on the R2R and R4R datasets show that the proposed SEvol model improves VLN models' performance by large margins, e.g., +3% absolute SPL accuracy for NvEM and +8% for EnvDrop on the R2R test set.
-
The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos. Most prior works deal with the open-set visual speech recognition problem by adapting existing automatic speech recognition techniques on top of trivially pooled visual features. Instead, in this paper, we focus on the unique challenges encountered in lip reading and propose tailored solutions. To this end, we make the following contributions: (1) we propose an attention-based pooling mechanism to aggregate visual speech representations; (2) we use sub-word units for lip reading for the first time and show that this allows us to better model the ambiguities of the task; (3) we propose a model for Visual Speech Detection (VSD), trained on top of the lip reading network. Following the above, we obtain state-of-the-art results on the challenging LRS2 and LRS3 benchmarks when training on public datasets, and even surpass models trained on large-scale industrial datasets by using an order of magnitude less data. Our best model achieves 22.6% word error rate on the LRS2 dataset, a performance unprecedented for lip reading models, significantly reducing the performance gap between lip reading and automatic speech recognition. Moreover, on the AVA-ActiveSpeaker benchmark, our VSD model surpasses all visual-only baselines and even outperforms several recent audio-visual methods.
-
The development of online economics arouses the demand of generating images of models on product clothes, to display new clothes and promote sales. However, the expensive proprietary model images challenge the existing image virtual try-on methods in this scenario, as most of them need to be trained on considerable amounts of model images accompanied with paired clothes images. In this paper, we propose a cheap yet scalable weakly-supervised method called Deep Generative Projection (DGP) to address this specific scenario. Lying in the heart of the proposed method is to imitate the process of human predicting the wearing effect, which is an unsupervised imagination based on life experience rather than computation rules learned from supervisions. Here a pretrained StyleGAN is used to capture the practical experience of wearing. Experiments show that projecting the rough alignment of clothing and body onto the StyleGAN space can yield photo-realistic wearing results. Experiments on real scene proprietary model images demonstrate the superiority of DGP over several state-of-the-art supervised methods when generating clothing model images.
-
Multi-view clustering has received increasing attention due to its effectiveness in fusing complementary information without manual annotations. Most previous methods hold the assumption that each instance appears in all views. However, it is not uncommon to see that some views may contain some missing instances, which gives rise to incomplete multi-view clustering (IMVC) in literature. Although many IMVC methods have been recently proposed, they always encounter high complexity and expensive time expenditure from being applied into large-scale tasks. In this paper, we present a flexible highly-efficient incomplete large-scale multi-view clustering approach based on bipartite graph framework to solve these issues. Specifically, we formalize multi-view anchor learning and incomplete bipartite graph into a unified framework, which coordinates with each other to boost cluster performance. By introducing the flexible bipartite graph framework to handle IMVC for the first practice, our proposed method enjoys linear complexity respecting to instance numbers, which is more applicable for large-scale IMVC tasks. Comprehensive experimental results on various benchmark datasets demonstrate the effectiveness and efficiency of our proposed algorithm against other IMVC competitors.
-
A fundamental challenge for machine learning models is generalizing to out-of-distribution (OOD) data, in part due to spurious correlations. To tackle this challenge, we first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG). We relax this non-trivial constrained optimization problem to a tractable form with finite-dimensional parameterization and empirical approximation. Then a theoretical analysis of the extent to which the above transformations deviates from the original problem is provided. Based on the transformation, we propose a primal-dual algorithm for joint representation disentanglement and domain generalization. In contrast to traditional approaches based on domain adversarial training and domain labels, DDG jointly learns semantic and variation encoders for disentanglement, enabling flexible manipulation and augmentation on training data. DDG aims to learn intrinsic representations of semantic concepts that are invariant to nuisance factors and generalizable across domains. Comprehensive experiments on popular benchmarks show that DDG can achieve competitive OOD performance and uncover interpretable salient structures within data.
-
Guided depth super-resolution (GDSR) is an essential topic in multi-modal image processing, which reconstructs high-resolution (HR) depth maps from low-resolution ones collected with suboptimal conditions with the help of HR RGB images of the same scene. To solve the challenges in interpreting the working mechanism, extracting cross-modal features and RGB texture over-transferred, we propose a novel Discrete Cosine Transform Network (DCTNet) to alleviate the problems from three aspects. First, the Discrete Cosine Transform (DCT) module reconstructs the multi-channel HR depth features by using DCT to solve the channel-wise optimization problem derived from the image domain. Second, we introduce a semi-coupled feature extraction module that uses shared convolutional kernels to extract common information and private kernels to extract modality-specific information. Third, we employ an edge attention mechanism to highlight the contours informative for guided upsampling. Extensive quantitative and qualitative evaluations demonstrate the effectiveness of our DCTNet, which outperforms previous state-of-the-art methods with a relatively small number of parameters. Codes are available at https://github.com/Zhaozixiang1228/GDSR-DCTNet.
-
Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance. In this paper, we tackle the new problem of joint semantic, affordance and attribute parsing. However, successfully resolving it requires a model to capture long-range dependency, learn from weakly aligned data and properly balance sub-tasks during training. To this end, we propose an attention-based architecture named Cerberus and a tailored training framework. Our method effectively addresses aforementioned challenges and achieves state-of-the-art performance on all three tasks. Moreover, an in-depth analysis shows concept affinity consistent with human cognition, which inspires us to explore the possibility of extremely low-shot learning. Surprisingly, Cerberus achieves strong results using only 0.1%-1% annotation. Visualizations further confirm that this success is credited to common attention maps across tasks. Code and models can be accessed at https://github.com/OPEN-AIR-SUN/Cerberus.
-
Standard semi-supervised learning (SSL) using class-balanced datasets has shown great progress to leverage unlabeled data effectively. However, the more realistic setting of class-imbalanced data - called imbalanced SSL - is largely underexplored and standard SSL tends to underperform. In this paper, we propose a novel co-learning framework (CoSSL), which decouples representation and classifier learning while coupling them closely. To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE) for classifier learning. Furthermore, the current evaluation protocol for imbalanced SSL focuses only on balanced test sets, which has limited practicality in real-world scenarios. Therefore, we further conduct a comprehensive evaluation under various shifted test distributions. In experiments, we show that our approach outperforms other methods over a large range of shifted distributions, achieving state-of-the-art performance on benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our code will be made publicly available.
-
This paper studies the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. However, by relying on appearance alone, these methods fail to separate objects from the background in cluttered scenes. This is a fundamental limitation since the definition of an object is inherently ambiguous and context-dependent. To resolve this ambiguity, we choose to focus on dynamic objects -- entities that can move independently in the world. We then scale the recent auto-encoder based frameworks for unsupervised object discovery from toy synthetic images to complex real-world scenes. To this end, we simplify their architecture, and augment the resulting model with a weak learning signal from general motion segmentation algorithms. Our experiments demonstrate that, despite only capturing a small subset of the objects that move, this signal is enough to generalize to segment both moving and static instances of dynamic objects. We show that our model scales to a newly collected, photo-realistic synthetic dataset with street driving scenarios. Additionally, we leverage ground truth segmentation and flow annotations in this dataset for thorough ablation and evaluation. Finally, our experiments on the real-world KITTI benchmark demonstrate that the proposed approach outperforms both heuristic- and learning-based methods by capitalizing on motion cues.
-
Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be irrelevant when it is not significantly related to objects/scenes. We propose an end-to-end trainable network that mines implicit contextual knowledge behind scene text image and enhance the semantics and correlation to fine-tune the image representation. Unlike the existing methods, our model integrates three modalities: visual feature extraction, text semantics extraction, and correlating background knowledge to fine-grained image classification. Specifically, we employ KnowBert to retrieve relevant knowledge for semantic representation and combine it with image features for fine-grained classification. Experiments on two benchmark datasets, Con-Text, and Drink Bottle, show that our method outperforms the state-of-the-art by 3.72% mAP and 5.39% mAP, respectively. To further validate the effectiveness of the proposed method, we create a new dataset on crowd activity recognition for the evaluation. The source code, new dataset, and pre-trained models of this work will be publicly available.
-
Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from this trend as they require spatially-diverse representations. However, learning dense representations is challenging, as in the unsupervised context it is not clear how to guide the model to learn representations that correspond to various potential object categories. In this paper, we argue that self-supervised learning of object parts is a solution to this issue. Object parts are generalizable: they are a priori independent of an object definition, but can be grouped to form objects a posteriori. To this end, we leverage the recently proposed Vision Transformer's capability of attending to objects and combine it with a spatially dense clustering task for fine-tuning the spatial tokens. Our method surpasses the state-of-the-art on three semantic segmentation benchmarks by 17%-3%, showing that our representations are versatile under various object definitions. Finally, we extend this to fully unsupervised segmentation - which refrains completely from using label information even at test-time - and demonstrate that a simple method for automatically merging discovered object parts based on community detection yields substantial gains.
-
Tracking objects in 3D space and predicting their 6DoF pose is an essential task in computer vision. State-of-the-art approaches often rely on object texture to tackle this problem. However, while they achieve impressive results, many objects do not contain sufficient texture, violating the main underlying assumption. In the following, we thus propose ICG, a novel probabilistic tracker that fuses region and depth information and only requires the object geometry. Our method deploys correspondence lines and points to iteratively refine the pose. We also implement robust occlusion handling to improve performance in real-world settings. Experiments on the YCB-Video, OPT, and Choi datasets demonstrate that, even for textured objects, our approach outperforms the current state of the art with respect to accuracy and robustness. At the same time, ICG shows fast convergence and outstanding efficiency, requiring only 1.3 ms per frame on a single CPU core. Finally, we analyze the influence of individual components and discuss our performance compared to deep learning-based methods. The source code of our tracker is publicly available.
-
We present a novel structured light technique that uses Single Photon Avalanche Diode (SPAD) arrays to enable 3D scanning at high-frame rates and low-light levels. This technique, called "Single-Photon Structured Light", works by sensing binary images that indicates the presence or absence of photon arrivals during each exposure; the SPAD array is used in conjunction with a high-speed binary projector, with both devices operated at speeds as high as 20 kHz. The binary images that we acquire are heavily influenced by photon noise and are easily corrupted by ambient sources of light. To address this, we develop novel temporal sequences using error correction codes that are designed to be robust to short-range effects like projector and camera defocus as well as resolution mismatch between the two devices. Our lab prototype is capable of 3D imaging in challenging scenarios involving objects with extremely low albedo or undergoing fast motion, as well as scenes under strong ambient illumination.
-
Image deblurring is an ill-posed problem with multiple plausible solutions for a given input image. However, most existing methods produce a deterministic estimate of the clean image and are trained to minimize pixel-level distortion. These metrics are known to be poorly correlated with human perception, and often lead to unrealistic reconstructions. We present an alternative framework for blind deblurring based on conditional diffusion models. Unlike existing techniques, we train a stochastic sampler that refines the output of a deterministic predictor and is capable of producing a diverse set of plausible reconstructions for a given input. This leads to a significant improvement in perceptual quality over existing state-of-the-art methods across multiple standard benchmarks. Our predict-and-refine approach also enables much more efficient sampling compared to typical diffusion models. Combined with a carefully tuned network architecture and inference procedure, our method is competitive in terms of distortion metrics such as PSNR. These results show clear benefits of our diffusion-based method for deblurring and challenge the widely used strategy of producing a single, deterministic reconstruction.
-
Observing that the 3D captioning task and the 3D grounding task contain both shared and complementary information in nature, in this work, we propose a unified framework to jointly solve these two distinct but closely related tasks in a synergistic fashion, which consists of both shared task-agnostic modules and lightweight task-specific modules. On one hand, the shared task-agnostic modules aim to learn precise locations of objects, fine-grained attribute features to characterize different objects, and complex relations between objects, which benefit both captioning and visual grounding. On the other hand, by casting each of the two tasks as the proxy task of another one, the lightweight task-specific modules solve the captioning task and the grounding task respectively. Extensive experiments and ablation study on three 3D vision and language datasets demonstrate that our joint training framework achieves significant performance gains for each individual task and finally improves the state-of-the-art performance for both captioning and grounding tasks.
-
The dominant CNN-based methods for cross-view image geo-localization rely on polar transform and fail to model global correlation. We propose a pure transformer-based approach (TransGeo) to address these limitations from a different perspective. TransGeo takes full advantage of the strengths of transformer related to global information modeling and explicit position information encoding. We further leverage the flexibility of transformer input and propose an attention-guided non-uniform cropping method, so that uninformative image patches are removed with negligible drop on performance to reduce computation cost. The saved computation can be reallocated to increase resolution only for informative patches, resulting in performance improvement with no additional computation cost. This "attend and zoom-in" strategy is highly similar to human behavior when observing images. Remarkably, TransGeo achieves state-of-the-art results on both urban and rural datasets, with significantly less computation cost than CNN-based methods. It does not rely on polar transform and infers faster than CNN-based methods. Code is available at https://github.com/Jeff-Zilence/TransGeo2022.
-
In the paradigm of object detection, the decision head is an important part, which affects detection performance significantly. Yet how to design a high-performance decision head remains to be an open issue. In this paper, we propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection. First, we disentangle the decision choices and prediction values by plugging soft decision trees into neural networks. To facilitate the effective learning, we propose the randomized decision routing with node selective and associative losses, which can boost the feature representative learning and network decision simultaneously. Second, we develop the decision head for object detection with narrow branches to generate the routing probabilities and masks, for the purpose of obtaining divergent decisions from different nodes. We name this approach as the randomized decision routing for object detection, abbreviated as R(Det)^2. Experiments on MS-COCO dataset demonstrate that R(Det)^2 is effective to improve the detection performance. Equipped with existing detectors, it achieves 1.4~ 3.6% AP improvement. Code will be released soon.
-
Low-light image enhancement, a pervasive but challenging problem, plays a central role in enhancing the visibility of an image captured in a poor illumination environment. Due to the fact that not all photons can pass the Bayer-Filter on the sensor of the color camera, in this work, we first present a De-Bayer-Filter simulator based on deep neural networks to generate a monochrome raw image from the colored raw image. Next, a fully convolutional network is proposed to achieve the low-light image enhancement by fusing colored raw data with synthesized monochrome data. Channel-wise attention is also introduced to the fusion process to establish a complementary interaction between features from colored and monochrome raw images. To train the convolutional networks, we propose a dataset with monochrome and color raw pairs named Mono-Colored Raw paired dataset (MCR) collected by using a monochrome camera without Bayer-Filter and a color camera with Bayer-Filter. The proposed pipeline take advantages of the fusion of the virtual monochrome and the color raw images and our extensive experiments indicate that significant improvement can be achieved by leveraging raw sensor data and data-driven learning.
-
We propose a learned method for stereo image compression that leverages the similarity of the left and right images in a stereo pair due to overlapping fields of view. The left image is compressed by a learned compression method based on an autoencoder with a hyperprior entropy model. The right image uses this information from the previously encoded left image in both the encoding and decoding stages. In particular, for the right image, we encode only the residual of its latent representation to the optimally shifted latent of the left image. On top of that, we also employ a stereo attention module to connect left and right images during decoding. The performance of the proposed method is evaluated on two benchmark stereo image datasets (Cityscapes and InStereo2K) and outperforms previous stereo image compression methods while being significantly smaller in model size.
-
We consider the object recognition problem in autonomous driving using automotive radar sensors. Comparing to Lidar sensors, radar is cost-effective and robust in all-weather conditions for perception in autonomous driving. However, radar signals suffer from low angular resolution and precision in recognizing surrounding objects. To enhance the capacity of automotive radar, in this work, we exploit the temporal information from successive ego-centric bird-eye-view radar image frames for radar object recognition. We leverage the consistency of an object's existence and attributes (size, orientation, etc.), and propose a temporal relational layer to explicitly model the relations between objects within successive radar images. In both object detection and multiple object tracking, we show the superiority of our method compared to several baseline approaches.
-
We address the problem of estimating the poses of multiple instances of the source point cloud within a target point cloud. Existing solutions require sampling a lot of hypotheses to detect possible instances and reject the outliers, whose robustness and efficiency degrade notably when the number of instances and outliers increase. We propose to directly group the set of noisy correspondences into different clusters based on a distance invariance matrix. The instances and outliers are automatically identified through clustering. Our method is robust and fast. We evaluated our method on both synthetic and real-world datasets. The results show that our approach can correctly register up to 20 instances with an F1 score of 90.46% in the presence of 70% outliers, which performs significantly better and at least 10x faster than existing methods.
-
Point cloud segmentation is fundamental in understanding 3D environments. However, current 3D point cloud segmentation methods usually perform poorly on scene boundaries, which degenerates the overall segmentation performance. In this paper, we focus on the segmentation of scene boundaries. Accordingly, we first explore metrics to evaluate the segmentation performance on scene boundaries. To address the unsatisfactory performance on boundaries, we then propose a novel contrastive boundary learning (CBL) framework for point cloud segmentation. Specifically, the proposed CBL enhances feature discrimination between points across boundaries by contrasting their representations with the assistance of scene contexts at multiple scales. By applying CBL on three different baseline methods, we experimentally show that CBL consistently improves different baselines and assists them to achieve compelling performance on boundaries, as well as the overall performance, e.g. in mIoU. The experimental results demonstrate the effectiveness of our method and the importance of boundaries for 3D point cloud segmentation. Code and model will be made publicly available at https://github.com/LiyaoTang/contrastBoundary.
-
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution
Single image super-resolution (SISR) with generative adversarial networks (GAN) has recently attracted increasing attention due to its potentials to generate rich details. However, the training of GAN is unstable, and it often introduces many perceptually unpleasant artifacts along with the generated details. In this paper, we demonstrate that it is possible to train a GAN-based SISR model which can stably generate perceptually realistic details while inhibiting visual artifacts. Based on the observation that the local statistics (e.g., residual variance) of artifact areas are often different from the areas of perceptually friendly details, we develop a framework to discriminate between GAN-generated artifacts and realistic details, and consequently generate an artifact map to regularize and stabilize the model training process. Our proposed locally discriminative learning (LDL) method is simple yet effective, which can be easily plugged in off-the-shelf SISR methods and boost their performance. Experiments demonstrate that LDL outperforms the state-of-the-art GAN based SISR methods, achieving not only higher reconstruction accuracy but also superior perceptual quality on both synthetic and real-world datasets. Codes and models are available at https://github.com/csjliang/LDL.
-
The classic active contour model raises a great promising solution to polygon-based object extraction with the progress of deep learning recently. Inspired by the physical vibration theory, we propose a contour vibration network (CVNet) for automatic building boundary delineation. Different from the previous contour models, the CVNet originally roots in the force and motion principle of contour string. Through the infinitesimal analysis and Newton's second law, we derive the spatial-temporal contour vibration model of object shapes, which is mathematically reduced to second-order differential equation. To concretize the dynamic model, we transform the vibration model into the space of image features, and reparameterize the equation coefficients as the learnable state from feature domain. The contour changes are finally evolved in a progressive mode through the computation of contour vibration equation. Both the polygon contour evolution and the model optimization are modulated to form a close-looping end-to-end network. Comprehensive experiments on three datasets demonstrate the effectiveness and superiority of our CVNet over other baselines and state-of-the-art methods for the polygon-based building extraction. The code is available at https://github.com/xzq-njust/CVNet.
-
For image segmentation, the current standard is to perform pixel-level optimization and inference in Euclidean output embedding spaces through linear hyperplanes. In this work, we show that hyperbolic manifolds provide a valuable alternative for image segmentation and propose a tractable formulation of hierarchical pixel-level classification in hyperbolic space. Hyperbolic Image Segmentation opens up new possibilities and practical benefits for segmentation, such as uncertainty estimation and boundary information for free, zero-label generalization, and increased performance in low-dimensional output embeddings.
-
In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the idea of backward compatible training (BCT) was proposed. To avoid the cost of backfilling, BCT modifies training of the new model to make its representations compatible with those of the old model. However, BCT can significantly hinder the performance of the new model. In this work, we propose a new learning paradigm for representation learning: forward compatible training (FCT). In FCT, when the old model is trained, we also prepare for a future unknown version of the model. We propose learning side-information, an auxiliary feature for each sample which facilitates future updates of the model. To develop a powerful and flexible framework for model compatibility, we combine side-information with a forward transformation from old to new embeddings. Training of the new model is not modified, hence, its accuracy is not degraded. We demonstrate significant retrieval accuracy improvement compared to BCT for various datasets: ImageNet-1k (+18.1%), Places-365 (+5.4%), and VGG-Face2 (+8.3%). FCT obtains model compatibility when the new and old models are trained across different datasets, losses, and architectures.
-
Multi-modal learning from video data has seen increased attention recently as it allows training of semantically meaningful embeddings without human annotation, enabling tasks like zero-shot retrieval and action localization. In this work, we present a multi-modal, modality agnostic fusion transformer that learns to exchange information between multiple modalities, such as video, audio, and text, and integrate them into a fused representation in a joined multi-modal embedding space. We propose to train the system with a combinatorial loss on everything at once - any combination of input modalities, such as single modalities as well as pairs of modalities, explicitly leaving out any add-ons such as position or modality encoding. At test time, the resulting model can process and fuse any number of input modalities. Moreover, the implicit properties of the transformer allow to process inputs of different lengths. To evaluate the proposed approach, we train the model on the large scale HowTo100M dataset and evaluate the resulting embedding space on four challenging benchmark datasets obtaining state-of-the-art results in zero-shot video retrieval and zero-shot video action localization. Our code for this work is also available.
-
We present techniques for scaling Swin Transformer [??] up to 3 billion parameters and making it capable of training with images of up to 1,536x1,536 resolution. By scaling up capacity and resolution, Swin Transformer sets new records on four representative vision benchmarks: 84.0% top-1 accuracy on ImageNet-V2 image classification, 63.1 / 54.4 box / mask mAP on COCO object detection, 59.9 mIoU on ADE20K semantic segmentation, and 86.8% top-1 accuracy on Kinetics-400 video action classification. We tackle issues of training instability, and study how to effectively transfer models pre-trained at low resolutions to higher resolution ones. To this aim, several novel technologies are proposed: 1) a residual post normalization technique and a scaled cosine attention approach to improve the stability of large vision models; 2) a log-spaced continuous position bias technique to effectively transfer models pre-trained at low-resolution images and windows to their higher-resolution counterparts. In addition, we share our crucial implementation details that lead to significant savings of GPU memory consumption and thus make it feasible to train large vision models with regular GPUs. Using these techniques and self-supervised pre-training, we successfully train a strong 3 billion Swin Transformer model and effectively transfer it to various vision tasks involving high-resolution images or windows, achieving the state-of-the-art accuracy on a variety of benchmarks. Code is available at https://github.com/microsoft/Swin-Transformer.
-
This paper introduces a novel framework called DT-Net for 3D mesh reconstruction and generation via Disentangled Topology. Beyond previous works, we learn a topology-aware neural template specific to each input then deform the template to reconstruct a detailed mesh while preserving the learned topology. One key insight is to decouple the complex mesh reconstruction into two sub-tasks: topology formulation and shape deformation. Thanks to the decoupling, DT-Net implicitly learns a disentangled representation for the topology and shape in the latent space. Hence, it can enable novel disentangled controls for supporting various shape generation applications, eg, remix the topologies of 3D objects, that are not achievable by previous reconstruction works. Extensive experimental results demonstrate that our method is able to produce high-quality meshes, particularly with diverse topologies, as compared with the state-of-the-art methods.
-
Backdoor attack is a type of serious security threat to deep learning models.An adversary can provide users with a model trained on poisoned data to manipulate prediction behavior in test stage using a backdoor. The backdoored models behave normally on clean images, yet can be activated and output incorrect prediction if the input is stamped with a specific trigger pattern.Most existing backdoor attacks focus on manually defining imperceptible triggers in input space without considering the abnormality of triggers' latent representations in the poisoned model.These attacks are susceptible to backdoor detection algorithms and even visual inspection.In this paper, We propose a novel and stealthy backdoor attack - DEFEAT. It poisons the clean data using adaptive imperceptible perturbation and restricts latent representation during training process to strengthen our attack's stealthiness and resistance to defense algorithms.We conduct extensive experiments on multiple image classifiers using real-world datasets to demonstrate that our attack can 1) hold against the state-of-the-art defenses, 2) deceive the victim model with high attack success without jeopardizing model utility, and 3) provide practical stealthiness on image data.
-
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network learning in both forward and backward passes. While several works have proposed different regression-friendly rotation representations, very few works have been devoted to improving the gradient backpropagating in the backward pass. In this paper, we propose a manifold-aware gradient that directly backpropagates into deep network weights. Leveraging Riemannian optimization to construct a novel projective gradient, our proposed regularized projective manifold gradient (RPMG) method helps networks achieve new state-of-the-art performance in a variety of rotation estimation tasks. Our proposed gradient layer can also be applied to other smooth manifolds such as the unit sphere. Our project page is at https://jychen18.github.io/RPMG.
-
It has been widely known that CAM (Class Activation Map) usually only activates discriminative object regions and falsely includes lots of object-related backgrounds. As only a fixed set of image-level object labels are available to the WSSS (weakly supervised semantic segmentation) model, it could be very difficult to suppress those diverse background regions consisting of open set objects. In this paper, we propose a novel Cross Language Image Matching (CLIMS) framework, based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress closely-related open background regions. In particular, we design object, background region and text label matching losses to guide the model to excite more reasonable object regions for CAM of each category. In addition, we design a co-occurring background suppression loss to prevent the model from activating closely-related background regions, with a predefined set of class-related background text descriptions. These designs enable the proposed CLIMS to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC2012 dataset show that our CLIMS significantly outperforms the previous state-of-the-art methods.
-
The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devising advanced action detectors, they still suffer from these co-occurring ingredients which often dominate the actual action content in videos. In this paper, we explore two orthogonal but complementary aspects of a video snippet, i.e., the action features and the co-occurrence features. Especially, we develop a novel auxiliary task by decoupling these two types of features within a video snippet and recombining them to generate a new feature representation with more salient action information for accurate action localization. We term our method RefactorNet, which first explicitly factorizes the action content and regularizes its co-occurrence features, and then synthesizes a new action-dominated video representation. Extensive experimental results and ablation studies on THUMOS14 and ActivityNet v1.3 demonstrate that our new representation, combined with a simple action detector, can significantly improve the action localization performance.
-
We present an approach for recommending a music track for a given video, and vice versa, based on both their temporal alignment and their correspondence at an artistic level. We propose a self-supervised approach that learns this correspondence directly from data, without any need of human annotations. In order to capture the high-level concepts that are required to solve the task, we propose modeling the long-term temporal context of both the video and the music signals, using Transformer networks for each modality. Experiments show that this approach strongly outperforms alternatives that do not exploit the temporal context. The combination of our contributions improve retrieval accuracy up to 10x over prior state of the art. This strong improvement allows us to introduce a wide range of analyses and applications. For instance, we can condition music retrieval based on visually-defined attributes.
-
We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language models on large public datasets has enabled strong differential privacy (DP) guarantees with minor loss of accuracy, a similar practice yields punishing trade-offs in vision tasks. A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset. AdaMix incorporates few-shot training, or cross-modal zero-shot learning, on public data prior to private fine-tuning, to improve the trade-off. AdaMix reduces the error increase from the non-private upper bound from the 167-311% of the baseline, on average across 6 datasets, to 68-92% depending on the desired privacy level selected by the user. AdaMix tackles the trade-off arising in visual classification, whereby the most privacy sensitive data, corresponding to isolated points in representation space, are also critical for high classification accuracy. In addition, AdaMix comes with strong theoretical privacy guarantees and convergence analysis.
-
Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to assign more importance to misclassified (hard) examples. In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality. We argue that the strategy to emphasize misclassified samples should be adjusted according to their image quality. Specifically, the relative importance of easy or hard samples should be based on the sample's image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method achieves this in the form of an adaptive margin function by approximating the image quality with feature norms. Extensive experiments show that our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets (IJB-B, IJB-C, IJB-S and TinyFace). Code and models are released in Supp.
-
Estimating keypoint scale and orientation is crucial to extracting invariant features under significant geometric changes. Recently, the estimators based on self-supervised learning have been designed to adapt to complex imaging conditions. Such learning-based estimators generally predict a single scalar for the keypoint scale or orientation, called hard estimators. However, hard estimators are difficult to handle the local patches containing structures of different objects or multiple edges. In this paper, a Soft Self-Supervised Estimator (S3Esti) is proposed to overcome this problem by learning to predict multiple scales and orientations. S3Esti involves three core factors. First, the estimator is constructed to predict the discrete distributions of scales and orientations. The elements with high confidence will be kept as the final scales and orientations. Second, a probabilistic covariant loss is proposed to improve the consistency of the scale and orientation distributions under different transformations. Third, an optimization algorithm is designed to minimize the loss function, whose convergence is proved in theory. When combined with different keypoint extraction models, S3Esti generally improves over 50% accuracy in image matching tasks under significant viewpoint changes. In the 3D reconstruction task, S3Esti decreases more than 10% reprojection error and improves the number of registered images.
-
We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results from the instability of bipartite graph matching which causes inconsistent optimization goals in early training stages. To address this issue, except for the Hungarian loss, our method additionally feeds ground-truth bounding boxes with noises into Transformer decoder and trains the model to reconstruct the original boxes, which effectively reduces the bipartite graph matching difficulty and leads to a faster convergence. Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement. As a result, our DN-DETR results in a remarkable improvement (+1.9AP) under the same setting and achieves the best result (AP 43.4 and 48.6 with 12 and 50 epochs of training respectively) among DETR-like methods with ResNet-50 backbone. Our code will be released after the blind review.
-
Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such structures with image representations can greatly benefit the semantic understanding on various downstream tasks. Existing contrastive representation learning methods lack such an important model capability. In addition, the negative pairs used in these methods are not guaranteed to be semantically distinct, which could further hamper the structural correctness of learned image representations. To tackle these limitations, we propose a novel contrastive learning framework called Hierarchical Contrastive Selective Coding (HCSC). In this framework, a set of hierarchical prototypes are constructed and also dynamically updated to represent the hierarchical semantic structures underlying the data in the latent space. To make image representations better fit such semantic structures, we employ and further improve conventional instance-wise and prototypical contrastive learning via an elaborate pair selection scheme. This scheme seeks to select more diverse positive pairs with similar semantics and more precise negative pairs with truly distinct semantics. On extensive downstream tasks, we verify the superior performance of HCSC over state-of-the-art contrastive methods, and the effectiveness of major model components is proved by plentiful analytical studies. We are continually building a comprehensive model zoo (see supplementary material). Our source code and model weights are available at https://github.com/gyfastas/HCSC.
-
Recognizing transformation types applied to a video clip (RecogTrans) is a long-established paradigm for self-supervised video representation learning, which achieves much inferior performance compared to instance discrimination approaches (InstDisc) in recent works. However, based on a thorough comparison of representative RecogTrans and InstDisc methods, we observe the great potential of RecogTrans on both semantic-related and temporal-related downstream tasks. Based on hard-label classification, existing RecogTrans approaches suffer from noisy supervision signals in pre-training. To mitigate this problem, we developed TransRank, a unified framework for recognizing Transformations in a Ranking formulation. TransRank provides accurate supervision signals by recognizing transformations relatively, consistently outperforming the classification-based formulation. Meanwhile, the unified framework can be instantiated with an arbitrary set of temporal or spatial transformations, demonstrating good generality. With a ranking-based formulation and several empirical practices, we achieve competitive performance on video retrieval and action recognition.Under the same setting, TransRank surpasses the previous state-of-the-art method by 6.4% on UCF101 and 8.3% on HMDB51 for action recognition (Top1 Acc); improves video retrieval on UCF101 by 20.4% (R@1). The promising results validate that RecogTrans is still a worth exploring paradigm for video self-supervised learning. Codes will be released at https://github.com/kennymckormick/TransRank.
-
We consider the problem of reconstructing the depth of dynamic objects from videos. Recent progress in dynamic video depth prediction has focused on improving the output of monocular depth estimators by means of multi-view constraints while imposing little to no restrictions on the deformation of the dynamic parts of the scene. However, the theory of Non-Rigid Structure from Motion prescribes to constrain the deformations for 3D reconstruction. We thus propose a new model that departs significantly from this prior work. The idea is to fit a dynamic point cloud to the video data using Sinkhorn's algorithm to associate the 3D points to 2D pixels and use a differentiable point renderer to ensure the compatibility of the 3D deformations with the measured optical flow. In this manner, our algorithm, called Keypoint Transporter, models the overall deformation of the object within the entire video, so it can constrain the reconstruction correspondingly. Compared to weaker deformation models, this significantly reduces the reconstruction ambiguity and, for dynamic objects, allows Keypoint Transporter to obtain reconstructions of the quality superior or at least comparable to prior approaches while being much faster and reliant on a pre-trained monocular depth estimator network. To assess the method, we evaluate on new datasets of synthetic videos depicting dynamic humans and animals with ground-truth depth. We also show qualitative results on crowd-sourced real-world videos of pets.
-
Video Question Answering (VideoQA) is the task of answering questions about a video. At its core is understanding the alignments between visual scenes in video and linguistic semantics in question to yield the answer. In leading VideoQA models, the typical learning objective, empirical risk minimization (ERM), latches on superficial correlations between video-question pairs and answers as the alignments. However, ERM can be problematic, because it tends to over-exploit the spurious correlations between question-irrelevant scenes and answers, instead of inspecting the causal effect of question-critical scenes. As a result, the VideoQA models suffer from unreliable reasoning. In this work, we first take a causal look at VideoQA and argue that invariant grounding is the key to ruling out the spurious correlations. Towards this end, we propose a new learning framework, Invariant Grounding for VideoQA (IGV), to ground the question-critical scene, whose causal relations with answers are invariant across different interventions on the complement. With IGV, the VideoQA models are forced to shield the answering process from the negative influence of spurious correlations, which significantly improves the reasoning ability. Experiments on three benchmark datasets validate the superiority of IGV in terms of accuracy, visual explainability, and generalization ability over the leading baselines.
-
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution of diverse prompts to handle the varying visual representations. In this way, we provide high-quality task-related content for facilitating recognition. This prompt distribution learning is realized by an efficient approach that learns the output embeddings of prompts instead of the input embeddings. Thus, we can employ a Gaussian distribution to model them effectively and derive a surrogate loss for efficient training. Extensive experiments on 12 datasets demonstrate that our method consistently and significantly outperforms existing methods. For example, with 1 sample per category, it relatively improves the average result by 9.1% compared to human-crafted prompts.
-
This paper proposes a deep recurrent Rotation Averaging Graph Optimizer (RAGO) for Multiple Rotation Averaging (MRA). Conventional optimization-based methods usually fail to produce accurate results due to corrupted and noisy relative measurements. Recent learning-based approaches regard MRA as a regression problem, while these methods are sensitive to initialization due to the gauge freedom problem. To handle these problems, we propose a learnable iterative graph optimizer minimizing a gauge-invariant cost function with an edge rectification strategy to mitigate the effect of inaccurate measurements. Our graph optimizer iteratively refines the global camera rotations by minimizing each node's single rotation objective function. Besides, our approach iteratively rectifies relative rotations to make them more consistent with the current camera orientations and observed relative rotations. Furthermore, we employ a gated recurrent unit to improve the result by tracing the temporal information of the cost graph. Our framework is a real-time learning-to-optimize rotation averaging graph optimizer with a tiny size deployed for real-world applications. RAGO outperforms previous traditional and deep methods on real-world and synthetic datasets. The code is available at github.com/sfu-gruvi-3dv/RAGO
-
Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search
Neural Architecture Search (NAS) aims to find efficient models for multiple tasks. Beyond seeking solutions for a single task, there are surging interests in transferring network design knowledge across multiple tasks. In this line of research, effectively modeling task correlations is vital yet highly neglected. Therefore, we propose Arch-Graph, a transferable NAS method that predicts task-specific optimal architectures with respect to given task embeddings. It leverages correlations across multiple tasks by using their embeddings as a part of the predictor's input for fast adaptation. We also formulate NAS as an architecture relation graph prediction problem, with the relational graph constructed by treating candidate architectures as nodes and their pairwise relations as edges. To enforce some basic properties such as acyclicity in the relational graph, we add additional constraints to the optimization process, converting NAS into the problem of finding a Maximal Weighted Acyclic Subgraph (MWAS). Our algorithm then strives to eliminate cycles and only establish edges in the graph if the rank results can be trusted. Through MWAS, Arch-Graph can effectively rank candidate models for each task with only a small budget to finetune the predictor. With extensive experiments on TransNAS-Bench-101, we show Arch-Graph's transferability and high sample efficiency across numerous tasks, beating many NAS methods designed for both single-task and multi-task search. It is able to find top 0.16% and 0.29% architectures on average on two search spaces under the budget of only 50 models.
-
Metrics for evaluating generative models aim to measure the discrepancy between real and generated images. The oftenused Frechet Inception Distance (FID) metric, for example, extracts "high-level" features using a deep network from the two sets. However, we find that the differences in "low-level" preprocessing, specifically image resizing and compression, can induce large variations and have unforeseen consequences. For instance, when resizing an image, e.g., with a bilinear or bicubic kernel, signal processing principles mandate adjusting prefilter width depending on the downsampling factor, to antialias to the appropriate bandwidth. However, commonly used implementations use a fixed-width prefilter, resulting in aliasing artifacts. Such aliasing leads to corruptions in the feature extraction downstream. Next, lossy compression, such as JPEG, is commonly used to reduce the file size of an image. Although designed to minimally degrade the perceptual quality of an image, the operation also produces variations downstream. Furthermore, we show that if compression is used on real training images, FID can actually improve if the generated images are also subsequently compressed. This paper shows that choices in low-level image processing have been an under-appreciated aspect of generative modeling. We identify and characterize variations in generative modeling development pipelines, provide recommendations based on signal processing principles, and release a reference implementation to facilitate future comparisons.
-
We present Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes. The key characteristics are the following techniques that exploit 3D positional knowledge for point cloud matching: 1) An architecture that disentangles point cloud representation into feature space and 3D position space. 2) A position encoding method that explicitly reveals 3D relative distance information through the dot product of vectors. 3) A repositioning technique that modifies the crosspoint-cloud relative positions. Ablation studies demonstrate the effectiveness of the above techniques. In rigid cases, Lepard combined with RANSAC and ICP demonstrates state-of-the-art registration recall of 93.9% / 71.3% on the 3DMatch / 3DLoMatch. In deformable cases, Lepard achieves +27.1% / +34.8% higher non-rigid feature matching recall than the prior art on our newly constructed 4DMatch / 4DLoMatch benchmark.
-
We present Virtual Elastic Objects (VEOs): virtual objects that not only look like their real-world counterparts but also behave like them, even when subject to novel interactions. Achieving this presents multiple challenges: not only do objects have to be captured including the physical forces acting on them, then faithfully reconstructed and rendered, but also plausible material parameters found and simulated. To create VEOs, we built a multi-view capture system that captures objects under the influence of a compressed air stream. Building on recent advances in model-free, dynamic Neural Radiance Fields, we reconstruct the objects and corresponding deformation fields. We propose to use a differentiable, particle-based simulator to use these deformation fields to find representative material parameters, which enable us to run new simulations. To render simulated objects, we devise a method for integrating the simulation results with Neural Radiance Fields. The resulting method is applicable to a wide range of scenarios: it can handle objects composed of inhomogeneous material, with very different shapes, and it can simulate interactions with other virtual objects. We present our results using a newly collected dataset of 12 objects under a variety of force fields, which will be made available upon publication.
-
Despite the popularity of Model Compression and Multitask Learning, how to effectively compress a multitask model has been less thoroughly analyzed due to the challenging entanglement of tasks in the parameter space. In this paper, we propose DiSparse, a simple, effective, and first-of-its-kind multitask pruning and sparse training scheme. We consider each task independently by disentangling the importance measurement and take the unanimous decisions among all tasks when performing parameter pruning and selection. Our experimental results demonstrate superior performance on various configurations and settings compared to popular sparse training and pruning methods. Besides the effectiveness in compression, DiSparse also provides a powerful tool to the multitask learning community. Surprisingly, we even observed better performance than some dedicated multitask learning methods in several cases despite the high model sparsity enforced by DiSparse. We analyzed the pruning masks generated with DiSparse and observed strikingly similar sparse network architecture identified by each task even before the training starts. We also observe the existence of a "watershed" layer where the task relatedness sharply drops, implying no benefits in continued parameters sharing. Our code and models will be available at: https://github.com/SHI-Labs/DiSparse-Multitask-Model-Compression.
-
Few-shot learning (FSL) is an important and topical problem in computer vision that has motivated extensive research into numerous methods spanning from sophisticated meta-learning methods to simple transfer learning baselines. We seek to push the limits of a simple-but-effective pipeline for real-world few-shot image classification in practice. To this end, we explore few-shot learning from the perspective of neural architecture, as well as a three stage pipeline of pre-training on external data, meta-training with labelled few-shot tasks, and task-specific fine-tuning on unseen tasks. We investigate questions such as: (1) How pre-training on external data benefits FSL? (2) How state of the art transformer architectures can be exploited? and (3) How to best exploit fine-tuning? Ultimately, we show that a simple transformer-based pipeline yields surprisingly good performance on standard benchmarks such as Mini-ImageNet, CIFAR-FS, CDFSL and Meta-Dataset. Our code is available at https://hushell.github.io/pmf.
-
Tracking and detecting any object, including ones never-seen-before during model training, is a crucial but elusive capability of autonomous systems. An autonomous agent that is blind to never-seen-before objects poses a safety hazard when operating in the real world - and yet this is how almost all current systems work. One of the main obstacles towards advancing tracking any object is that this task is notoriously difficult to evaluate. A benchmark that would allow us to perform an apple-to-apple comparison of existing efforts is a crucial first step towards advancing this important research field. This paper addresses this evaluation deficit and lays out the landscape and evaluation methodology for detecting and tracking both known and unknown objects in the open-world setting. We propose a new benchmark, TAO-OW: Tracking Any Object in an Open World, analyze existing efforts in multi-object tracking, and construct a baseline for this task while highlighting future challenges. We hope to open a new front in multi-object tracking research that will hopefully bring us a step closer to intelligent systems that can operate safely in the real world.
-
Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated a significant performance boost on training large-scale models such as vision transformers. However, the update rule of SAM requires two sequential (non-parallelizable) gradient computations at each step, which can double the computational overhead. In this paper, we propose a novel algorithm LookSAM - that only periodically calculates the inner gradient ascent, to significantly reduce the additional training cost of SAM. The empirical results illustrate that LookSAM achieves similar accuracy gains to SAM while being tremendously faster - it enjoys comparable computational complexity with first-order optimizers such as SGD or Adam. To further evaluate the performance and scalability of LookSAM, we incorporate a layer-wise modification and perform experiments in the large-batch training scenario, which is more prone to converge to sharp local minima. Equipped with the proposed algorithms, we are the first to successfully scale up the batch size when training Vision Transformers (ViTs). With a 64k batch size, we are able to train ViTs from scratch in minutes while maintaining competitive performance. The code is available here: https://github.com/yong-6/LookSAM
-
Detecting objects from LiDAR point clouds is of tremendous significance in autonomous driving. In spite of good progress, accurate and reliable 3D detection is yet to be achieved due to the sparsity and irregularity of LiDAR point clouds. Among existing strategies, multi-view methods have shown great promise by leveraging the more comprehensive information from both bird's eye view (BEV) and range view (RV). These multi-view methods either refine the proposals predicted from single view via fused features, or fuse the features without considering the global spatial context; their performance is limited consequently. In this paper, we propose to adaptively fuse multi-view features in a global spatial context via Dual Cross-VIew SpaTial Attention (VISTA). The proposed VISTA is a novel plug-and-play fusion module, wherein the multi-layer perceptron widely adopted in standard attention modules is replaced with a convolutional one. Thanks to the learned attention mechanism, VISTA can produce fused features of high quality for prediction of proposals. We decouple the classification and regression tasks in VISTA, and an additional constraint of attention variance is applied that enables the attention module to focus on specific targets instead of generic points. We conduct thorough experiments on the benchmarks of nuScenes and Waymo; results confirm the efficacy of our designs. At the time of submission, our method achieves 63.0% in overall mAP and 69.8% in NDS on the nuScenes benchmark, outperforming all published methods by up to 24% in safety-crucial categories such as cyclist.
-
A model that can authentically restore a low-quality face image to a high-quality one can benefit many applications. While existing approaches for face restoration make significant progress in generating high-quality faces, they often fail to preserve facial features and cannot authentically reconstruct the faces. Because the human visual system is very sensitive to faces, even minor facial changes may alter the identity and significantly degrade the perceptual quality. In this work, we argue the problems of existing models can be traced down to the two sub-tasks of the face restoration problem, i.e. face generation and face reconstruction, and the fragile balance between them. Based on the observation, we propose a new face restoration model that improves both generation and reconstruction by learning a stochastic model and enhancing the latent features respectively. Furthermore, we adapt the number of skip connections for a better balance between the two sub-tasks. Besides the model improvement, we also introduce a new evaluation metric for measuring models' ability to preserve the identity in the restored faces. Extensive experiments demonstrate that our model achieves state-of-the-art performance on multiple face restoration benchmarks. The user study shows that our model produces higher quality faces while better preserving the identity 86.4% of the time compared with the best performing baselines.
-
We address the problem of inferring the anatomic skeleton of a person, in an arbitrary pose, from the 3D surface of the body; i.e. we predict the inside (bones) from the outside (skin). This has many applications in medicine and biomechanics. Existing state-of-the-art biomechanical skeletons are detailed but do not easily generalize to new subjects. Additionally, computer vision and graphics methods that predict skeletons are typically heuristic, not learned from data, do not leverage the full 3D body surface, and are not validated against ground truth. To our knowledge, our system, called OSSO (Obtaining Skeletal Shape from Outside), is the first to learn the mapping from the 3D body surface to the internal skeleton from real data. We do so using 1000 male and 1000 female dual-energy X-ray absorptiometry (DXA) scans. To these, we fit a parametric 3D body shape model (STAR) to capture the body surface and a novel part-based 3D skeleton model to capture the bones. This provides inside/outside training pairs. We model the statistical variation of full skeletons using PCA in a pose-normalized space and train a regressor from body shape parameters to skeleton shape parameters. Given an arbitrary 3D body shape and pose, OSSO predicts a realistic skeleton inside. In contrast to previous work, we evaluate the accuracy of the skeleton shape quantitatively on held out DXA scans, outperforming the state-of-the art. We also show 3D skeleton prediction from varied and challenging 3D bodies. The code to infer a skeleton from a body shape is available at https://osso.is.tue.mpg.de, and the dataset of paired outer surface (skin) and skeleton (bone) meshes is available as a Biobank Returned Dataset. This research has been conducted using the UK Biobank Resource.
-
The objective of this paper is a temporal alignment network that ingests long term video sequences, and associated text sentences, in order to: (1) determine if a sentence is alignable with the video; and (2) if it is alignable, then determine its alignment. The challenge is to train such networks from large-scale datasets, such as HowTo100M, where the associated text sentences have significant noise, and are only weakly aligned when relevant. Apart from proposing the alignment network, we also make four contributions: (i) we describe a novel co-training method that enables to denoise and train on raw instructional videos without using manual annotation, despite the considerable noise; (ii) to benchmark the alignment performance, we manually curate a 10-hour subset of HowTo100M, totalling 80 videos, with sparse temporal descriptions. Our proposed model, trained on HowTo100M, outperforms strong baselines (CLIP, MIL-NCE) on this alignment dataset by a significant margin; (iii) we apply the trained model in the zero-shot settings to multiple downstream video understanding tasks and achieve state-of-the-art results, including text-video retrieval on YouCook2, and weakly supervised video action segmentation on Breakfast-Action. (iv) we use the automatically-aligned HowTo100M annotations for end-to-end finetuning of the backbone model, and obtain improved performance on downstream action recognition tasks.
-
The head swapping task aims at flawlessly placing a source head onto a target body, which is of great importance to various entertainment scenarios. While face swapping has drawn much attention in the community, the task of head swapping has rarely been explored, particularly under the few-shot setting. It is inherently challenging due to its unique needs in head modeling and background blending. In this paper, we present the Head Swapper (HeSer), which achieves few-shot head swapping in the wild through two dedicated designed modules. Firstly, a Head2Head Aligner is devised to holistically migrate position and expression information from the target to the source head by examining multi-scale information. Secondly, to tackle the challenges of skin color variations and head-background mismatches, a Head2Scene Blender is introduced to simultaneously modify facial skin color and fill mismatched gaps on the background around the head. Particularly, seamless blending is achieved through a semantic-guided exemplar warping procedure. User studies and experimental results demonstrate that the proposed method produces superior head swapping results on a variety of scenes.
-
Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases, such as ineffective or uneven data sampling, but also ethical concerns, as the social biases are implicitly present--even inadvertently, in the training data or explicitly defined in unfair training schedules. In tasks having impact on human processes, the learning of social biases may produce discriminatory, unethical and untrustworthy consequences. It is often assumed that social biases stem from supervised learning on labelled data, and thus, Self-Supervised Learning (SSL) wrongly appears as an efficient and bias-free solution, as it does not require labelled data. However, it was recently proven that a popular SSL method also incorporates biases. In this paper, we study the biases of a varied set of SSL visual models, trained using ImageNet data, using a method and dataset designed by psychological experts to measure social biases. We show that there is a correlation between the type of the SSL model and the number of biases that it incorporates. Furthermore, the results also suggest that this number does not strictly depend on the model's accuracy and changes throughout the network. Finally, we conclude that a careful SSL model selection process can reduce the number of social biases in the deployed model, whilst keeping high performance. The code is available at https://github.com/vpulab/SB-SSL.
-
Previous super-resolution (SR) approaches often formulate SR as a regression problem and pixel wise restoration, which leads to a blurry and unreal SR output. Recent works combine adversarial loss with pixel-wise loss to train a GAN-based model or introduce normalizing flows into SR problems to generate more realistic images. As another powerful generative approach, autoregressive (AR) model has not been noticed in low level tasks due to its limitation. Based on the fact that given the structural information, the textural details in the natural images are locally related without long term dependency, in this paper we propose a novel autoregressive model-based SR approach, namely LAR-SR, which can efficiently generate realistic SR images using a novel local autoregressive (LAR) module. The proposed LAR module can sample all the patches of textural components in parallel, which greatly reduces the time consumption. In addition to high time efficiency, it is also able to leverage contextual information of pixels and can be optimized with a consistent loss. Experimental results on the widely-used datasets show that the proposed LAR-SR approach achieves superior performance on the visual quality and quantitative metrics compared with other generative models such as GAN, Flow, and is competitive with the mixture generative model.
-
Generalization under distributional shift is an open challenge for machine learning. Invariant Risk Minimization (IRM) is a promising framework to tackle this issue by extracting invariant features. However, despite the potential and popularity of IRM, recent works have reported negative results of it on deep models. We argue that the failure can be primarily attributed to deep models' tendency to overfit the data. Specifically, our theoretical analysis shows that IRM degenerates to empirical risk minimization (ERM) when overfitting occurs. Our empirical evidence also provides supports: IRM methods that work well in typical settings significantly deteriorate even if we slightly enlarge the model size or lessen the training data. To alleviate this issue, we propose Bayesian Invariant Risk Minimization (BIRM) by introducing Bayesian inference into the IRM. The key motivation is to estimate the penalty of IRM based on the posterior distribution of classifiers (as opposed to a single classifier), which is much less prone to overfitting. Extensive experimental results on four datasets demonstrate that BIRM consistently outperforms the existing IRM baselines significantly.
-
Co-salient object detection, with the target of detecting co-existed salient objects among a group of images, is gaining popularity. Recent works use the attention mechanism or extra information to aggregate common co-salient features, leading to incomplete even incorrect responses for target objects. In this paper, we aim to mine comprehensive co-salient features with democracy and reduce background interference without introducing any extra information. To achieve this, we design a democratic prototype generation module to generate democratic response maps, covering sufficient co-salient regions and thereby involving more shared attributes of co-salient objects. Then a comprehensive prototype based on the response maps can be generated as a guide for final prediction. To suppress the noisy background information in the prototype, we propose a self-contrastive learning module, where both positive and negative pairs are formed without relying on additional classification information. Besides, we also design a democratic feature enhancement module to further strengthen the co-salient features by readjusting attention values. Extensive experiments show that our model obtains better performance than previous state-of-the-art methods, especially on challenging real-world cases (e.g., for CoCA, we obtain a gain of 2.0% for MAE, 5.4% for maximum F-measure, 2.3% for maximum E-measure, and 3.7% for S-measure) under the same settings. Code will be released soon.
-
Unsupervised image-to-image (I2I) translation aims to learn a domain mapping function that can preserve the semantics of the input images without paired data. However, because the underlying semantics distributions in the source and target domains are often mismatched, current distribution matching-based methods may distort the semantics when matching distributions, resulting in the inconsistency between the input and translated images, which is known as the semantics distortion problem. In this paper, we focus on the low-level I2I translation, where the structure of images is highly related to their semantics. To alleviate semantic distortions in such translation tasks without paired supervision, we propose a novel I2I translation constraint, called Structure Consistency Constraint (SCC), to promote the consistency of image structures by reducing the randomness of color transformation in the translation process. To facilitate estimation and maximization of SCC, we propose an approximate representation of mutual information called relative Squared-loss Mutual Information (rSMI) that enjoys efficient analytic solutions. Our SCC can be easily incorporated into most existing translation models. Quantitative and qualitative comparisons on a range of low-level I2I translation tasks show that translation models with SCC outperform the original models by a significant margin with little additional computational and memory costs.
-
The human visual system is remarkable in learning new visual concepts from just a few examples. This is precisely the goal behind few-shot class incremental learning (FSCIL), where the emphasis is additionally placed on ensuring the model does not suffer from "forgetting". In this paper, we push the boundary further for FSCIL by addressing two key questions that bottleneck its ubiquitous application (i) can the model learn from diverse modalities other than just photo (as humans do), and (ii) what if photos are not readily accessible (due to ethical and privacy constraints). Our key innovation lies in advocating the use of sketches as a new modality for class support. The product is a "Doodle It Yourself" (DIY) FSCIL framework where the users can freely sketch a few examples of a novel class for the model to learn to recognise photos of that class. For that, we present a framework that infuses (i) gradient consensus for domain invariant learning, (ii) knowledge distillation for preserving old class information, and (iii) graph attention networks for message passing between old and novel classes. We experimentally show that sketches are better class support than text in the context of FSCIL, echoing findings elsewhere in the sketching literature.
-
Current methods for learning realistic and animatable 3D clothed avatars need either posed 3D scans or 2D images with carefully controlled user poses. In contrast, our goal is to learn the avatar from only 2D images of people in unconstrained poses. Given a set of images, our method estimates a detailed 3D surface from each image and then combines these into an animatable avatar. Implicit functions are well suited to the first task, as they can capture details like hair or clothes. Current methods, however, are not robust to varied human poses and often produce 3D surfaces with broken or disembodied limbs, missing details, or non-human shapes. The problem is that these methods use global feature encoders that are sensitive to global pose. To address this, we propose ICON ("Implicit Clothed humans Obtained from Normals"), which uses local features. ICON has two main modules, both of which exploit the SMPL body model. First, ICON infers detailed clothed-human normals(front/back) conditioned on the SMPL normals. Second, a visibility-aware implicit surface regressor produces an iso-surface of the human occupancy field. Importantly, at inference time, a feedback loop alternates between refining the SMPL mesh using the inferred clothed normals and then refining the normals. Given multiple reconstructed frames of a subject in varied poses, we use modified SCANimate to produce an animatable avatar from them. Evaluation on the AGORA and CAPE datasets shows that ICON outperforms the state-of-the-art in reconstruction, even with heavily limited training data. Additionally, it is much more robust to out-of-distribution samples, e.g., in-the-wild poses/images and out-of-frame cropping. ICON takes a step towards pose-robust 3D clothed human reconstruction from in-the-wild images. This enables creating avatars directly from video with personalized and nature pose-dependent cloth deformation. Our models and code will be available for research.
-
Image prediction methods often struggle on tasks that require changing the positions of objects, such as video prediction, producing blurry images that average over the many positions that objects might occupy. In this paper, we propose a simple change to existing image similarity metrics that makes them more robust to positional errors: we match the images using optical flow, then measure the visual similarity of corresponding pixels. This change leads to crisper and more perceptually accurate predictions, and does not require modifications to the image prediction network. We apply our method to a variety of video prediction tasks, where it obtains strong performance with simple network architectures, and to the closely related task of video interpolation. Code and results are available at our webpage: https://dangeng.github.io/CorrWiseLosses
-
Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific paradigm, leading to inefficient collaboration between tasks and high marginal costs of developing perception models for new tasks. In this paper, we present a generic perception architecture named Uni-Perceiver, which processes a variety of modalities and tasks with unified modeling and shared parameters. Specifically, Uni-Perceiver encodes different task inputs and targets from arbitrary modalities into a unified representation space with a modality-agnostic Transformer encoder and lightweight modality-specific tokenizers. Different perception tasks are modeled as the same formulation, that is, finding the maximum likelihood target for each input through the similarity of their representations. The model is pre-trained on several uni-modal and multi-modal tasks, and evaluated on a variety of downstream tasks, including novel tasks that did not appear in the pre-training stage. Results show that our pre-trained model without any tuning can achieve reasonable performance even on novel tasks. The performance can be improved to a level close to state-of-the-art methods by conducting prompt tuning on 1% of downstream task data. Full-data fine-tuning further delivers results on par with or better than state-of-the-art results. Code and pre-trained weights shall be released.
-
Generalization to novel domains is a fundamental challenge for computer vision. Near-perfect accuracy on benchmarks is common, but these models do not work as expected when deployed outside of the training distribution. To build computer vision systems that truly solve real-world problems at global scale, we need benchmarks that fully capture real-world complexity, including geographic domain shift, long-tailed distributions, and data noise. We propose urban forest monitoring as an ideal testbed for studying and improving upon these computer vision challenges, while simultaneously working towards filling a crucial environmental and societal need. Urban forests provide significant benefits to urban societies (e.g., cleaner air and water, carbon sequestration, and energy savings among others). However, planning and maintaining these forests is expensive. One particularly costly aspect of urban forest management is monitoring the existing trees in a city: e.g., tracking tree locations, species, and health. Monitoring efforts are currently based on tree censuses built by human experts, costing cities millions of dollars per census and thus collected infrequently. Previous investigations into automating urban forest monitoring focused on small datasets from single cities, covering only common categories. To address these shortcomings, we introduce a new large-scale dataset that joins public tree censuses from 23 cities with a large collection of street level and aerial imagery. Our Auto Arborist dataset contains over 2.5M trees and 344 genera and is >2 orders of magnitude larger than the closest dataset in the literature. We introduce baseline results on our dataset across modalities as well as metrics for the detailed analysis of generalization with respect to geographic distribution shifts, vital for such a system to be deployed at-scale.
-
Relative pose estimation using the 5-point or 7-point Random Sample Consensus (RANSAC) algorithms can fail even when no outliers are present and there are enough inliers to support a hypothesis. These cases arise due to numerical instability of the 5- and 7-point minimal problems. This paper characterizes these instabilities, both in terms of minimal world scene configurations that lead to infinite condition number in epipolar estimation, and also in terms of the related minimal image feature pair correspondence configurations. The instability is studied in the context of a novel framework for analyzing the conditioning of minimal problems in multiview geometry, based on Riemannian manifolds. Experiments with synthetic and real-world data reveal that RANSAC does not only serve to filter out outliers, but RANSAC also selects for well-conditioned image data, sufficiently separated from the ill-posed locus that our theory predicts. These findings suggest that, in future work, one could try to accelerate and increase the success of RANSAC by testing only well-conditioned image data.
-
We present a new data-driven approach with physics-based priors to scene-level normal estimation from a single polarization image. Existing shape from polarization (SfP) works mainly focus on estimating the normal of a single object rather than complex scenes in the wild. A key barrier to high-quality scene-level SfP is the lack of real-world SfP data in complex scenes. Hence, we contribute the first real-world scene-level SfP dataset with paired input polarization images and ground-truth normal maps. Then we propose a learning-based framework with a multi-head self-attention module and viewing encoding, which is designed to handle increasing polarization ambiguities caused by complex materials and non-orthographic projection in scene-level SfP. Our trained model can be generalized to far-field outdoor scenes as the relationship between polarized light and surface normals is not affected by distance. Experimental results demonstrate that our approach significantly outperforms existing SfP models on two datasets. Our dataset and source code will be publicly available.
-
This demonstration showcases our innovations on efficient, accurate, and temporally consistent video semantic segmentation on mobile device. We employ our test-time unsupervised scheme, AuxAdapt, to enable the segmentation model to adapt to a given video in an online manner. More specifically, we leverage a small auxiliary network to perform weight updates and keep the large, main segmentation network frozen. This significantly reduces the computational cost of adaptation when compared to previous methods (e.g., Tent, DVP), and at the same time, prevents catastrophic forgetting. By running AuxAdapt, we can considerably improve the temporal consistency of video segmentation while maintaining the accuracy. We demonstrate how to efficiently deploy our adaptive video segmentation algorithm on a smartphone powered by a Snapdragon Mobile Platform. Rather than simply running the entire algorithm on the GPU, we adopt a cross-unit deployment strategy. The main network, which will be frozen during test time, will perform inferences on a highly optimized AI accelerator unit, while the small auxiliary network, which will be updated on the fly, will run forward passes and back-propagations on the GPU. Such a deployment scheme best utilizes the available processing power on the smartphone and enables real-time operation of our adaptive video segmentation algorithm. We provide example videos in supplementary material.
-
We present a self-supervised method to learn dynamic 3D deformations of garments worn by parametric human bodies. State-of-the-art data-driven approaches to model 3D garment deformations are trained using supervised strategies that require large datasets, usually obtained by expensive physics-based simulation methods or professional multi-camera capture setups. In contrast, we propose a new training scheme that removes the need for ground-truth samples, enabling self-supervised training of dynamic 3D garment deformations. Our key contribution is to realize that physics-based deformation models, traditionally solved in a frame-by-frame basis by implicit integrators, can be recasted as an optimization problem. We leverage such optimization-based scheme to formulate a set of physics-based loss terms that can be used to train neural networks without precomputing ground-truth data. This allows us to learn models for interactive garments, including dynamic deformations and fine wrinkles, with two orders of magnitude speed up in training time compared to state-of-the-art supervised methods.
-
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo labels are typically biased to the majority classes and basically noisy, leading to an error-prone and suboptimal model. In this paper, we propose a simple region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performance. Our algorithm, Region Impurity and Prediction Uncertainty (RIPU), introduces a new acquisition strategy characterizing the spatial adjacency of image regions along with the prediction confidence. We show that the proposed region-based selection strategy makes more efficient use of a limited budget than image-based or point-based counterparts. Further, we enforce local prediction consistency between a pixel and its nearest neighbors on a source image. Alongside, we develop a negative learning loss to make the features more discriminative. Extensive experiments demonstrate that our method only requires very few annotations to almost reach the supervised performance and substantially outperforms state-of-the-art methods. The code is available at https://github.com/BIT-DA/RIPU.
-
Transparent and semi-transparent materials pose significant challenges for existing scene understanding and segmentation algorithms due to their lack of RGB texture which impedes the extraction of meaningful features. In this work, we exploit that the light-matter interactions on glass materials provide unique intensity-polarization cues for each observed wavelength of light. We present a novel learning-based glass segmentation network that leverages both trichromatic (RGB) intensities as well as trichromatic linear polarization cues from a single photograph captured without making any assumption on the polarization state of the illumination. Our novel network architecture dynamically fuses and weights both the trichromatic color and polarization cues using a novel global-guidance and multi-scale self-attention module, and leverages global cross-domain contextual information to achieve robust segmentation. We train and extensively validate our segmentation method on a new large-scale RGB-Polarization dataset (RGBP-Glass), and demonstrate that our method outperforms state-of-the-art segmentation approaches by a significant margin.
-
Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which operates without any human labeling, is a promising approach to address this issue. We observe in the real world that humans are capable of mapping the visual concepts learnt from 2D images to understand the 3D world. Encouraged by this insight, we propose CrossPoint, a simple cross-modal contrastive learning approach to learn transferable 3D point cloud representations. It enables a 3D-2D correspondence of objects by maximizing agreement between point clouds and the corresponding rendered 2D image in the invariant space, while encouraging invariance to transformations in the point cloud modality. Our joint training objective combines the feature correspondences within and across modalities, thus ensembles a rich learning signal from both 3D point cloud and 2D image modalities in a self-supervised fashion. Experimental results show that our approach outperforms the previous unsupervised learning methods on a diverse range of downstream tasks including 3D object classification and segmentation. Further, the ablation studies validates the potency of our approach for a better point cloud understanding. Code and pretrained models are available at https://github.com/MohamedAfham/CrossPoint.
-
Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption. However, existing methods are prone to model overfitting and collapse in extremely few shot setting (less than 10). To solve this problem, we propose a relaxed spatial structural alignment (RSSA) method to calibrate the target generative models during the adaption. We design a cross-domain spatial structural consistency loss comprising the self-correlation and disturbance correlation consistency loss. It helps align the spatial structural information between the synthesis image pairs of the source and target domains. To relax the cross-domain alignment, we compress the original latent space of generative models to a subspace. Image pairs generated from the subspace are pulled closer. Qualitative and quantitative experiments show that our method consistently surpasses the state-of-the-art methods in few shot setting. Our source code: https://github.com/StevenShaw1999/RSSA.
-
Domain adaptive object detection (DAOD) is a promising way to alleviate performance drop of detectors in new scenes. Albeit great effort made in single source domain adaptation, a more generalized task with multiple source domains remains not being well explored, due to knowledge degradation during their combination. To address this issue, we propose a novel approach, namely target-relevant knowledge preservation (TRKP), to unsupervised multi-source DAOD. Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain. The teacher network is further equipped with an adversarial multi-source disentanglement (AMSD) module to preserve source domain-specific knowledge and simultaneously perform cross-domain alignment. Besides, a holistic target-relevant mining (HTRM) scheme is developed to re-weight the source images according to the source-target relevance. By this means, the teacher network is enforced to capture target-relevant knowledge, thus benefiting decreasing domain shift when mentoring object detection in the target domain. Extensive experiments are conducted on various widely used benchmarks with new state-of-the-art scores reported, highlighting the effectiveness.
-
Recent salient object detection (SOD) methods based on deep neural network have achieved remarkable performance. However, most of existing SOD models designed for low-resolution input perform poorly on high-resolution images due to the contradiction between the sampling depth and the receptive field size. Aiming at resolving this contradiction, we propose a novel one-stage framework called Pyramid Grafting Network (PGNet), using transformer and CNN backbone to extract features from different resolution images independently and then graft the features from transformer branch to CNN branch. An attention-based Cross-Model Grafting Module (CMGM) is proposed to enable CNN branch to combine broken detailed information more holistically, guided by different source feature during decoding process. Moreover, we design an Attention Guided Loss (AGL) to explicitly supervise the attention matrix generated by CMGM to help the network better interact with the attention from different models. We contribute a new Ultra-High-Resolution Saliency Detection dataset UHRSD, containing 5,920 images at 4K-8K resolutions. To our knowledge, it is the largest dataset in both quantity and resolution for high-resolution SOD task, which can be used for training and testing in future research. Sufficient experiments on UHRSD and widely-used SOD datasets demonstrate that our method achieves superior performance compared to the state-of-the-art methods.
-
Current image-to-image translations do not control the output domain beyond the classes used during training, nor do they interpolate between different domains well, leading to implausible results. This limitation largely arises because labels do not consider the semantic distance. To mitigate such problems, we propose a style-aware discriminator that acts as a critic as well as a style encoder to provide conditions. The style-aware discriminator learns a controllable style space using prototype-based self-supervised learning and simultaneously guides the generator. Experiments on multiple datasets verify that the proposed model outperforms current state-of-the-art image-to-image translation methods. In contrast with current methods, the proposed approach supports various applications, including style interpolation, content transplantation, and local image translation. The code is available at github.com/kunheek/style-aware-discriminator.
-
In this paper, we aim to estimate the direction of an underlying signal from its nonlinear observations following the semi-parametric single index model (SIM). Unlike for conventional compressed sensing where the signal is assumed to be sparse, we assume that the signal lies in the range of an L-Lipschitz continuous generative model with bounded k-dimensional inputs. This is mainly motivated by the tremendous success of deep generative models in various real applications. Our reconstruction method is non-iterative (though approximating the projection step may require an iterative procedure) and highly efficient, and it is shown to attain the near-optimal statistical rate of order \sqrt (k \log L)/m , where m is the number of measurements. We consider two specific instances of the SIM, namely noisy 1-bit and cubic measurement models, and perform experiments on image datasets to demonstrate the efficacy of our method. In particular, for the noisy 1-bit measurement model, we show that our non-iterative method significantly outperforms a state-of-the-art iterative method in terms of both accuracy and efficiency.
-
Due to the constraints of the imaging device and high cost in operation time, computer tomography (CT) scans are usually acquired with low within-slice resolution. Improving the inter-slice resolution is beneficial to the disease diagnosis for both human experts and computer-aided systems. To this end, this paper builds a novel medical slice synthesis to increase the inter-slice resolution. Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy to accomplish this task in the self-supervised learning manner. Specifically, we model this problem from three different views: slice-wise interpolation from axial view and pixel-wise interpolation from coronal and sagittal views. Under this circumstance, the models learned from different views can distill valuable knowledge to guide the learning processes of each other. We can repeat this process to make the models synthesize intermediate slice data with increasing between-slice resolution. To demonstrate the effectiveness of the proposed approach, we conduct comprehensive experiments on a large-scale CT dataset. Quantitative and qualitative comparison results show that our method outperforms state-of-the-art algorithms by clear margins.
-
Adversarial training has been shown to be one of the most effective approaches to improve the robustness of deep neural networks. It is formalized as a min-max optimization over model weights and adversarial perturbations, where the weights can be optimized through gradient descent methods like SGD. In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through Second-Order Statistics Optimization (S^2O) with respect to the weights. By relaxing a common (but unrealistic) assumption of previous PAC-Bayesian frameworks that all weights are statistically independent, we derive an improved PAC-Bayesian adversarial generalization bound, which suggests that optimizing second-order statistics of weights can effectively tighten the bound. In addition to this theoretical insight, we conduct an extensive set of experiments, which show that S^2O not only improves the robustness and generalization of the trained neural networks when used in isolation, but also integrates easily in state-of-the-art adversarial training techniques like TRADES, AWP, MART, and AVMixup, leading to a measurable improvement of these techniques. The code is available at https://github.com/Alexkael/S2O.
-
We scrutinise an important observation plaguing scene-level sketch research -- that a significant portion of scene sketches are "partial". A quick pilot study reveals: (i) a scene sketch does not necessarily contain all objects in the corresponding photo, due to the subjective holistic interpretation of scenes, (ii) there exists significant empty (white) regions as a result of object-level abstraction, and as a result, (iii) existing scene-level fine-grained sketch-based image retrieval methods collapse as scene sketches become more partial. To solve this "partial" problem, we advocate for a simple set-based approach using optimal transport (OT) to model cross-modal region associativity in a partially-aware fashion. Importantly, we improve upon OT to further account for holistic partialness by comparing intra-modal adjacency matrices. Our proposed method is not only robust to partial scene-sketches but also yields state-of-the-art performance on existing datasets.
-
Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior because the negative sample size (NSS) is limited by its mini-batch size (MBS). To decouple the NSS from the MBS, a dynamic dictionary has been adopted in a large volume of CL frameworks, among which arguably the most popular one is MoCo family. In essence, MoCo adopts a momentum-based queue dictionary, for which we perform a fine-grained analysis of its size and consistency. We point out that InfoNCE loss used in MoCo implicitly attract anchors to their corresponding positive sample with various strength of penalties and identify such inter-anchor hardness-awareness property as a major reason for the necessity of a large dictionary. Our findings motivate us to simplify MoCo v2 via the removal of its dictionary as well as momentum. Based on an InfoNCE with the proposed dual temperature, our simplified frameworks, SimMoCo and SimCo, outperform MoCo v2 by a visible margin. Moreover, our work bridges the gap between CL and non-CL frameworks, contributing to a more unified understanding of these two mainstream frameworks in SSL. Code is available at: https://bit.ly/3LkQbaT.
-
A novel ordinal regression algorithm, called moving window regression (MWR), is proposed in this paper. First, we propose the notion of relative rank (rho-rank), which is a new order representation scheme for input and reference instances. Second, we develop global and local relative regressors (rho-regressors) to predict rho-ranks within entire and specific rank ranges, respectively. Third, we refine an initial rank estimate iteratively by selecting two reference instances to form a search window and then estimating the rho-rank within the window. Extensive experiments results show that the proposed algorithm achieves the state-of-the-art performances on various benchmark datasets for facial age estimation and historical color image classification. The codes are available at https://github.com/nhshin-mcl/MWR.
-
Conditional image repainting (CIR) is an advanced image editing task, which requires the model to generate visual content in user-specified regions conditioned on multiple cross-modality constraints, and composite the visual content with the provided background seamlessly. Existing methods based on two-phase architecture design assume dependency between phases and cause color-image incongruity. To solve these problems, we propose a novel Unified Conditional image Repainting Network (UniCoRN). We break the two-phase assumption in CIR task by constructing the interaction and dependency relationship between background and other conditions. We further introduce the hierarchical structure into cross-modality similarity model to capture feature patterns at different levels and bridge the gap between visual content and color condition. A new LANDSCAPE-CIR dataset is collected and annotated to expand the application scenarios of the CIR task. Experiments show that UniCoRN achieves higher synthetic quality, better condition consistency, and more realistic compositing effect.
-
We propose the task of forecasting characteristic 3d poses: from a short sequence observation of a person, predict a future 3d pose of that person in a likely action-defining, characteristic pose - for instance, from observing a person picking up an apple, predict the pose of the person eating the apple. Prior work on human motion prediction estimates future poses at fixed time intervals. Although easy to define, this frame-by-frame formulation confounds temporal and intentional aspects of human action. Instead, we define a semantically meaningful pose prediction task that decouples the predicted pose from time, taking inspiration from goal-directed behavior. To predict characteristic poses, we propose a probabilistic approach that models the possible multi-modality in the distribution of likely characteristic poses. We then sample future pose hypotheses from the predicted distribution in an autoregressive fashion to model dependencies between joints. To evaluate our method, we construct a dataset of manually annotated characteristic 3d poses. Our experiments with this dataset suggest that our proposed probabilistic approach outperforms state-of-the-art methods by 26% on average.
-
Effective semi-supervised learning (SSL) in medical image analysis (MIA) must address two challenges: 1) work effectively on both multi-class (e.g., lesion classification) and multi-label (e.g., multiple-disease diagnosis) problems, and 2) handle imbalanced learning (because of the high variance in disease prevalence). One strategy to explore in SSL MIA is based on the pseudo labelling strategy, but it has a few shortcomings. Pseudo-labelling has in general lower accuracy than consistency learning, it is not specifically designed for both multi-class and multi-label problems, and it can be challenged by imbalanced learning. In this paper, unlike traditional methods that select confident pseudo label by threshold, we propose a new SSL algorithm, called anti-curriculum pseudo-labelling (ACPL), which introduces novel techniques to select informative unlabelled samples, improving training balance and allowing the model to work for both multi-label and multi-class problems, and to estimate pseudo labels by an accurate ensemble of classifiers (improving pseudo label accuracy). We run extensive experiments to evaluate ACPL on two public medical image classification benchmarks: Chest X-Ray14 for thorax disease multi-label classification and ISIC2018 for skin lesion multi-class classification. Our method outperforms previous SOTA SSL methods on both datasets
-
Defocus deblurring is a challenging task due to the spatially varying nature of defocus blur. While deep learning approach shows great promise in solving image restoration problems, defocus deblurring demands accurate training data that consists of all-in-focus and defocus image pairs, which is difficult to collect. Naive two-shot capturing cannot achieve pixel-wise correspondence between the defocused and all-in-focus image pairs. Synthetic aperture of light fields is suggested to be a more reliable way to generate accurate image pairs. However, the defocus blur generated from light field data is different from that of the images captured with a traditional digital camera. In this paper, we propose a novel deep defocus deblurring network that leverages the strength and overcomes the shortcoming of light fields. We first train the network on a light field-generated dataset for its highly accurate image correspondence. Then, we fine-tune the network using feature loss on another dataset collected by the two-shot method to alleviate the differences between the defocus blur exists in the two domains. This strategy is proved to be highly effective and able to achieve the state-of-the-art performance both quantitatively and qualitatively on multiple test sets. Extensive ablation studies have been conducted to analyze the effect of each network module to the final performance.
-
Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abnormal test samples. Among the successful approaches for anomaly detection, a distinguished category of methods relies on predicting masked information (e.g. patches, future frames, etc.) and leveraging the reconstruction error with respect to the masked information as an abnormality score. Different from related methods, we propose to integrate the reconstruction-based functionality into a novel self-supervised predictive architectural building block. The proposed self-supervised block is generic and can easily be incorporated into various state-of-the-art anomaly detection methods. Our block starts with a convolutional layer with dilated filters, where the center area of the receptive field is masked. The resulting activation maps are passed through a channel attention module. Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field. We demonstrate the generality of our block by integrating it into several state-of-the-art frameworks for anomaly detection on image and video, providing empirical evidence that shows considerable performance improvements on MVTec AD, Avenue, and ShanghaiTech. We release our code as open source at: https://github.com/ristea/sspcab.
-
Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a large domain gap lies between the source and target domains. In this paper we propose a novel solution named SSRT (Safe Self-Refinement for Transformer-based domain adaptation), which brings improvement from two aspects. First, encouraged by the success of vision transformers in various vision tasks, we arm SSRT with a transformer backbone. We find that the combination of vision transformer with simple adversarial adaptation surpasses best reported Convolutional Neural Network (CNN)-based results on the challenging DomainNet benchmark, showing its strong transferable feature representation. Second, to reduce the risk of model collapse and improve the effectiveness of knowledge transfer between domains with large gaps, we propose a Safe Self-Refinement strategy. Specifically, SSRT utilizes predictions of perturbed target domain data to refine the model. Since the model capacity of vision transformer is large and predictions in such challenging tasks can be noisy, a safe training mechanism is designed to adaptively adjust learning configuration. Extensive evaluations are conducted on several widely tested UDA benchmarks and SSRT achieves consistently the best performances, including 85.43% on Office-Home, 88.76% on VisDA-2017 and 45.2% on DomainNet.
-
Local density of point clouds is crucial for representing local details, but has been overlooked by existing point cloud compression methods. To address this, we propose a novel deep point cloud compression method that preserves local density information. Our method works in an auto-encoder fashion: the encoder downsamples the points and learns point-wise features, while the decoder upsamples the points using these features. Specifically, we propose to encode local geometry and density with three embeddings: density embedding, local position embedding and ancestor embedding. During the decoding, we explicitly predict the upsampling factor for each point, and the directions and scales of the upsampled points. To mitigate the clustered points issue in existing methods, we design a novel sub-point convolution layer, and an upsampling block with adaptive scale. Furthermore, our method can also compress point-wise attributes, such as normal. Extensive qualitative and quantitative results on SemanticKITTI and ShapeNet demonstrate that our method achieves the state-of-the-art rate-distortion trade-off.
-
We apply style transfer on mesh reconstructions of indoor scenes. This enables VR applications like experiencing 3D environments painted in the style of a favorite artist. Style transfer typically operates on 2D images, making stylization of a mesh challenging. When optimized over a variety of poses, stylization patterns become stretched out and inconsistent in size. On the other hand, model-based 3D style transfer methods exist that allow stylization from a sparse set of images, but they require a network at inference time. To this end, we optimize an explicit texture for the reconstructed mesh of a scene and stylize it jointly from all available input images. Our depth- and angle-aware optimization leverages surface normal and depth data of the underlying mesh to create a uniform and consistent stylization for the whole scene. Our experiments show that our method creates sharp and detailed results for the complete scene without view-dependent artifacts. Through extensive ablation studies, we show that the proposed 3D awareness enables style transfer to be applied to the 3D domain of a mesh. Our method can be used to render a stylized mesh in real-time with traditional rendering pipelines.
-
Transfer learning has been recently popularized as a data-efficient alternative to training models from scratch, in particular for computer vision tasks where it provides a remarkably solid baseline. The emergence of rich model repositories, such as TensorFlow Hub, enables the practitioners and researchers to unleash the potential of these models across a wide range of downstream tasks. As these repositories keep growing exponentially, efficiently selecting a good model for the task at hand becomes paramount. We provide a formalization of this problem through a familiar notion of regret and introduce the predominant strategies, namely task-agnostic (e.g. ranking models by their ImageNet performance) and task-aware search strategies (such as linear or kNN evaluation). We conduct a large-scale empirical study and show that both task-agnostic and task-aware methods can yield high regret. We then propose a simple and computationally efficient hybrid search strategy which outperforms the existing approaches. We highlight the practical benefits of the proposed solution on a set of 19 diverse vision tasks.
-
To deal with the great number of untrimmed videos produced every day, we propose an efficient unsupervised action segmentation method by detecting boundaries, named action boundary detection (ABD). In particular, the proposed method has the following advantages: no training stage and low-latency inference. To detect action boundaries, we estimate the similarities across smoothed frames, which inherently have the properties of internal consistency within actions and external discrepancy across actions. Under this circumstance, we successfully transfer the boundary detection task into the change point detection based on the similarity. Then, non-maximum suppression (NMS) is conducted in local windows to select the smallest points as candidate boundaries. In addition, a clustering algorithm is followed to refine the initial proposals. Moreover, we also extend ABD to the online setting, which enables real-time action segmentation in long untrimmed videos. By evaluating on four challenging datasets, our method achieves state-of-the-art performance. Moreover, thanks to the efficiency of ABD, we achieve the best trade-off between the accuracy and the inference time compared with existing unsupervised approaches.
-
Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations. We propose a 2-stage training scheme, i) feature augmentation - cloning part of the backbone and fine-tuning it on the novel data, and ii) fusion - combining the base and novel classifiers into a unified classifier. Experiments show that the proposed method significantly outperforms state-of-the-art CIL methods on the large-scale ImageNet dataset (e.g. +10% overall accuracy than the best). We also propose and analyze understudied practical CIL scenarios, such as base-novel overlap with distribution shift. Our proposed method is robust and generalizes to all analyzed CIL settings.
-
Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). While most existing graph regularizers focus on manipulating graph topological structures by adding/removing edges, we offer a method to augment node features for better performance. We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. By making the model invariant to small fluctuations in input data, our method helps models generalize to out-of-distribution samples and boosts model performance at test time. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks. FLAG is also highly flexible and scalable, and is deployable with arbitrary GNN backbones and large-scale datasets. We demonstrate the efficacy and stability of our method through extensive experiments and ablation studies. We also provide intuitive observations for a deeper understanding of our method. We open source our implementation at https://github.com/devnkong/FLAG.
-
Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn to denoise the (attacked) point clouds by reconstruction, and then feed them to the classifiers as input. In contrast to the literature, we propose a family of robust structured declarative classifiers for point cloud classification, where the internal constrained optimization mechanism can effectively defend adversarial attacks through implicit gradients. Such classifiers can be formulated using a bilevel optimization framework. We further propose an effective and efficient instantiation of our approach, namely, Lattice Point Classifier (LPC), based on structured sparse coding in the permutohedral lattice and 2D convolutional neural networks (CNNs) that is end-to-end trainable. We demonstrate state-of-the-art robust point cloud classification performance on ModelNet40 and ScanNet under seven different attackers. For instance, we achieve 89.51% and 83.16% test accuracy on each dataset under the recent JGBA attacker that outperforms DUP-Net and IF-Defense with PointNet by 70%. Demo code is available at https://zhang-vislab.github.io.
-
Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout. In this work, we go beyond this to propose PhotoScene, a framework that takes input image(s) of a scene along with approximately aligned CAD geometry (either reconstructed automatically or manually specified) and builds a photorealistic digital twin with high-quality materials and similar lighting. We model scene materials using procedural material graphs; such graphs represent photorealistic and resolution-independent materials. We optimize the parameters of these graphs and their texture scale and rotation, as well as the scene lighting to best match the input image via a differentiable rendering layer. We evaluate our technique on objects and layout reconstructions from ScanNet, SUN RGB-D and stock photographs, and demonstrate that our method reconstructs high-quality, fully relightable 3D scenes that can be re-rendered under arbitrary viewpoints, zooms and lighting.
-
The transferability of adversarial examples allows the deception on black-box models, and transfer-based targeted attacks have attracted a lot of interest due to their practical applicability. To maximize the transfer success rate, adversarial examples should avoid overfitting to the source model, and image augmentation is one of the primary approaches for this. However, prior works utilize simple image transformations such as resizing, which limits input diversity. To tackle this limitation, we propose the object-based diverse input (ODI) method that draws an adversarial image on a 3D object and induces the rendered image to be classified as the target class. Our motivation comes from the humans' superior perception of an image printed on a 3D object. If the image is clear enough, humans can recognize the image content in a variety of viewing conditions. Likewise, if an adversarial example looks like the target class to the model, the model should also classify the rendered image of the 3D object as the target class. The ODI method effectively diversifies the input by leveraging an ensemble of multiple source objects and randomizing viewing conditions. In our experimental results on the ImageNet-Compatible dataset, this method boosts the average targeted attack success rate from 28.3% to 47.0% compared to the state-of-the-art methods. We also demonstrate the applicability of the ODI method to adversarial examples on the face verification task and its superior performance improvement. Our code is available at https://github.com/dreamflake/ODI.
-
We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material textures readily deployable in existing graphics pipelines. We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material textures readily deployable in existing graphics pipelines. Our method adopts neural representations for geometry as signed distance fields (SDFs) and materials during optimization to enjoy their flexibility and compactness, and features a hybrid optimization scheme for neural SDFs: first, optimize using a volumetric radiance field approach to recover correct topology, then optimize further using edge-aware physics-based surface rendering for geometry refinement and disentanglement of materials and lighting. In the second stage, we also draw inspiration from mesh-based differentiable rendering, and design a novel edge sampling algorithm for neural SDFs to further improve performance. We show that our IRON achieves significantly better inverse rendering quality compared to prior works.
-
Objects play a crucial role in our everyday activities. Though multisensory object-centric learning has shown great potential lately, the modeling of objects in prior work is rather unrealistic. ObjectFolder 1.0 is a recent dataset that introduces 100 virtualized objects with visual, auditory, and tactile sensory data. However, the dataset is small in scale and the multisensory data is of limited quality, hampering generalization to real-world scenarios. We present ObjectFolder 2.0, a large-scale, multisensory dataset of common household objects in the form of implicit neural representations that significantly enhances ObjectFolder 1.0 in three aspects. First, our dataset is 10 times larger in the amount of objects and orders of magnitude faster in rendering time. Second, we significantly improve the multisensory rendering quality for all three modalities. Third, we show that models learned from virtual objects in our dataset successfully transfer to their real-world counterparts in three challenging tasks: object scale estimation, contact localization, and shape reconstruction. ObjectFolder 2.0 offers a new path and testbed for multisensory learning in computer vision and robotics. The dataset is available at https://github.com/rhgao/ObjectFolder.
-
Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train model that serves as a foundation for data-efficient downstream tasks transfer. To this end, we propose the Human-Centric Multi-Modal Contrastive Learning framework HCMoCo that leverages the multi-modal nature of human data (e.g. RGB, depth, 2D keypoints) for effective representation learning. The objective comes with two main challenges: dense pre-train for multi-modality data, efficient usage of sparse human priors. To tackle the challenges, we design the novel Dense Intra-sample Contrastive Learning and Sparse Structure-aware Contrastive Learning targets by hierarchically learning a modal-invariant latent space featured with continuous and ordinal feature distribution and structure-aware semantic consistency. HCMoCo provides pre-train for different modalities by combining heterogeneous datasets, which allows efficient usage of existing task-specific human data. Extensive experiments on four downstream tasks of different modalities demonstrate the effectiveness of HCMoCo, especially under data-efficient settings (7.16% and 12% improvement on DensePose Estimation and Human Parsing). Moreover, we demonstrate the versatility of HCMoCo by exploring cross-modality supervision and missing-modality inference, validating its strong ability in cross-modal association and reasoning.
-
360deg cameras can capture complete environments in a single shot, which makes 360deg imagery alluring in many computer vision tasks. However, monocular depth estimation remains a challenge for 360deg data, particularly for high resolutions like 2K (2048x1024) and beyond that are important for novel-view synthesis and virtual reality applications. Current CNN-based methods do not support such high resolutions due to limited GPU memory. In this work, we propose a flexible framework for monocular depth estimation from high-resolution 360deg images using tangent images. We project the 360deg input image onto a set of tangent planes that produce perspective views, which are suitable for the latest, most accurate state-of-the-art perspective monocular depth estimators. To achieve globally consistent disparity estimates, we recombine the individual depth estimates using deformable multi-scale alignment followed by gradient-domain blending. The result is a dense, high-resolution 360deg depth map with a high level of detail, also for outdoor scenes which are not supported by existing methods. Our source code and data are available at https://manurare.github.io/360monodepth/.
-
We present a method for semantically transferring the visual appearance of one natural image to another. Specifically, our goal is to generate an image in which objects in a source structure image are "painted" with the visual appearance of their semantically related objects in a target appearance image. Our method works by training a generator given only a single structure/appearance image pair as input. To integrate semantic information into our framework---a pivotal component in tackling this task---our key idea is to leverage a pre-trained and fixed Vision Transformer (ViT) model which serves as an external semantic prior. Specifically, we derive novel representations of structure and appearance extracted from deep ViT features, untwisting them from the learned self-attention modules. We then establish an objective function that splices the desired structure and appearance representations, interweaving them together in the space of ViT features. Our framework, which we term "Splice", does not involve adversarial training, nor does it require any additional input information such as semantic segmentation or correspondences, and can generate high resolution results, e.g., work in HD. We demonstrate high quality results on a variety of in-the-wild image pairs, under significant variations in the number of objects, their pose and appearance.
-
Appearance-based Gaze Estimation leverages deep neural networks to regress the gaze direction from monocular images and achieve impressive performance. However, its success depends on expensive and cumbersome annotation capture. When lacking precise annotation, the large domain gap hinders the performance of trained models on new domains. In this paper, we propose a novel gaze adaptation approach, namely Contrastive Regression Gaze Adaptation (CRGA), for generalizing gaze estimation on the target domain in an unsupervised manner. CRGA leverages the Contrastive Domain Generalization (CDG) module to learn the stable representation from the source domain and leverages the Contrastive Self-training Adaptation (CSA) module to learn from the pseudo labels on the target domain. The core of both CDG and CSA is the Contrastive Regression (CR) loss, a novel contrastive loss for regression by pulling features with closer gaze directions closer together while pushing features with farther gaze directions farther apart. Experimentally, we choose ETH-XGAZE and Gaze-360 as the source domain and test the domain generalization and adaptation performance on MPIIGAZE, RT-GENE, GazeCapture, EyeDiap respectively. The results demonstrate that our CRGA achieves remarkable performance improvement compared with the baseline models and also outperforms the state-of-the-art domain adaptation approaches on gaze adaptation tasks.
-
Accurate long-term trajectory prediction in complex scenes, where multiple agents (e.g., pedestrians or vehicles) interact with each other and the environment while attempting to accomplish diverse and often unknown goals, is a challenging stochastic forecasting problem. In this work, we propose MUSE-VAE, a new probabilistic modeling framework based on a cascade of Conditional VAEs, which tackles the long-term, uncertain trajectory prediction task using a coarse-to-fine multi-factor forecasting architecture. In its Macro stage, the model learns a joint pixel-space representation of two key factors, the underlying environment and the agent movements, to predict the long and short term motion goals. Conditioned on them, the Micro stage learns a fine-grained spatio-temporal representation for the prediction of individual agent trajectories. The VAE backbones across the two stages make it possible to naturally account for the joint uncertainty at both levels of granularity. As a result, MUSE-VAE offers diverse and simultaneously more accurate predictions compared to the current state-of-the-art. We demonstrate these assertions through a comprehensive set of experiments on nuScenes and SDD benchmarks as well as PFSD, a new synthetic dataset, which challenges the forecasting ability of models on complex agent-environment interaction scenarios.
-
3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view consistent images. To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints. By leveraging the underlying 3D geometry information of generated images, i.e., depth and camera transformation matrix, we explicitly establish stereo correspondence between views to perform multi-view joint optimization. In particular, we enforce the photometric consistency between pairs of views and integrate a stereo mixup mechanism into the training process, encouraging the model to reason about the correct 3D shape. Besides, we design a two-stage training strategy with feature-level multi-view joint optimization to improve the image quality. Extensive experiments on three datasets demonstrate that MVCGAN achieves the state-of-the-art performance for 3D-aware image synthesis.
-
Given an image with multiple people, our goal is to directly regress the pose and shape of all the people as well as their relative depth. Inferring the depth of a person in an image, however, is fundamentally ambiguous without knowing their height. This is particularly problematic when the scene contains people of very different sizes, e.g. from infants to adults. To solve this, we need several things. First, we develop a novel method to infer the poses and depth of multiple people in a single image. While previous work that estimates multiple people does so by reasoning in the image plane, our method, called BEV, adds an additional imaginary Bird's-Eye-View representation to explicitly reason about depth. BEV reasons simultaneously about body centers in the image and in depth and, by combing these, estimates 3D body position. Unlike prior work, BEV is a single-shot method that is end-to-end differentiable. Second, height varies with age, making it impossible to resolve depth without also estimating the age of people in the image. To do so, we exploit a 3D body model space that lets BEV infer shapes from infants to adults. Third, to train BEV, we need a new dataset. Specifically, we create a "Relative Human" (RH) dataset that includes age labels and relative depth relationships between the people in the images. Extensive experiments on RH and AGORA demonstrate the effectiveness of the model and training scheme. BEV outperforms existing methods on depth reasoning, child shape estimation, and robustness to occlusion. The code and dataset are released for research purposes.
-
Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector. To overcome this limitation, a few approaches infer latent vectors on a coarse regular 3D grid or on 3D patches, and interpolate them to answer occupancy queries. In doing so, they loose the direct connection with the input points sampled on the surface of objects, and they attach information uniformly in space rather than where it matters the most, i.e., near the surface. Besides, relying on fixed patch sizes may require discretization tuning. To address these issues, we propose to use point cloud convolutions and compute latent vectors at each input point. We then perform a learning-based interpolation on nearest neighbors using inferred weights. Experiments on both object and scene datasets show that our approach significantly outperforms other methods on most classical metrics, producing finer details and better reconstructing thinner volumes. The code is available at https://github.com/valeoai/POCO
-
In this paper, we propose a simple yet effective video super-resolution method that aims at generating high-fidelity high-resolution (HR) videos from low-resolution (LR) ones. Previous methods predominantly leverage temporal neighbor frames to assist the super-resolution of the current frame. Those methods achieve limited performance as they suffer from the challenges in spatial frame alignment and the lack of useful information from similar LR neighbor frames. In contrast, we devise a cross-frame non-local attention mechanism that allows video super-resolution without frame alignment, leading to being more robust to large motions in the video. In addition, to acquire general video prior information beyond neighbor frames, and to compensate for the information loss caused by large motions, we design a novel memory-augmented attention module to memorize general video details during the super-resolution training. We have thoroughly evaluated our work on various challenging datasets. Compared to other recent video super-resolution approaches, our method not only achieves significant performance gains on large motion videos but also shows better generalization. Our source code and the new Parkour benchmark dataset will be released.
-
We deal with the controllable person image synthesis task which aims to re-render a human from a reference image with explicit control over body pose and appearance. Observing that person images are highly structured, we propose to generate desired images by extracting and distributing semantic entities of reference images. To achieve this goal, a neural texture extraction and distribution operation based on double attention is described. This operation first extracts semantic neural textures from reference feature maps. Then, it distributes the extracted neural textures according to the spatial distributions learned from target poses. Our model is trained to predict human images in arbitrary poses, which encourages it to extract disentangled and expressive neural textures representing the appearance of different semantic entities. The disentangled representation further enables explicit appearance control. Neural textures of different reference images can be fused to control the appearance of the interested areas. Experimental comparisons show the superiority of the proposed model. Code is available at https://github.com/RenYurui/Neural-Texture-Extraction-Distribution.
-
Today's VidSGG models are all proposal-based methods, i.e., they first generate numerous paired subject-object snippets as proposals, and then conduct predicate classification for each proposal. In this paper, we argue that this prevalent proposal-based framework has three inherent drawbacks: 1) The ground-truth predicate labels for proposals are partially correct. 2) They break the high-order relations among different predicate instances of a same subject-object pair. 3) VidSGG performance is upper-bounded by the quality of the proposals. To this end, we propose a new classification-then-grounding framework for VidSGG, which can avoid all the three overlooked drawbacks. Meanwhile, under this framework, we reformulate the video scene graphs as temporal bipartite graphs, where the entities and predicates are two types of nodes with time slots, and the edges denote different semantic roles between these nodes. This formulation takes full advantage of our new framework. Accordingly, we further propose a novel BIpartite Graph based SGG model: BIG. It consists of a classification stage and a grounding stage, where the former aims to classify the categories of all the nodes and the edges, and the latter tries to localize the temporal location of each relation instance. Extensive ablations on two VidSGG datasets have attested to the effectiveness of our framework and BIG. Code is available at https://github.com/Dawn-LX/VidSGG-BIG.
-
Magnetic resonance imaging (MRI) can present multi-contrast images of the same anatomical structures, enabling multi-contrast super-resolution (SR) techniques. Compared with SR reconstruction using a single-contrast, multi-contrast SR reconstruction is promising to yield SR images with higher quality by leveraging diverse yet complementary information embedded in different imaging modalities. However, existing methods still have two shortcomings: (1) they neglect that the multi-contrast features at different scales contain different anatomical details and hence lack effective mechanisms to match and fuse these features for better reconstruction; and (2) they are still deficient in capturing long-range dependencies, which are essential for the regions with complicated anatomical structures. We propose a novel network to comprehensively address these problems by developing a set of innovative Transformer-empowered multi-scale contextual matching and aggregation techniques; we call it McMRSR. Firstly, we tame transformers to model long-range dependencies in both reference and target images. Then, a new multi-scale contextual matching method is proposed to capture corresponding contexts from reference features at different scales. Furthermore, we introduce a multi-scale aggregation mechanism to gradually and interactively aggregate multi-scale matched features for reconstructing the target SR MR image. Extensive experiments demonstrate that our network outperforms state-of-the-art approaches and has great potential to be applied in clinical practice.
-
Appearance-based gaze estimation aims to predict the 3D eye gaze direction from a single image. While recent deep learning-based approaches have demonstrated excellent performance, they usually assume one calibrated face in each input image and cannot output multi-person gaze in real time. However, simultaneous gaze estimation for multiple people in the wild is necessary for real-world applications. In this paper, we propose the first one-stage end-to-end gaze estimation method, GazeOnce, which is capable of simultaneously predicting gaze directions for multiple faces (>10) in an image. In addition, we design a sophisticated data generation pipeline and propose a new dataset, MPSGaze, which contains full images of multiple people with 3D gaze ground truth. Experimental results demonstrate that our unified framework not only offers a faster speed, but also provides a lower gaze estimation error compared with state-of-the-art methods. This technique can be useful in real-time applications with multiple users.
-
Online action detection is the task of predicting the action as soon as it happens in a streaming video. A major challenge is that the model does not have access to the future and has to solely rely on the history, i.e., the frames observed so far, to make predictions. It is therefore important to accentuate parts of the history that are more informative to the prediction of the current frame. We present GateHUB, Gated History Unit with Background Suppression, that comprises a novel position-guided gated cross-attention mechanism to enhance or suppress parts of the history as per how informative they are for current frame prediction. GateHUB further proposes Future-augmented History (FaH) to make history features more informative by using subsequently observed frames when available. In a single unified framework, GateHUB integrates the transformer's ability of long-range temporal modeling and the recurrent model's capacity to selectively encode relevant information. GateHUB also introduces a background suppression objective to further mitigate false positive background frames that closely resemble the action frames. Extensive validation on three benchmark datasets, THUMOS, TVSeries, and HDD, demonstrates that GateHUB significantly outperforms all existing methods and is also more efficient than the existing best work. Furthermore, a flow-free version of GateHUB is able to achieve higher or close accuracy at 2.8x higher frame rate compared to all existing methods that require both RGB and optical flow information for prediction.
-
Few-shot font generation (FFG), which aims to generate a new font with a few examples, is gaining increasing attention due to the significant reduction in labor cost. A typical FFG pipeline considers characters in a standard font library as content glyphs and transfers them to a new target font by extracting style information from the reference glyphs. Most existing solutions explicitly disentangle content and style of reference glyphs globally or component-wisely. However, the style of glyphs mainly lies in the local details, i.e. the styles of radicals, components, and strokes together depict the style of a glyph. Therefore, even a single character can contain different styles distributed over spatial locations. In this paper, we propose a new font generation approach by learning 1) the fine-grained local styles from references, and 2) the spatial correspondence between the content and reference glyphs. Therefore each spatial location in the content glyph can be assigned with the right fine-grained style. To this end, we adopt cross-attention over the representation of the content glyphs as the queries and the representations of the reference glyphs as the keys and values. Instead of explicitly disentangling global or component-wise modeling, the cross attention mechanism can attend to the right local styles in the reference glyphs and aggregates the reference styles into a fine-grained style representation for the given content glyphs. The experiments show that the proposed method outperforms the state-of-the-art methods in FFG. In particular, the user studies also demonstrate the style consistency of our approach is significantly outperforms previous methods.
-
Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local associations between videos and texts. Another line of research uses a joint encoder to interact video with texts, but results in low efficiency since each text-video pair needs to be fed into the model. In this work, we enable fine-grained video-text interactions while maintaining high efficiency for retrieval via a novel pretext task, dubbed as Multiple Choice Questions (MCQ), where a parametric module BridgeFormer is trained to answer the "questions" constructed by the text features via resorting to the video features. Specifically, we exploit the rich semantics of text (i.e., nouns and verbs) to build questions, with which the video encoder can be trained to capture more regional content and temporal dynamics. In the form of questions and answers, the semantic associations between local video-text features can be properly established. BridgeFormer is able to be removed for downstream retrieval, rendering an efficient and flexible model with only two encoders. Our method outperforms state-of-the-art methods on the popular text-to-video retrieval task in five datasets with different experimental setups (i.e., zero-shot and fine-tune), including HowTo100M (one million videos). We further conduct zero-shot action recognition, which can be cast as video-to-text retrieval, and our approach also significantly surpasses its counterparts. As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e.g., action recognition with linear evaluation.
-
Talking head video generation aims to produce a synthetic human face video that contains the identity and pose information respectively from a given source image and a driving video. Existing works for this task heavily rely on 2D representations (e.g. appearance and motion) learned from the input images. However, dense 3D facial geometry (e.g. pixel-wise depth) is extremely important for this task as it is particularly beneficial for us to essentially generate accurate 3D face structures and distinguish noisy information from the possibly cluttered background. Nevertheless, dense 3D geometry annotations are prohibitively costly for videos and are typically not available for this video generation task. In this paper, we introduce a self-supervised face-depth learning method to automatically recover dense 3D facial geometry (i.e. depth) from the face videos without the requirement of any expensive 3D annotation data. Based on the learned dense depth maps, we further propose to leverage them to estimate sparse facial keypoints that capture the critical movement of the human head. In a more dense way, the depth is also utilized to learn 3D-aware cross-modal (i.e. appearance and depth) attention to guide the generation of motion fields for warping source image representations. All these contributions compose a novel depth-aware generative adversarial network (DaGAN) for talking head generation. Extensive experiments conducted demonstrate that our proposed method can generate highly realistic faces, and achieve significant results on the unseen human faces.
-
Deep image inpainting can inpaint a corrupted image using a feed-forward inference, but still fails to handle large missing area or complex semantics. Recently, GAN inversion based inpainting methods propose to leverage semantic information in pretrained generator (e.g., StyleGAN) to solve the above issues. Different from feed-forward methods, they seek for a closest latent code to the corrupted image and feed it to a pretrained generator. However, inferring the latent code is either time-consuming or inaccurate. In this paper, we develop a dual-path inpainting network with inversion path and feed-forward path, in which inversion path provides auxiliary information to help feed-forward path. We also design a novel deformable fusion module to align the feature maps in two paths. Experiments on FFHQ and LSUN demonstrate that our method is effective in solving the aforementioned problems while producing more realistic results than state-of-the-art methods.
-
Synthesizing high-quality realistic images from text descriptions is a challenging task. Existing text-to-image Generative Adversarial Networks generally employ a stacked architecture as the backbone yet still remain three flaws. First, the stacked architecture introduces the entanglements between generators of different image scales. Second, existing studies prefer to apply and fix extra networks in adversarial learning for text-image semantic consistency, which limits the supervision capability of these networks. Third, the cross-modal attention-based text-image fusion that widely adopted by previous works is limited on several special image scales because of the computational cost. To these ends, we propose a simpler but more effective Deep Fusion Generative Adversarial Networks (DF-GAN). To be specific, we propose: (i) a novel one-stage text-to-image backbone that directly synthesizes high-resolution images without entanglements between different generators, (ii) a novel Target-Aware Discriminator composed of Matching-Aware Gradient Penalty and One-Way Output, which enhances the text-image semantic consistency without introducing extra networks, (iii) a novel deep text-image fusion block, which deepens the fusion process to make a full fusion between text and visual features. Compared with current state-of-the-art methods, our proposed DF-GAN is simpler but more efficient to synthesize realistic and text-matching images and achieves better performance on widely used datasets. Code is available at https://github.com/tobran/DF-GAN.
-
Flow-based generative models have shown an excellent ability to explicitly learn the probability density function of data via a sequence of invertible transformations. Yet, learning attentions in generative flows remains understudied, while it has made breakthroughs in other domains. To fill the gap, this paper introduces two types of invertible attention mechanisms, i.e., map-based and transformer-based attentions, for both unconditional and conditional generative flows. The key idea is to exploit a masked scheme of these two attentions to learn long-range data dependencies in the context of generative flows. The masked scheme allows for invertible attention modules with tractable Jacobian determinants, enabling its seamless integration at any positions of the flow-based models. The proposed attention mechanisms lead to more efficient generative flows, due to their capability of modeling the long-term data dependencies. Evaluation on multiple image synthesis tasks shows that the proposed attention flows result in efficient models and compare favorably against the state-of-the-art unconditional and conditional generative flows.
-
Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic Neural Networks (HNNs) exploit such representational power by lifting Euclidean features into hyperbolic space for classification, outperforming Euclidean neural networks (ENNs) on datasets with known semantic hierarchies. However, HNNs underperform ENNs on standard benchmarks without clear hierarchies, greatly restricting HNNs' applicability in practice. Our key insight is that HNNs' poorer general classification performance results from vanishing gradients during backpropagation, caused by their hybrid architecture connecting Euclidean features to a hyperbolic classifier. We propose an effective solution by simply clipping the Euclidean feature magnitude while training HNNs. Our experiments demonstrate that clipped HNNs become super-hyperbolic classifiers: They are not only consistently better than HNNs which already outperform ENNs on hierarchical data, but also on-par with ENNs on MNIST, CIFAR10, CIFAR100 and ImageNet benchmarks, with better adversarial robustness and out-of-distribution detection.
-
Image denoising has achieved unprecedented progress as great efforts have been made to exploit effective deep denoisers. To improve the denoising performance in real-world, two typical solutions are used in recent trends: devising better noise models for the synthesis of more realistic training data, and estimating noise level function to guide non-blind denoisers. In this work, we combine both noise modeling and estimation, and propose an innovative noise model estimation and noise synthesis pipeline for realistic noisy image generation. Specifically, our model learns a noise estimation model with fine-grained statistical noise model in a contrastive manner. Then, we use the estimated noise parameters to model camera-specific noise distribution, and synthesize realistic noisy training data. The most striking thing for our work is that by calibrating noise models of several sensors, our model can be extended to predict other cameras. In other words, we can estimate camera-specific noise models for unknown sensors with only testing images, without any laborious calibration frames or paired noisy/clean data. The proposed pipeline endows deep denoisers with competitive performances with state-of-the-art real noise modeling methods.
-
Current deep neural network approaches for camera pose estimation rely on scene structure for 3D motion estimation, but this decreases the robustness and thereby makes cross-dataset generalization difficult. In contrast, classical approaches to structure from motion estimate 3D motion utilizing optical flow and then compute depth. Their accuracy, however, depends strongly on the quality of the optical flow. To avoid this issue, direct methods have been proposed, which separate 3D motion from depth estimation but compute 3D motion using only image gradients in the form of normal flow. In this paper, we introduce a network NFlowNet, for normal flow estimation which is used to enforce robust and direct constraints. In particular, normal flow is used to estimate relative camera pose based on the cheirality (depth positivity) constraint. We achieve this by formulating the optimization problem as a differentiable cheirality layer, which allows for end-to-end learning of camera pose. We perform extensive qualitative and quantitative evaluation of the proposed DiffPoseNet's sensitivity to noise and its generalization across datasets. We compare our approach to existing state-of-the-art methods on KITTI, TartanAir, and TUM-RGBD datasets
-
Finding prototypes (e.g., mean and median) for a dataset is central to a number of common machine learning algorithms. Subspaces have been shown to provide useful, robust representations for datasets of images, videos and more. Since subspaces correspond to points on a Grassmann manifold, one is led to consider the idea of a subspace prototype for a Grassmann-valued dataset. While a number of different subspace prototypes have been described, the calculation of some of these prototypes has proven to be computationally expensive while other prototypes are affected by outliers and produce highly imperfect clustering on noisy data. This work proposes a new subspace prototype, the flag median, and introduces the FlagIRLS algorithm for its calculation. We provide evidence that the flag median is robust to outliers and can be used effectively in algorithms like Linde-Buzo-Grey (LBG) to produce improved clusterings on Grassmannians. Numerical experiments include a synthetic dataset, the MNIST handwritten digits dataset, the Mind's Eye video dataset and the UCF YouTube action dataset. The flag median is compared the other leading algorithms for computing prototypes on the Grassmannian, namely, the l_2-median and to the flag mean. We find that using FlagIRLS to compute the flag median converges in 4 iterations on a synthetic dataset. We also see that Grassmannian LBG with a codebook size of 20 and using the flag median produces at least a 10% improvement in cluster purity over Grassmannian LBG using the flag mean or l_2-median on the Mind's Eye dataset.
-
Quantization has been applied to multiple domains in Deep Neural Networks (DNNs). We propose Depthwise Quantization (DQ) where quantization is applied to a decomposed sub-tensor along the feature axis of weak statistical dependence. The feature decomposition leads to an exponential increase in representation capacity with a linear increase in memory and parameter cost. In addition, DQ can be directly applied to existing encoder-decoder frameworks without modification of the DNN architecture. We use DQ in the context of Hierarchical Auto-Encoders and train end-to-end on an image feature representation. We provide an analysis of the cross-correlation between spatial and channel features and propose a decomposition of the image feature representation along the channel axis. The improved performance of the depthwise operator is due to the increased representation capacity from implicit feature decoupling. We evaluate DQ on the likelihood estimation task, where it outperforms the previous state-of-the-art on CIFAR-10, ImageNet-32 and ImageNet-64. We progressively train with increasing image size a single hierarchical model that uses 69% fewer parameters and has faster convergence than the previous work.
-
Deep learning for graph matching has received growing interest and developed rapidly in the past decade. Although recent deep graph matching methods have shown excellent performance on matching between graphs of equal size in the computer vision area, the size-varied graph matching problem, where the number of keypoints in the images of the same category may vary due to occlusion, is still an open and challenging problem. To tackle this, we firstly propose to formulate the combinatorial problem of graph matching as an Integer Linear Programming (ILP) problem, which is more flexible and efficient to facilitate comparing graphs of varied sizes. A novel Graph-context Attention Network (GCAN), which jointly capture intrinsic graph structure and cross-graph information for improving the discrimination of node features, is then proposed and trained to resolve this ILP problem with node correspondence supervision. We further show that the proposed GCAN model is efficient to resolve the graph-level matching problem and is able to automatically learn node-to-node similarity via graph-level matching. The proposed approach is evaluated on three public keypoint-matching datasets and one graph-matching dataset for blood vessel patterns, with experimental results showing its superior performance over existing state-of-the-art algorithms on the keypoint and graph-level matching tasks.
-
Previous portrait image generation methods roughly fall into two categories: 2D GANs and 3D-aware GANs. 2D GANs can generate high fidelity portraits but with low view consistency. 3D-aware GAN methods can maintain view consistency but their generated images are not locally editable. To overcome these limitations, we propose FENeRF, a 3D-aware generator that can produce view-consistent and locally-editable portrait images. Our method uses two decoupled latent codes to generate corresponding facial semantics and texture in a spatial-aligned 3D volume with shared geometry. Benefiting from such underlying 3D representation, FENeRF can jointly render the boundary-aligned image and semantic mask and use the semantic mask to edit the 3D volume via GAN inversion. We further show such 3D representation can be learned from widely available monocular image and semantic mask pairs. Moreover, we reveal that joint learning semantics and texture helps to generate finer geometry. Our experiments demonstrate that FENeRF outperforms state-of-the-art methods in various face editing tasks.
-
We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i.e. camera control). We allow the user to annotate which part of the scene one wishes to control with just a small number of mask annotations in the training images. Our key idea is to treat the attributes as latent variables that are regressed by the neural network given the scene encoding. This leads to a few-shot learning framework, where attributes are discovered automatically by the framework when annotations are not provided. We apply our method to various scenes with different types of controllable attributes (e.g. expression control on human faces, or state control in the movement of inanimate objects). Overall, we demonstrate, to the best of our knowledge, for the first time novel view and novel attribute re-rendering of scenes from a single video.
-
Image noise modeling is a long-standing problem with many applications in computer vision. Early attempts that propose simple models, such as signal-independent additive white Gaussian noise or the heteroscedastic Gaussian noise model (a.k.a., camera noise level function) are not sufficient to learn the complex behavior of the camera sensor noise. Recently, more complex learning-based models have been proposed that yield better results in noise synthesis and downstream tasks, such as denoising. However, their dependence on supervised data (i.e., paired clean images) is a limiting factor given the challenges in producing ground-truth images. This paper proposes a framework for training a noise model and a denoiser simultaneously while relying only on pairs of noisy images rather than noisy/clean paired image data. We apply this framework to the training of the Noise Flow architecture. The noise synthesis and density estimation results show that our framework outperforms previous signal-processing-based noise models and is on par with its supervised counterpart. The trained denoiser is also shown to significantly improve upon both supervised and weakly supervised baseline denoising approaches. The results indicate that the joint training of a denoiser and a noise model yields significant improvements in the denoiser.
-
Less than 35% of recyclable waste is being actually recycled in the US, which leads to increased soil and sea pollution and is one of the major concerns of environmental researchers as well as the common public. At the heart of the problem are the inefficiencies of the waste sorting process (separating paper, plastic, metal, glass, etc.) due to the extremely complex and cluttered nature of the waste stream. Recyclable waste detection poses a unique computer vision challenge as it requires detection of highly deformable and often translucent objects in cluttered scenes without the kind of context information usually present in human-centric datasets. This challenging computer vision task currently lacks suitable datasets or methods in the available literature. In this paper, we take a step towards computer-aided waste detection and present the first in-the-wild industrial-grade waste detection and segmentation dataset, ZeroWaste. We believe that ZeroWaste will catalyze research in object detection and semantic segmentation in extreme clutter as well as applications in the recycling domain. Our project page can be found at http://ai.bu.edu/zerowaste/.
-
To realize trajectory prediction, most previous methods adopt the parameter-based approach, which encodes all the seen past-future instance pairs into model parameters. However, in this way, the model parameters come from all seen instances, which means a huge amount of irrelevant seen instances might also involve in predicting the current situation, disturbing the performance. To provide a more explicit link between the current situation and the seen instances, we imitate the mechanism of retrospective memory in neuropsychology and propose MemoNet, an instance-based approach that predicts the movement intentions of agents by looking for similar scenarios in the training data. In MemoNet, we design a pair of memory banks to explicitly store representative instances in the training set, acting as prefrontal cortex in the neural system, and a trainable memory addresser to adaptively search a current situation with similar instances in the memory bank, acting like basal ganglia. During prediction, MemoNet recalls previous memory by using the memory addresser to index related instances in the memory bank. We further propose a two-step trajectory prediction system, where the first step is to leverage MemoNet to predict the destination and the second step is to fulfill the whole trajectory according to the predicted destinations. Experiments show that the proposed MemoNet improves the FDE by 20.3%/10.2%/28.3% from the previous best method on SDD/ETH-UCY/NBA datasets. Experiments also show that our MemoNet has the ability to trace back to specific instances during prediction, promoting more interpretability.
-
Recent video question answering benchmarks indicate that state-of-the-art models struggle to answer compositional questions. However, it remains unclear which types of compositional reasoning cause models to mispredict. Furthermore, it is difficult to discern whether models arrive at answers using compositional reasoning or by leveraging data biases. In this paper, we develop a question decomposition engine that programmatically deconstructs a compositional question into a directed acyclic graph of sub-questions. The graph is designed such that each parent question is a composition of its children. We present AGQA-Decomp, a benchmark containing 2.3M question graphs, with an average of 11.49 sub-questions per graph, and 4.55M total new sub-questions. Using question graphs, we evaluate three state-of-the-art models with a suite of novel compositional consistency metrics. We find that models either cannot reason correctly through most compositions or are reliant on incorrect reasoning to reach answers, frequently contradicting themselves or achieving high accuracies when failing at intermediate reasoning steps.
-
Instance contrast for unsupervised representation learning has achieved great success in recent years. In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks. By considering instance contrastive learning as a dictionary look-up operation, we construct a semantics-aware dictionary with samples from both source and target domains where each target sample is assigned a (pseudo) category label based on the category priors of source samples. This allows category contrastive learning (between target queries and the category-level dictionary) for category-discriminative yet domain-invariant feature representations: samples of the same category (from either source or target domain) are pulled closer while those of different categories are pushed apart simultaneously. Extensive UDA experiments in multiple visual tasks (e.g., segmentation, classification and detection) show that CaCo achieves superior performance as compared with state-of-the-art methods. The experiments also demonstrate that CaCo is complementary to existing UDA methods and generalizable to other learning setups such as unsupervised model adaptation, open-/partial-set adaptation etc.
-
While Visual Question Answering (VQA) has progressed rapidly, previous works raise concerns about robustness of current VQA models. In this work, we study the robustness of VQA models from a novel perspective: visual context. We suggest that the models over-rely on the visual context, i.e., irrelevant objects in the image, to make predictions. To diagnose the models' reliance on visual context and measure their robustness, we propose a simple yet effective perturbation technique, SwapMix. SwapMix perturbs the visual context by swapping features of irrelevant context objects with features from other objects in the dataset. Using SwapMix we are able to change answers to more than 45% of the questions for a representative VQA model. Additionally, we train the models with perfect sight and find that the context over-reliance highly depends on the quality of visual representations. In addition to diagnosing, SwapMix can also be applied as a data augmentation strategy during training in order to regularize the context over-reliance. By swapping the context object features, the model reliance on context can be suppressed effectively. Two representative VQA models are studied using SwapMix: a co-attention model MCAN and a large-scale pretrained model LXMERT. Our experiments on the popular GQA dataset show the effectiveness of SwapMix for both diagnosing model robustness, and regularizing the over-reliance on visual context.
-
We introduce UNIST, the first deep neural implicit model for general-purpose, unpaired shape-to-shape translation, in both 2D and 3D domains. Our model is built on autoencoding implicit fields, rather than point clouds which represents the state of the art. Furthermore, our translation network is trained to perform the task over a latent grid representation which combines the merits of both latent-space processing and position awareness, to not only enable drastic shape transforms but also well preserve spatial features and fine local details for natural shape translations. With the same network architecture and only dictated by the input domain pairs, our model can learn both style-preserving content alteration and content-preserving style transfer. We demonstrate the generality and quality of the translation results, and compare them to well-known baselines. Code is available at https://qiminchen.github.io/unist/.
-
Due to the rising concern of data privacy, it's reasonable to assume the local client data can't be transferred to a centralized server, nor their associated identity label is provided. To support continuous learning and fill the last-mile quality gap, we introduce a new problem setup called Local-Adaptive Face Recognition (LaFR). Leveraging the environment-specific local data after the deployment of the initial global model, LaFR aims at getting optimal performance by training local-adapted models automatically and un-supervisely, as opposed to fixing their initial global model. We achieve this by a newly proposed embedding cluster model based on Graph Convolution Network (GCN), which is trained via meta-optimization procedure. Compared with previous works, our meta-clustering model can generalize well in unseen local environments. With the pseudo identity labels from the clustering results, we further introduce novel regularization techniques to improve the model adaptation performance. Extensive experiments on racial and internal sensor adaptation demonstrate that our proposed solution is more effective for adapting face recognition models in each specific environment. Meanwhile, we show that LaFR can further improve the global model by a simple federated aggregation over the updated local models.
-
Quantitative evaluation has increased dramatically among recent video inpainting work, but the video and mask content used to gauge performance has received relatively little attention. Although attributes such as camera and background scene motion inherently change the difficulty of the task and affect methods differently, existing evaluation schemes fail to control for them, thereby providing minimal insight into inpainting failure modes. To address this gap, we propose the Diagnostic Evaluation of Video Inpainting on Landscapes (DEVIL) benchmark, which consists of two contributions: (i) a novel dataset of videos and masks labeled according to several key inpainting failure modes, and (ii) an evaluation scheme that samples slices of the dataset characterized by a fixed content attribute, and scores performance on each slice according to reconstruction, realism, and temporal consistency quality. By revealing systematic changes in performance induced by particular characteristics of the input content, our challenging benchmark enables more insightful analysis into video inpainting methods and serves as an invaluable diagnostic tool for the field. Our code and data are available at github.com/MichiganCOG/devil.
-
Pan-sharpening aims to integrate the complementary information of texture-rich PAN images and multi-spectral (MS) images to produce the texture-rich MS images. Despite the remarkable progress, existing state-of-the-art Pan-sharpening methods don't explicitly enforce the complementary information learning between two modalities of PAN and MS images. This leads to information redundancy not being handled well, which further limits the performance of these methods. To address the above issue, we propose a novel mutual information-driven Pan-sharpening framework in this paper. To be specific, we first project the PAN and MS image into modality-aware feature space independently, and then impose the mutual information minimization over them to explicitly encourage the complementary information learning. Such operation is capable of reducing the information redundancy and improving the model performance. Extensive experimental results over multiple satellite datasets demonstrate that the proposed algorithm outperforms other state-of-the-art methods qualitatively and quantitatively with great generalization ability to real-world scenes.
-
Visual grounding focuses on establishing fine-grained alignment between vision and natural language, which has essential applications in multimodal reasoning systems. Existing methods use pre-trained query-agnostic visual backbones to extract visual feature maps independently without considering the query information. We argue that the visual features extracted from the visual backbones and the features really needed for multimodal reasoning are inconsistent. One reason is that there are differences between pre-training tasks and visual grounding. Moreover, since the backbones are query-agnostic, it is difficult to completely avoid the inconsistency issue by training the visual backbone end-to-end in the visual grounding framework. In this paper, we propose a Query-modulated Refinement Network (QRNet) to address the inconsistent issue by adjusting intermediate features in the visual backbone with a novel Query-aware Dynamic Attention (QD-ATT) mechanism and query-aware multiscale fusion. The QD-ATT can dynamically compute query-dependent visual attention at the spatial and channel level of the feature maps produced by the visual backbone. We apply the QRNet to an end-to-end visual grounding framework. Extensive experiments show that the proposed method outperforms state-of-the-art methods on five widely used datasets.
-
Self-explaining deep models are designed to learn the latent concept-based explanations implicitly during training, which eliminates the requirement of any post-hoc explanation generation technique. In this work, we propose one such model that appends an explanation generation module on top of any basic network and jointly trains the whole module that shows high predictive performance and generates meaningful explanations in terms of concepts. Our training strategy is suitable for unsupervised concept learning with much lesser parameter space requirements compared to baseline methods. Our proposed model also has provision for leveraging self-supervision on concepts to extract better explanations. However, with full concept supervision, we achieve the best predictive performance compared to recently proposed concept-based explainable models. We report both qualitative and quantitative results with our method, which shows better performance than recently proposed concept-based explainability methods. We reported exhaustive results with two datasets without ground truth concepts, i.e., CIFAR10, ImageNet, and two datasets with ground truth concepts, i.e., AwA2, CUB-200, to show the effectiveness of our method for both cases. To the best of our knowledge, we are the first ante-hoc explanation generation method to show results with a large-scale dataset such as ImageNet.
-
Evaluating and improving planning for autonomous vehicles requires scalable generation of long-tail traffic scenarios. To be useful, these scenarios must be realistic and challenging, but not impossible to drive through safely. In this work, we introduce STRIVE, a method to automatically generate challenging scenarios that cause a given planner to produce undesirable behavior, like collisions. To maintain scenario plausibility, the key idea is to leverage a learned model of traffic motion in the form of a graph-based conditional VAE. Scenario generation is formulated as an optimization in the latent space of this traffic model, perturbing an initial real-world scene to produce trajectories that collide with a given planner. A subsequent optimization is used to find a "solution" to the scenario, ensuring it is useful to improve the given planner. Further analysis clusters generated scenarios based on collision type. We attack two planners and show that STRIVE successfully generates realistic, challenging scenarios in both cases. We additionally "close the loop" and use these scenarios to optimize hyperparameters of a rule-based planner.
-
Multi-object multi-part scene parsing is a challenging task which requires detecting multiple object classes in a scene and segmenting the semantic parts within each object. In this paper, we propose FLOAT, a factorized label space framework for scalable multi-object multi-part parsing. Our framework involves independent dense prediction of object category and part attributes which increases scalability and reduces task complexity compared to the monolithic label space counterpart. In addition, we propose an inference-time 'zoom' refinement technique which significantly improves segmentation quality, especially for smaller objects/parts. Compared to state of the art, FLOAT obtains an absolute improvement of 2.0% for mean IOU (mIOU) and 4.8% for segmentation quality IOU (sqIOU) on the Pascal-Part-58 dataset. For the larger Pascal-Part-108 dataset, the improvements are 2.1% for mIOU and 3.9% for sqIOU. We incorporate previously excluded part attributes and other minor parts of the Pascal-Part dataset to create the most comprehensive and challenging version which we dub Pascal-Part-201. FLOAT obtains improvements of 8.6% for mIOU and 7.5% for sqIOU on the new dataset, demonstrating its parsing effectiveness across a challenging diversity of objects and parts. The code and datasets are available at floatseg.github.io.
-
Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations that are not 3D-consistent; the former limits quality and resolution of the generated images and the latter adversely affects multi-view consistency and shape quality. In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations. We introduce an expressive hybrid explicit-implicit network architecture that, together with other design choices, synthesizes not only high-resolution multi-view-consistent images in real time but also produces high-quality 3D geometry. By decoupling feature generation and neural rendering, our framework is able to leverage state-of-the-art 2D CNN generators, such as StyleGAN2, and inherit their efficiency and expressiveness. We demonstrate state-of-the-art 3D-aware synthesis with FFHQ and AFHQ Cats, among other experiments.
-
In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. Training GANs is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as GANs have a large-scale strategy space. In DO-GAN, we extend the double oracle framework to GANs. We first generalize the players' strategies as the trained models of generator and discriminator from the best response oracles. We then compute the meta-strategies using a linear program. For scalability of the framework where multiple generators and discriminator best responses are stored in the memory, we propose two solutions: 1) pruning the weakly-dominated players' strategies to keep the oracles from becoming intractable; 2) applying continual learning to retain the previous knowledge of the networks. We apply our framework to established GAN architectures such as vanilla GAN, Deep Convolutional GAN, Spectral Normalization GAN and Stacked GAN. Finally, we conduct experiments on MNIST, CIFAR-10 and CelebA datasets and show that DO-GAN variants have significant improvements in both subjective qualitative evaluation and quantitative metrics, compared with their respective GAN architectures.
-
Imaging in low light is extremely challenging due to low photon counts. Using sensitive CMOS cameras, it is currently possible to take videos at night under moonlight (0.05-0.3 lux illumination). In this paper, we demonstrate photorealistic video under starlight (no moon present, <0.001 lux) for the first time. To enable this, we develop a GAN-tuned physics-based noise model to more accurately represent camera noise at the lowest light levels. Using this noise model, we train a video denoiser using a combination of simulated noisy video clips and real noisy still images. We capture a 5-10 fps video dataset with significant motion at approximately 0.6-0.7 millilux with no active illumination. Comparing against alternative methods, we achieve improved video quality at the lowest light levels, demonstrating photorealistic video denoising in starlight for the first time.
-
Interactive image segmentation is an essential tool in pixel-level annotation and image editing. To obtain a high-precision binary segmentation mask, users tend to add interaction clicks around the object details, such as edges and holes, for efficient refinement. Current methods regard these repair clicks as the guidance to jointly determine the global prediction. However, the global view makes the model lose focus from later clicks, and is not in line with user intentions. In this paper, we dive into the view of clicks' eyes to endow them with the decisive role in object details again. To verify the necessity of focus view, we design a simple yet effective pipeline, named FocusCut, which integrates the functions of object segmentation and local refinement. After obtaining the global prediction, it crops click-centered patches from the original image with adaptive scopes to refine the local predictions progressively. Without user perception and parameters increase, our method has achieved state-of-the-art results. Extensive experiments and visualized results demonstrate that FocusCut makes hyper-fine segmentation possible for interactive image segmentation.
-
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects represented by surface meshes, their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral coordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to isometric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
-
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes suboptimal for learning spatio-temporally fine-grained features in videos, where scenes and instances evolve through space and time. In this paper, we present Contextualized Spatio-Temporal Contrastive Learning (ConST-CL) to effectively learn spatio-temporally fine-grained video representations via self-supervision. We first design a region-based pretext task which requires the model to transform instance representations from one view to another, guided by context features. Further, we introduce a simple network design that successfully reconciles the simultaneous learning process of both holistic and local representations. We evaluate our learned representations on a variety of downstream tasks and show that ConST-CL achieves competitive results on 6 datasets, including Kinetics, UCF, HMDB, AVAKinetics, AVA and OTB. Our code and models will be available.
-
Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental challenges such as the lack of convergence and the potential for catastrophic forgetting across real-world heterogeneous devices. In this paper, we demonstrate that self-attention-based architectures (e.g., Transformers) are more robust to distribution shifts and hence improve federated learning over heterogeneous data. Concretely, we conduct the first rigorous empirical investigation of different neural architectures across a range of federated algorithms, real-world benchmarks, and heterogeneous data splits. Our experiments show that simply replacing convolutional networks with Transformers can greatly reduce catastrophic forgetting of previous devices, accelerate convergence, and reach a better global model, especially when dealing with heterogeneous data. We will release our code and pretrained models to encourage future exploration in robust architectures as an alternative to current research efforts on the optimization front.
-
Rigged puppets are one of the most prevalent representations to create 2D character animations. Creating these puppets requires partitioning characters into independently moving parts. In this work, we present a method to automatically identify such articulated parts from a small set of character poses shown in a sprite sheet, which is an illustration of the character that artists often draw before puppet creation. Our method is trained to infer articulated parts, e.g. head, torso and limbs, that can be re-assembled to best reconstruct the given poses. Our results demonstrate significantly better performance than alternatives qualitatively and quantitatively. Our project page https://zhan-xu.github.io/parts/ includes our code and data.
-
While significant progress has been made in garment transfer, one of the most applicable directions of human-centric image generation, existing works overlook the in-the-wild imagery, presenting severe garment-person misalignment as well as noticeable degradation in fine texture details. This paper, therefore, attends to virtual try-on in real-world scenes and brings essential improvements in authenticity and naturalness especially for loose garment (e.g., skirts, formal dresses), challenging poses (e.g., cross arms, bent legs), and cluttered backgrounds. Specifically, we find that the pixel flow excels at handling loose garments whereas the vertex flow is preferred for hard poses, and by combining their advantages we propose a novel generative network called wFlow that can effectively push up garment transfer to in-the-wild context. Moreover, former approaches require paired images for training. Instead, we cut down the laboriousness by working on a newly constructed large-scale video dataset named Dance50k with self-supervised cross-frame training and an online cycle optimization. The proposed Dance50k can boost real-world virtual dressing by covering a wide variety of garments under dancing poses. Extensive experiments demonstrate the superiority of our wFlow in generating realistic garment transfer results for in-the-wild images without resorting to expensive paired datasets.
-
Visual private information leakage is an emerging key issue for the fast growing applications of video understanding like activity recognition. Existing approaches for mitigating privacy leakage in action recognition require privacy labels along with the action labels from the video dataset. However, annotating frames of video dataset for privacy labels is not feasible. Recent developments of self-supervised learning (SSL) have unleashed the untapped potential of the unlabeled data. For the first time, we present a novel training framework which removes privacy information from input video in a self-supervised manner without requiring privacy labels. Our training framework consists of three main components: anonymization function, self-supervised privacy removal branch, and action recognition branch. We train our framework using a minimax optimization strategy to minimize the action recognition cost function and maximize the privacy cost function through a contrastive self-supervised loss. Employing existing protocols of known-action and privacy attributes, our framework achieves a competitive action-privacy trade-off to the existing state-of-the-art supervised methods. In addition, we introduce a new protocol to evaluate the generalization of learned the anonymization function to novel-action and privacy attributes and show that our self-supervised framework outperforms existing supervised methods. Code available at: https://github.com/DAVEISHAN/SPAct
-
As RGB-D sensors become more affordable, using RGB-D images to obtain high-accuracy 6D pose estimation results becomes a better option. State-of-the-art approaches typically use different backbones to extract features for RGB and depth images. They use a 2D CNN for RGB images and a per-pixel point cloud network for depth data, as well as a fusion network for feature fusion. We find that the essential reason for using two independent backbones is the "projection breakdown" problem. In the depth image plane, the projected 3D structure of the physical world is preserved by the 1D depth value and its built-in 2D pixel coordinate (UV). Any spatial transformation that modifies UV, such as resize, flip, crop, or pooling operations in the CNN pipeline, breaks the binding between the pixel value and UV coordinate. As a consequence, the 3D structure is no longer preserved by a modified depth image or feature. To address this issue, we propose a simple yet effective method denoted as Uni6D that explicitly takes the extra UV data along with RGB-D images as input. Our method has a Unified CNN framework for 6D pose estimation with a single CNN backbone. In particular, the architecture of our method is based on Mask R-CNN with two extra heads, one named RT head for directly predicting 6D pose and the other named abc head for guiding the network to map the visible points to their coordinates in the 3D model as an auxiliary module. This end-to-end approach balances simplicity and accuracy, achieving comparable accuracy with state of the arts and 7.2x faster inference speed on the YCB-Video dataset.
-
With increasing focus on augmented and virtual reality applications (XR) comes the demand for algorithms that can lift objects from images and videos into representations that are suitable for a wide variety of related 3D tasks. Large-scale deployment of XR devices and applications means that we cannot solely rely on supervised learning, as collecting and annotating data for the unlimited variety of objects in the real world is infeasible. We present a weakly supervised method that is able to decompose a single image of an object into shape (depth and normals), material (albedo, reflectivity and shininess) and global lighting parameters. For training, the method only relies on a rough initial shape estimate of the training objects to bootstrap the learning process. This shape supervision can come for example from a pretrained depth network or - more generically - from a traditional structure-from-motion pipeline. In our experiments, we show that the method can successfully de-render 2D images into a decomposed 3D representation and generalizes to unseen object categories. Since in-the-wild evaluation is difficult due to the lack of ground truth data, we also introduce a photo-realistic synthetic test set that allows for quantitative evaluation. Please find our project page at: https://github.com/Brummi/derender3d
-
Parametric 3D models have formed a fundamental role in modeling deformable objects, such as human bodies, faces, and hands; however, the construction of such parametric models requires significant manual intervention and domain expertise. Recently, neural implicit 3D representations have shown great expressibility in capturing 3D shape geometry. We observe that deformable object motion is often semantically structured, and thus propose to learn Structured-implicit PArametric Models (SPAMs) as a deformable object representation that structurally decomposes non-rigid object motion into part-based disentangled representations of shape and pose, with each being represented by deep implicit functions. This enables a structured characterization of object movement, with part decomposition characterizing a lower-dimensional space in which we can establish coarse motion correspondence. In particular, we can leverage the part decompositions at test time to fit to new depth sequences of unobserved shapes, by establishing part correspondences between the input observation and our learned part spaces; this guides a robust joint optimization between the shape and pose of all parts, even under dramatic motion sequences. Experiments demonstrate that our part-aware shape and pose understanding lead to state-of-the-art performance in reconstruction and tracking of depth sequences of complex deforming object motion.
-
Recently, deep network-based image compressed sensing methods achieved high reconstruction quality and reduced computational overhead compared with traditional methods. However, existing methods obtain measurements only from partial features in the network and use it only once for image reconstruction. They ignore there are low, mid, and high-level features in the network and all of them are essential for high-quality reconstruction. Moreover, using measurements only once may not be enough for extracting richer information from measurements. To address these issues, we propose a novel Measurements Reuse Convolutional Compressed Sensing Network (MR-CCSNet) which employs Global Sensing Module (GSM) to collect all level features for achieving an efficient sensing and Measurements Reuse Block (MRB) to reuse measurements multiple times on multi-scale. Finally, we conduct a series of experiments on three benchmark datasets to show that our model can significantly outperform state-of-the-art methods. Code is available at https://github.com/fze0012/MR-CCSNet.
-
Auxiliary loss is additional loss besides the main branch loss to help optimize the learning process of neural networks. In order to calculate the auxiliary loss between the feature maps of intermediate layers and the ground truth in the field of semantic segmentation, the size of each feature map must match the ground truth. In all studies using the auxiliary losses with the segmentation models, from what we have investigated, they either use a down-sampling function to reduce the size of the ground truth or use an up-sampling function to increase the size of the feature map in order to match the resolution between the feature map and the ground truth. However, in the process of selecting representative values through down-sampling and up-sampling, information loss is inevitable. In this paper, we introduce Class Probability Preserving (CPP) pooling to alleviate information loss in down-sampling the ground truth in semantic segmentation tasks. We demonstrated the superiority of the proposed method on Cityscapes, Pascal VOC, Pascal Context, and NYU-Depth-v2 datasets by using CPP pooling with auxiliary losses based on seven popular segmentation models. In addition, we propose See-Through Network (SeeThroughNet) that adopts an improved multi-scale attention-coupled decoder structure to maximize the effect of CPP pooling. SeeThroughNet shows cutting-edge results in the field of semantic understanding of urban street scenes, which ranked #1 on the Cityscapes benchmark.
-
Differentiable rendering is an essential operation in modern vision, allowing inverse graphics approaches to 3D understanding to be utilized in modern machine learning frameworks. Yet, explicit shape representations (e.g., voxels, point clouds, meshes), while relatively easily rendered, often suffer from limited geometric fidelity or topological constraints. On the other hand, implicit representations (e.g., occupancy, distance, or radiance fields) preserve greater fidelity, but suffer from complex or inefficient rendering processes, limiting scalability. In this work, we endeavour to address both shortcomings with a novel shape representation that allows fast differentiable rendering within an implicit architecture. Building on implicit distance representations, we define Directed Distance Fields (DDFs), which map an oriented point (position and direction) to surface visibility and depth. Such a field can render a depth map with a single forward pass per pixel, enable differential surface geometry extraction (e.g., surface normals and curvatures) via network derivatives, can be easily composed, and permit extraction of classical unsigned distance fields. Using probabilistic DDFs (PDDFs), we show how to model inherent discontinuities in the underlying field. Finally, we apply our method to fitting single shapes, unpaired 3D-aware generative image modelling, and single-image 3D reconstruction tasks, showcasing strong performance with simple architectural components via the versatility of our representation.
-
Representational learning forms the backbone of most deep learning applications, and the value of a learned representation is intimately tied to its information content regarding different factors of variation. Finding good representations depends on the nature of supervision and the learning algorithm. We propose a novel algorithm that utilizes a weak form of supervision where the data is partitioned into sets according to certain inactive (common) factors of variation which are invariant across elements of each set. Our key insight is that by seeking correspondence between elements of different sets, we learn strong representations that exclude the inactive factors of variation and isolate the active factors that vary within all sets. As a consequence of focusing on the active factors, our method can leverage a mix of set-supervised and wholly unsupervised data, which can even belong to a different domain. We tackle the challenging problem of synthetic-to-real object pose transfer, without pose annotations on anything, by isolating pose information which generalizes to the category level and across the synthetic/real domain gap. The method can also boost performance in supervised settings, by strengthening intermediate representations, as well as operate in practically attainable scenarios with set-supervised natural images, where quantity is limited and nuisance factors of variation are more plentiful.
-
We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects. We derive challenging benchmarks that exploit the unique properties of ABO and measure the current limits of the state-of-the-art on three open problems for real-world 3D object understanding: single-view 3D reconstruction, material estimation, and cross-domain multi-view object retrieval.
-
Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method that pretrains the entire object detection network, including the object localization and embedding components. During pretraining, DETReg predicts object localizations to match the localizations from an unsupervised region proposal generator and simultaneously aligns the corresponding feature embeddings with embeddings from a self-supervised image encoder. We implement DETReg using the DETR family of detectors and show that it improves over competitive baselines when finetuned on COCO, PASCAL VOC, and Airbus Ship benchmarks. In low-data regimes, including semi-supervised and few-shot learning settings, DETReg establishes many state-of-the-art results, e.g., on COCO we see a +6.0 AP improvement for 10-shot detection and +3.5 AP improvement when training with only 1% of the labels.
-
In-the-wild 3D face modelling is a challenging problem as the predicted facial geometry and texture suffer from a lack of reliable clues or priors, when the input images are degraded. To address such a problem, in this paper we propose a novel Learning to Restore (L2R) 3D face framework for unsupervised high-quality face reconstruction from low-resolution images. Rather than directly refining 2D image appearance, L2R learns to recover fine-grained 3D details on the proxy against degradation via extracting generative facial priors. Concretely, L2R proposes a novel albedo restoration network to model high-quality 3D facial texture, in which the diverse guidance from the pre-trained Generative Adversarial Networks (GANs) is leveraged to complement the lack of input facial clues. With the finer details of the restored 3D texture, L2R then learns displacement maps from scratch to enhance the significant facial structure and geometry. Both of the procedures are mutually optimized with a novel 3D-aware adversarial loss, which further improves the modelling performance and suppresses the potential uncertainty. Extensive experiments on benchmarks show that L2R outperforms state-of-the-art methods under the condition of low-quality inputs, and obtains superior performances than 2D pre-processed modelling approaches with limited 3D proxy.
-
Defense models against adversarial attacks have grown significantly, but the lack of practical evaluation methods has hindered progress. Evaluation can be defined as looking for defense models' lower bound of robustness given a budget number of iterations and a test dataset. A practical evaluation method should be convenient (i.e., parameter-free), efficient (i.e., fewer iterations) and reliable (i.e., approaching the lower bound of robustness). Towards this target, we propose a parameter-free Adaptive Auto Attack (A3) evaluation method which addresses the efficiency and reliability in a test-time-training fashion. Specifically, by observing that adversarial examples to a specific defense model follow some regularities in their starting points, we design an Adaptive Direction Initialization strategy to speed up the evaluation. Furthermore, to approach the lower bound of robustness under the budget number of iterations, we propose an online statistics-based discarding strategy that automatically identifies and abandons hard-to-attack images. Extensive experiments on nearly 50 widely-used defense models demonstrate the effectiveness of our A3.By consuming much fewer iterations than existing methods, i.e., 1/10 on average (10x speed up), we achieve lower robust accuracy in all cases. Notably, we won first place out of 1681 teams in CVPR 2021 White-box Adversarial Attacks on Defense Models competitions with this method. Code is available at: https://github.com/liuye6666/adaptive_auto_attack
-
In many different fields interactions between objects play a critical role in determining their behavior. Graph neural networks (GNNs) have emerged as a powerful tool for modeling interactions, although often at the cost of adding considerable complexity and latency. In this paper, we consider the problem of spatial interaction modeling in the context of predicting the motion of actors around autonomous vehicles, and investigate alternatives to GNNs. We revisit 2D convolutions and show that they can demonstrate comparable performance to graph networks in modeling spatial interactions with lower latency, thus providing an effective and efficient alternative in time-critical systems. Moreover, we propose a novel interaction loss to further improve the interaction modeling of the considered methods.
-
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. The temporal relation is complex in those datasets, including challenges like composite action, and co-occurring action. For detecting actions in those complex videos, efficiently capturing both short-term and long-term temporal information in the video is critical. To this end, we propose a novel ConvTransformer network for action detection. This network comprises three main components: (1) Temporal Encoder module extensively explores global and local temporal relations at multiple temporal resolutions. (2) Temporal Scale Mixer module effectively fuses the multi-scale features to have a unified feature representation. (3) Classification module is used to learn the instance center-relative position and predict the frame-level classification scores. The extensive experiments on multiple datasets, including Charades, TSU and MultiTHUMOS, confirm the effectiveness of our proposed method. Our network outperforms the state-of-the-art methods on all the three datasets.
-
Weakly supervised object detection (WSOD) has recently attracted much attention. However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD. To bridge the performance and technical gaps between WSOD and FSOD, this paper proposes a new framework, Salvage of Supervision (SoS), with the key idea being to harness every potentially useful supervisory signal in WSOD: the weak image-level labels, the pseudo-labels, and the power of semi-supervised object detection. This paper shows that each type of supervisory signal brings in notable improvements, outperforms existing WSOD methods (which mainly use only the weak labels) by large margins. The proposed SoS-WSOD method also have the ability to freely use modern FSOD techniques. SoS-WSOD achieves 64.4 mAP50 on VOC2007, 61.9 mAP50 on VOC2012 and 16.6 mAP50:95 on MS-COCO, and also has fast inference speed. Ablations and visualization further verify the effectiveness of SoS.
-
We present cross-view transformers, an efficient attention-based model for map-view semantic segmentation from multiple cameras. Our architecture implicitly learns a mapping from individual camera views into a canonical map-view representation using a camera-aware cross-view attention mechanism. Each camera uses positional embeddings that depend on its intrinsic and extrinsic calibration. These embeddings allow a transformer to learn the mapping across different views without ever explicitly modeling it geometrically. The architecture consists of a convolutional image encoder for each view and cross-view transformer layers to infer a map-view semantic segmentation. Our model is simple, easily parallelizable, and runs in real-time. The presented architecture performs at state-of-the-art on the nuScenes dataset, with 4x faster inference speeds. Code is available at https://github.com/bradyz/cross_view_transformers.
-
Generalized zero-shot learning (GZSL) aims to recognize samples whose categories may not have been seen at training. Recognizing unseen classes as seen ones or vice versa often leads to poor performance in GZSL. Therefore, distinguishing seen and unseen domains is naturally an effective yet challenging solution for GZSL. In this paper, we present a novel method which leverages both visual and semantic modalities to distinguish seen and unseen categories. Specifically, our method deploys two variational autoencoders to generate latent representations for visual and semantic modalities in a shared latent space, in which we align latent representations of both modalities by Wasserstein distance and reconstruct two modalities with the representations of each other. In order to learn a clearer boundary between seen and unseen classes, we propose a two-stage training strategy which takes advantage of seen and unseen semantic descriptions and searches a threshold to separate seen and unseen visual samples. At last, a seen expert and an unseen expert are used for final classification. Extensive experiments on five widely used benchmarks verify that the proposed method can significantly improve the results of GZSL. For instance, our method correctly recognizes more than 99% samples when separating domains and improves the final classification accuracy from 72.6% to 82.9% on AWA1.
-
Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. Large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning scenarios under noisy data streams are yet underexplored. We consider a more practical CL setup of an online learning from blurry data stream with corrupted noise, where existing CL methods struggle. To address the task, we first argue the importance of both diversity and purity of examples in the episodic memory of continual learning models. To balance diversity and purity in the episodic memory, we propose a novel strategy to manage and use the memory by a unified approach of label noise aware diverse sampling and robust learning with semi-supervised learning. Our empirical validations on four real-world or synthetic benchmark datasets (CIFAR10 and 100, mini-WebVision, and Food-101N) show that our method significantly outperforms prior arts in this realistic and challenging continual learning scenario.
-
Multi-task learning commonly encounters competition for resources among tasks, specifically when model capacity is limited. This challenge motivates models which allow control over the relative importance of tasks and total compute cost during inference time. In this work, we propose such a controllable multi-task network that dynamically adjusts its architecture and weights to match the desired task preference as well as the resource constraints. In contrast to the existing dynamic multi-task approaches that adjust only the weights within a fixed architecture, our approach affords the flexibility to dynamically control the total computational cost and match the user-preferred task importance better. We propose a disentangled training of two hypernetworks, by exploiting task affinity and a novel branching regularized loss, to take input preferences and accordingly predict tree-structured models with adapted weights. Experiments on three multi-task benchmarks, namely PASCAL-Context, NYU-v2, and CIFAR-100, show the efficacy of our approach. Project page is available at https://www.nec-labs.com/ mas/DYMU.
-
Deep neural network (DNN) suffers from catastrophic forgetting when learning incrementally, which greatly limits its applications. Although maintaining a handful of samples (called "exemplars") of each task could alleviate forgetting to some extent, existing methods are still limited by the small number of exemplars since these exemplars are too few to carry enough task-specific knowledge, and therefore the forgetting remains. To overcome this problem, we propose to "imagine" diverse counterparts of given exemplars referring to the abundant semantic-irrelevant information from unlabeled data. Specifically, we develop a learnable feature generator to diversify exemplars by adaptively generating diverse counterparts of exemplars based on semantic information from exemplars and semantically-irrelevant information from unlabeled data. We introduce semantic contrastive learning to enforce the generated samples to be semantic consistent with exemplars and perform semanticdecoupling contrastive learning to encourage diversity of generated samples. The diverse generated samples could effectively prevent DNN from forgetting when learning new tasks. Our method does not bring any extra inference cost and outperforms state-of-the-art methods on two benchmarks CIFAR-100 and ImageNet-Subset by a clear margin.
-
Several recent works seek to create lightweight deep networks for video object detection on mobiles. We observe that many existing detectors, previously deemed computationally costly for mobiles, intrinsically support adaptive inference, and offer a multi-branch object detection framework (MBODF). Here, an MBODF is referred to as a solution that has many execution branches and one can dynamically choose from among them at inference time to satisfy varying latency requirements (e.g. by varying resolution of an input frame). In this paper, we ask, and answer, the wide-ranging question across all MBODFs: How to expose the right set of execution branches and then how to schedule the optimal one at inference time? In addition, we uncover the importance of making a content-aware decision on which branch to run, as the optimal one is conditioned on the video content. Finally, we explore a content-aware scheduler, an Oracle one, and then a practical one, leveraging various lightweight feature extractors. Our evaluation shows that layered on Faster R-CNN-based MBODF, compared to 7 baselines, our SMARTADAPT achieves a higher Pareto optimal curve in the accuracy-vs-latency space for the ILSVRC VID dataset.
-
Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. However, fine-tuning the entire parameter set of pre-trained models becomes impractical since the model size is growing rapidly. Hence, in this paper, we introduce adapter-based parameter-efficient transfer learning techniques to V&L models such as VL-BART and VL-T5. We evaluate our methods in a unified multi-task setup on both image-text and video-text benchmarks. For the image-text tasks, we use four diverse V&L datasets: VQAv2, GQA, NLVR2, and MSCOCO image captioning. For video-text tasks, we use TVQA, How2QA, TVC, and YC2C. With careful training and thorough experiments, we benchmark three popular adapter-based methods (Adapter, Hyperformer, Compacter) against the standard full fine-tuning and the recently proposed prompt-tuning approach. We also enhance the efficiency and performance of adapters by sharing their weights to attain knowledge across tasks. Our results demonstrate that training the adapter with the weight-sharing technique (4.18% of total parameters for image-text tasks and 3.39% for video-text tasks) can match the performance of fine-tuning the entire model. Lastly, we present a comprehensive analysis including the combination of adapter and task-specific prompts and the impact of V&L pre-training on adapters.
-
We propose a principled and practical method for out-of-distribution (OoD) detection with deep hybrid models (DHMs), which model the joint density p(x,y) of features and labels with a single forward pass. By factorizing the joint density p(x,y) into three sources of uncertainty, we show that our approach has the ability to identify samples semantically different from the training data. To ensure computational scalability, we add a weight normalization step during training, which enables us to plug in state-of-the-art (SoTA) deep neural network (DNN) architectures for approximately modeling and inferring expressive probability distributions. Our method provides an efficient, general, and flexible framework for predictive uncertainty estimation with promising results and theoretical support. To our knowledge, this is the first work to reach 100% in OoD detection tasks on both vision and language datasets, especially on notably difficult dataset pairs such as CIFAR-10 vs. SVHN and CIFAR-100 vs. CIFAR-10. This work is a step towards enabling DNNs in real-world deployment for safety-critical applications.
-
We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream. Specifically, we propose a motion vector-based warping method for propagating segmentation masks from keyframes to other frames in a bi-directional and multi-hop manner. Additionally, we introduce a residual-based correction module that can fix wrongly propagated segmentation masks from noisy or erroneous motion vectors. Our approach is flexible and can be added on top of several existing video object segmentation algorithms. We achieved highly competitive results on DAVIS17 and YouTube-VOS on various base models with substantial speed-ups of up to 3.5X with minor drops in accuracy.
-
Source-free domain adaptation (SFDA) newly emerges to transfer the relevant knowledge of a well-trained source model to an unlabeled target domain, which is critical in various privacy-preserving scenarios. Most existing methods focus on learning the domain-invariant representations depending solely on the target data, leading to the obtained representations are target-specific. In this way, they cannot fully address the distribution shift problem across domains. In contrast, we provide a fascinating insight: rather than attempting to learn domain-invariant representations, it is better to explore the domain-invariant parameters of the source model. The motivation behind this insight is clear: the domain-invariant representations are dominated by only partial parameters of an available deep source model. We devise the Domain-Invariant Parameter Exploring (DIPE) approach to capture such domain-invariant parameters in the source model to generate domain-invariant representations. A distinguishing method is developed correspondingly for two types of parameters, i.e., domain-invariant and domain-specific parameters, as well as an effective update strategy based on the clustering correction technique and a target hypothesis is proposed. Extensive experiments verify that DIPE successfully exceeds the current state-of-the-art models on many domain adaptation datasets.
-
We present a massively parallel Lagrange decomposition method for solving 0--1 integer linear programs occurring in structured prediction. We propose a new iterative update scheme for solving the Lagrangean dual and a perturbation technique for decoding primal solutions. For representing subproblems we follow Lange et al. (2021) and use binary decision diagrams (BDDs). Our primal and dual algorithms require little synchronization between subproblems and optimization over BDDs needs only elementary operations without complicated control flow. This allows us to exploit the parallelism offered by GPUs for all components of our method. We present experimental results on combinatorial problems from MAP inference for Markov Random Fields, quadratic assignment and cell tracking for developmental biology. Our highly parallel GPU implementation improves upon the running times of the algorithms from Lange et al. (2021) by up to an order of magnitude. In particular, we come close to or outperform some state-of-the-art specialized heuristics while being problem agnostic. Our implementation is available at https://github.com/LPMP/BDD.
-
Dynamic model pruning is a recent direction that allows for the inference of a different sub-network for each input sample during deployment. However, current dynamic methods rely on learning a continuous channel gating through regularization by inducing sparsity loss. This formulation introduces complexity in balancing different losses (e.g task loss, regularization loss). In addition, regularization based methods lack transparent tradeoff hyperparameter selection to realize computational budget. Our contribution is two-fold: 1) decoupled task and pruning training. 2) Simple hyperparameter selection that enables FLOPs reduction estimation before training. Inspired by the Hebbian theory in Neuroscience: "neurons that fire together wire together", we propose to predict a mask to process k filters in a layer based on the activation of its previous layer. We pose the problem as a self-supervised binary classification problem. Each mask predictor module is trained to predict if the log-likelihood for each filter in the current layer belongs to the top-k activated filters. The value k is dynamically estimated for each input based on a novel criterion using the mass of heatmaps. We show experiments on several neural architectures, such as VGG, ResNet and MobileNet on CIFAR and ImageNet datasets. On CIFAR, we reach similar accuracy to SOTA methods with 15% and 24% higher FLOPs reduction. Similarly in ImageNet, we achieve lower drop in accuracy with up to 13% improvement in FLOPs reduction.
-
Deep learning-based image salient object detection (SOD) heavily relies on large-scale training data with pixel-wise labeling. High-quality labels involve intensive labor and are expensive to acquire. In this paper, we propose a novel multi-source uncertainty mining method to facilitate unsupervised deep learning from multiple noisy labels generated by traditional handcrafted SOD methods. We design an Uncertainty Mining Network (UMNet) which consists of multiple Merge-and-Split (MS) modules to recursively analyze the commonality and difference among multiple noisy labels and infer pixel-wise uncertainty map for each label. Meanwhile, we model the noisy labels using Gibbs distribution and propose a weighted uncertainty loss to jointly train the UMNet with the SOD network. As a consequence, our UMNet can adaptively select reliable labels for SOD network learning. Extensive experiments on benchmark datasets demonstrate that our method not only outperforms existing unsupervised methods, but also is on par with fully-supervised state-of-the-art models.
-
Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based methods for keypoint detection rely on standard translation-equivariant CNNs but often fail to detect reliable keypoints against geometric variations. To learn to detect robust oriented keypoints, we introduce a self-supervised learning framework using rotation-equivariant CNNs. We propose a dense orientation alignment loss by an image pair generated by synthetic transformations for training a histogram-based orientation map. Our method outperforms the previous methods on an image matching benchmark and a camera pose estimation benchmark.
-
Remarkable achievements have been attained with Generative Adversarial Networks (GANs) in image-to-image translation. However, due to a tremendous amount of parameters, state-of-the-art GANs usually suffer from low efficiency and bulky memory usage. To tackle this challenge, firstly, this paper investigates GANs performance from a frequency perspective. The results show that GANs, especially small GANs lack the ability to generate high-quality high frequency information. To address this problem, we propose a novel knowledge distillation method referred to as wavelet knowledge distillation. Instead of directly distilling the generated images of teachers, wavelet knowledge distillation first decomposes the images into different frequency bands with discrete wavelet transformation and then only distills the high frequency bands. As a result, the student GAN can pay more attention to its learning on high frequency bands. Experiments demonstrate that our method leads to 7.08X compression and 6.80X acceleration on CycleGAN with almost no performance drop. Additionally, we have studied the relation between discriminators and generators which shows that the compression of discriminators can promote the performance of compressed generators.
-
Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object detection, the features of the teacher and student vary greatly in different areas, especially in the foreground and background. If we distill them equally, the uneven differences between feature maps will negatively affect the distillation. Thus, we propose Focal and Global Distillation (FGD). Focal distillation separates the foreground and background, forcing the student to focus on the teacher's critical pixels and channels. Global distillation rebuilds the relation between different pixels and transfers it from teachers to students, compensating for missing global information in focal distillation. As our method only needs to calculate the loss on the feature map, FGD can be applied to various detectors. We experiment on various detectors with different backbones and the results show that the student detector achieves excellent mAP improvement. For example, ResNet-50 based RetinaNet, Faster RCNN, RepPoints and Mask RCNN with our distillation method achieve 40.7%, 42.0%, 42.0% and 42.1% mAP on COCO2017, which are 3.3, 3.6, 3.4 and 2.9 higher than the baseline, respectively. Our codes are available at https://github.com/yzd-v/FGD.
-
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task identity at test time to retrieve learned knowledge and address forgetting, while this work presents a new paradigm for continual learning that aims to train a more succinct memory system without accessing task identity at test time. Our method learns to dynamically prompt (L2P) a pre-trained model to learn tasks sequentially under different task transitions. In our proposed framework, prompts are small learnable parameters, which are maintained in a memory space. The objective is to optimize prompts to instruct the model prediction and explicitly manage task-invariant and task-specific knowledge while maintaining model plasticity. We conduct comprehensive experiments under popular image classification benchmarks with different challenging continual learning settings, where L2P consistently outperforms prior state-of-the-art methods. Surprisingly, L2P achieves competitive results against rehearsal-based methods even without a rehearsal buffer and is directly applicable to challenging task-agnostic continual learning. Source code is available at https://github.com/google-research/l2p.
-
Videos from edited media like movies are a useful, yet under-explored source of information, with rich variety of appearance and interactions between humans depicted over a large temporal context. However, the richness of data comes at the expense of fundamental challenges such as abrupt shot changes and close up shots of actors with heavy truncation, which limits the applicability of existing 3D human understanding methods. In this paper, we address these limitations with the insight that while shot changes of the same scene incur a discontinuity between frames, the 3D structure of the scene still changes smoothly. This allows us to handle frames before and after the shot change as multi-view signal that provide strong cues to recover the 3D state of the actors. We propose a multi-shot optimization framework that realizes this insight, leading to improved 3D reconstruction and mining of sequences with pseudo-ground truth 3D human mesh. We treat this data as valuable supervision for models that enable human mesh recovery from movies; both from single image and from video, where we propose a transformer-based temporal encoder that can naturally handle missing observations due to shot changes in the input frames. We demonstrate the importance of our insight and proposed models through extensive experiments. The tools we develop open the door to processing and analyzing in 3D content from a large library of edited media, which could be helpful for many downstream applications. Code, models and data are available at: https://geopavlakos.github.io/multishot/
-
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. It is thus imperative to devise effective attack algorithms to identify the deficiencies of DNNs beforehand in security-sensitive applications. To efficiently tackle the black-box setting where the target model's particulars are unknown, feature-level transfer-based attacks propose to contaminate the intermediate feature outputs of local models, and then directly employ the crafted adversarial samples to attack the target model. Due to the transferability of features, feature-level attacks have shown promise in synthesizing more transferable adversarial samples. However, existing feature-level attacks generally employ inaccurate neuron importance estimations, which deteriorates their transferability. To overcome such pitfalls, in this paper, we propose the Neuron Attribution-based Attack (NAA), which conducts feature-level attacks with more accurate neuron importance estimations. Specifically, we first completely attribute a model's output to each neuron in a middle layer. We then derive an approximation scheme of neuron attribution to tremendously reduce the computation overhead. Finally, we weight neurons based on their attribution results and launch feature-level attacks. Extensive experiments confirm the superiority of our approach to the state-of-the-art benchmarks.
-
Backdoor attacks aim to cause misclassification of a subject model by stamping a trigger to inputs. Backdoors could be injected through malicious training and naturally exist. Deriving backdoor trigger for a subject model is critical to both attack and defense. A popular trigger inversion method is by optimization. Existing methods are based on finding a smallest trigger that can uniformly flip a set of input samples by minimizing a mask. The mask defines the set of pixels that ought to be perturbed. We develop a new optimization method that directly minimizes individual pixel changes, without using a mask. Our experiments show that compared to existing methods, the new one can generate triggers that require a smaller number of input pixels to be perturbed, have a higher attack success rate, and are more robust. They are hence more desirable when used in real-world attacks and more effective when used in defense. Our method is also more cost-effective.
-
Segmenting an image into its parts is a frequent preprocess for high-level vision tasks such as image editing. However, annotating masks for supervised training is expensive. Weakly-supervised and unsupervised methods exist, but they depend on the comparison of pairs of images, such as from multi-views, frames of videos, and image augmentation, which limits their applicability. To address this, we propose a GAN-based approach that generates images conditioned on latent masks, thereby alleviating full or weak annotations required in previous approaches. We show that such mask-conditioned image generation can be learned faithfully when conditioning the masks in a hierarchical manner on latent keypoints that define the position of parts explicitly. Without requiring supervision of masks or points, this strategy increases robustness to viewpoint and object positions changes. It also lets us generate image-mask pairs for training a segmentation network, which outperforms the state-of-the-art unsupervised segmentation methods on established benchmarks.
-
The ultimate goal of semi-supervised object detection (SSOD) is to facilitate the utilization and deployment of detectors in actual applications with the help of a large amount of unlabeled data. Although a few works have proposed various self-training-based methods or consistency-regularization-based methods, they all target anchor-based detectors, while ignoring the dependency on anchor-free detectors of the actual industrial deployment. To this end, in this paper, we intend to bridge the gap on anchor-free SSOD algorithm by proposing a DenSe Learning (DSL) based algorithm for SSOD. It is mainly achieved by introducing several novel techniques, including (1) Adaptive Ignoring strategy with MetaNet for assigning multi-level and accurate dense pixel-wise pseudo-labels, (2) Aggregated Teacher for producing stable and precise pseudo-labels, and (3) uncertainty consistency regularization among scales and shuffled patches for improving the generalization of the detector. In order to verify the effectiveness of our proposed method, extensive experiments have been conducted over the popular datasets MS-COCO [??] and PASCAL-VOC [??], achieving state-of-the-art performances. Codes will be available at \textcolor[rgb] 1,0,0 xxxxxxxxx .
-
This paper studies the problem of fixing malfunctional 3D objects. While previous works focus on building passive perception models to learn the functionality from static 3D objects, we argue that functionality is reckoned with respect to the physical interactions between the object and the user. Given a malfunctional object, humans can perform mental simulations to reason about its functionality and figure out how to fix it. Inspired by this, we propose FixIt, a dataset that contains around 5k poorly-designed 3D physical objects paired with choices to fix them. To mimic humans' mental simulation process, we present FixNet, a novel framework that seamlessly incorporates perception and physical dynamics. Specifically, FixNet consists of a perception module to extract the structured representation from the 3D point cloud, a physical dynamics prediction module to simulate the results of interactions on 3D objects, and a functionality prediction module to evaluate the functionality and choose the correct fix. Experimental results show that our framework outperforms baseline models by a large margin, and can generalize well to objects with similar interaction types. We will release our code and dataset.
-
In the biological visual pathway, especially the retina, neurons are tiled along spatial dimensions with the electrical coupling as their local association, while in a convolution layer, kernels are placed along the channel dimension singly. We propose Convolution of Convolution, associating kernels in a layer and letting them collaborate spatially. With this method, a layer can provide feature maps with extra transformations and learn its kernels together instead of isolatedly. It is only used during training, bringing in negligible extra costs; and can be re-parameterized to common convolution before testing, boosting performance gratuitously in tasks like classification, detection and segmentation. Our method works even better when large receptive fields are demanded. The code is available on site: https://github.com/Genera1Z/ConvolutionOfConvolution.
-
Generating controllable videos conforming to user intentions is an appealing yet challenging topic in computer vision. To enable maneuverable control in line with user intentions, a novel video generation task, named Text-Image-to-Video generation (TI2V), is proposed. With both controllable appearance and motion, TI2V aims at generating videos from a static image and a text description. The key challenges of TI2V task lie both in aligning appearance and motion from different modalities, and in handling uncertainty in text descriptions. To address these challenges, we propose a Motion Anchor-based video GEnerator (MAGE) with an innovative motion anchor (MA) structure to store appearance-motion aligned representation. To model the uncertainty and increase the diversity, it further allows the injection of explicit condition and implicit randomness. Through three-dimensional axial transformers, MA is interacted with given image to generate next frames recursively with satisfying controllability and diversity. Accompanying the new task, we build two new video-text paired datasets based on MNIST and CATER for evaluation. Experiments conducted on these datasets verify the effectiveness of MAGE and show appealing potentials of TI2V task. Code and datasets are released at https://github.com/Youncy-Hu/MAGE.
-
Long-tail object detection suffers from poor performance on tail categories. We reveal that the real culprit lies in the extremely imbalanced distribution of the classifier's weight norm. For conventional softmax cross-entropy loss, such imbalanced weight norm distribution yields ill conditioned decision boundary for categories which have small weight norms. To get rid of this situation, we choose to maximize the cosine similarity between the learned feature and the weight vector of target category rather than the inner-product of them. The decision boundary between any two categories is the angular bisector of their weight vectors. Whereas, the absolutely equal decision boundary is suboptimal because it reduces the model's sensitivity to various categories. Intuitively, categories with rich data diversity should occupy a larger area in the classification space while categories with limited data diversity should occupy a slightly small space. Hence, we devise a Category-Aware Angular Margin Loss (C2AM Loss) to introduce an adaptive angular margin between any two categories. Specifically, the margin between two categories is proportional to the ratio of their classifiers' weight norms. As a result, the decision boundary is slightly pushed towards the category which has a smaller weight norm. We conduct comprehensive experiments on LVIS dataset. C2AM Loss brings 4.9 5.2 AP improvements on different detectors and backbones compared with baseline.
-
In this paper, we propose Neural Points, a novel point cloud representation and apply it to the arbitrary-factored upsampling task. Different from traditional point cloud representation where each point only represents a position or a local plane in the 3D space, each point in Neural Points represents a local continuous geometric shape via neural fields. Therefore, Neural Points contain more shape information and thus have a stronger representation ability. Neural Points is trained with surface containing rich geometric details, such that the trained model has enough expression ability for various shapes. Specifically, we extract deep local features on the points and construct neural fields through the local isomorphism between the 2D parametric domain and the 3D local patch. In the final, local neural fields are integrated together to form the global surface. Experimental results show that Neural Points has powerful representation ability and demonstrate excellent robustness and generalization ability. With Neural Points, we can resample point cloud with arbitrary resolutions, and it outperforms the state-of-the-art point cloud upsampling methods. Code is available at https://github.com/WanquanF/NeuralPoints.
-
Recent progress on neural architecture search (NAS) has demonstrated exciting results on automating deep network architecture designs. In order to overcome the unaffordable complexity of training each candidate architecture from scratch, the state-of-the-art one-shot NAS approaches adopt a weight-sharing strategy to improve training efficiency. Although the computational cost is greatly reduced, such one-shot process introduces a severe weight coupling problem that largely degrades the evaluation accuracy of each candidate. The existing approaches often address the problem by shrinking the search space, model distillation, or few-shot training. Instead, in this paper, we propose a novel distribution consistent one-shot neural architecture search algorithm. We first theoretically investigate how the weight coupling problem affects the network searching performance from a parameter distribution perspective, and then propose a novel supernet training strategy with a Distribution Consistent Constraint that can provide a good measurement for the extent to which two architectures can share weights. Our strategy optimizes the supernet through iteratively inferring network weights and corresponding local sharing states. Such joint optimization of supernet's weights and topologies can diminish the discrepancy between the weights inherited from the supernet and the ones that are trained with a stand-alone model. As a result, it enables a more accurate model evaluation phase and leads to a better searching performance. We conduct extensive experiments on benchmark datasets with multiple searching spaces. The resulting architecture achieves superior performance over the current state-of-the-art NAS algorithms with comparable search costs, which demonstrates the efficacy of our approach.
-
Learning generic joint representations for video and text by a supervised method requires a prohibitively substantial amount of manually annotated video datasets. As a practical alternative, a large-scale but uncurated and narrated video dataset, HowTo100M, has recently been introduced. But it is still challenging to learn joint embeddings of video and text in a self-supervised manner, due to its ambiguity and non-sequential alignment. In this paper, we propose a novel multi-modal self-supervised framework Video-Text Temporally Weak Alignment-based Contrastive Learning (VT-TWINS) to capture significant information from noisy and weakly correlated data using a variant of Dynamic Time Warping (DTW). We observe that the standard DTW inherently cannot handle weakly correlated data and only considers the globally optimal alignment path. To address these problems, we develop a differentiable DTW which also reflects local information with weak temporal alignment. Moreover, our proposed model applies a contrastive learning scheme to learn feature representations on weakly correlated data. Our extensive experiments demonstrate that VT-TWINS attains significant improvements in multi-modal representation learning and outperforms various challenging downstream tasks. Code is available at https://github.com/mlvlab/VT-TWINS.
-
The saliency ranking task is recently proposed to study the visual behavior that humans would typically shift their attention over different objects of a scene based on their degrees of saliency. Existing approaches focus on learning either object-object or object-scene relations. Such a strategy follows the idea of object-based attention in Psychology, but it tends to favor those objects with strong semantics (e.g., humans), resulting in unrealistic saliency ranking. We observe that spatial attention works concurrently with object-based attention in the human visual recognition system. During the recognition process, the human spatial attention mechanism would move, engage, and disengage from region to region (i.e., context to context). This inspires us to model the region-level interactions, in addition to the object-level reasoning, for saliency ranking. To this end, we propose a novel bi-directional method to unify spatial attention and object-based attention for saliency ranking. Our model includes two novel modules: (1) a selective object saliency (SOS) module that models object-based attention via inferring the semantic representation of the salient object, and (2) an object-context-object relation (OCOR) module that allocates saliency ranks to objects by jointly modeling the object-context and context-object interactions of the salient objects. Extensive experiments show that our approach outperforms existing state-of-the-art methods. Code and pretrained model are available at https://github.com/GrassBro/OCOR.
-
Instance segmentation is a fundamental vision task that aims to recognize and segment each object in an image. However, it requires costly annotations such as bounding boxes and segmentation masks for learning. In this work, we propose a fully unsupervised learning method that learns class-agnostic instance segmentation without any annotations. We present FreeSOLO, a self-supervised instance segmentation framework built on top of the simple instance segmentation method SOLO. Our method also presents a novel localization-aware pre-training framework, where objects can be discovered from complicated scenes in an unsupervised manner. FreeSOLO achieves 9.8% AP50 on the challenging COCO dataset, which even outperforms several segmentation proposal methods that use manual annotations. For the first time, we demonstrate unsupervised class-agnostic instance segmentation successfully. FreeSOLO's box localization significantly outperforms state-of-the-art unsupervised object detection/discovery methods, with about 100% relative improvements in COCO AP. FreeSOLO further demonstrates superiority as a strong pre-training method, outperforming state-of-the-art self-supervised pre-training methods by +9.8% AP when fine-tuning instance segmentation with only 5% COCO masks.
-
Today's state of the art visual navigation agents typically consist of large deep learning architectures trained end to end. Such models offer little to no interpretability about the skills learned by the agent or the actions taken by it in response to its environment. While past works have explored interpreting deep learning models, little attention has been devoted to interpreting embodied AI systems, which often involve reasoning about the structure of the environment, target characteristics and the outcome of one's actions. In this paper, we introduce the Interpretability System for Embodied agEnts (iSEE) for Point Goal (PointNav) and Object Goal (ObjectNav) navigation models. We use iSEE to probe the dynamic representations produced by PointNav and ObjectNav agents for the presence of information about their agents location and actions, as well as the environment. We demonstrate interesting insights about navigation agents using iSEE, including the ability to encode reachable locations (to avoid obstacles), visibility of the target, progress from the initial spawn location as well as the dramatic effect on the behaviors of agents when we mask out critical individual neurons.
-
We propose Path-CNN, a method for the segmentation of centerlines of tubular structures by embedding convolutional neural networks (CNNs) into the progressive minimal path method. Minimal path methods are widely used for topology-aware centerline segmentation, but usually these methods rely on weak, hand-tuned image features. In contrast, CNNs use strong image features which are learned automatically from images. But CNNs usually do not take the topology of the results into account, and often require a large amount of annotations for training. We integrate CNNs into the minimal path method, so that both techniques benefit from each other: CNNs employ learned image features to improve the determination of minimal paths, while the minimal path method ensures the correct topology of the segmented centerlines, provides strong geometric priors to increase the performance of CNNs, and reduces the amount of annotations for the training of CNNs significantly. Our method has lower hardware requirements than many recent methods. Qualitative and quantitative comparison with other methods shows that Path-CNN achieves better performance, especially when dealing with tubular structures with complex shapes in challenging environments.
-
Robust visual recognition under adverse weather conditions is of great importance in real-world applications. In this context, we propose a new method for learning semantic segmentation models robust against fog. Its key idea is to consider the fog condition of an image as its style and close the gap between images with different fog conditions in neural style spaces of a segmentation model. In particular, since the neural style of an image is in general affected by other factors as well as fog, we introduce a fog-pass filter module that learns to extract a fog-relevant factor from the style. Optimizing the fog-pass filter and the segmentation model alternately gradually closes the style gap between different fog conditions and allows to learn fog-invariant features in consequence. Our method substantially outperforms previous work on three real foggy image datasets. Moreover, it improves performance on both foggy and clear weather images, while existing methods often degrade performance on clear scenes.
-
3D face reconstruction from a single image is a task that has garnered increased interest in the Computer Vision community, especially due to its broad use in a number of applications such as realistic 3D avatar creation, pose invariant face recognition and face hallucination. Since the introduction of the 3D Morphable Model in the late 90's, we witnessed an explosion of research aiming at particularly tackling this task. Nevertheless, despite the increasing level of detail in the 3D face reconstructions from single images mainly attributed to deep learning advances, finer and highly deformable components of the face such as the tongue are still absent from all 3D face models in the literature, although being very important for the realness of the 3D avatar representations. In this work we present the first, to the best of our knowledge, end-to-end trainable pipeline that accurately reconstructs the 3D face together with the tongue. Moreover, we make this pipeline robust in "in-the-wild" images by introducing a novel GAN method tailored for 3D tongue surface generation. Finally, we make publicly available to the community the first diverse tongue dataset, consisting of 1,800 raw scans of 700 individuals varying in gender, age, and ethnicity backgrounds. As we demonstrate in an extensive series of quantitative as well as qualitative experiments, our model proves to be robust and realistically captures the 3D tongue structure, even in adverse "in-the-wild" conditions.
-
Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the min-max adversarial training, but instead learn from a weak adversary inefficiently. Conversely, we propose Hardness Manipulation to efficiently perturb the training triplet till a specified level of hardness for adversarial training, according to a harder benign triplet or a pseudo-hardness function. It is flexible since regular training and min-max adversarial training are its boundary cases. Besides, Gradual Adversary, a family of pseudo-hardness functions is proposed to gradually increase the specified hardness level during training for a better balance between performance and robustness. Additionally, an Intra-Class Structure loss term among benign and adversarial examples further improves model robustness and efficiency. Comprehensive experimental results suggest that the proposed method, although simple in its form, overwhelmingly outperforms the state-of-the-art defenses in terms of robustness, training efficiency, as well as performance on benign examples.
-
Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale low-resolution representations, which makes dense prediction tasks such as semantic segmentation challenging for ViTs. Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs. We balance the model performance and efficiency of HRViT by various branch-block co-optimization techniques. Specifically, we explore heterogeneous branch designs, reduce the redundancy in linear layers, and augment the attention block with enhanced expressiveness. Those approaches enabled \ours to push the Pareto frontier of performance and efficiency on semantic segmentation to a new level, as our evaluation results on ADE20K and Cityscapes show. HRViT achieves 50.20% mIoU on ADE20K and 83.16% mIoU on Cityscapes for semantic segmentation tasks, surpassing state-of-the-art MiT and CSWin backbones with an average of +1.78 mIoU improvement, 28% parameter reduction, and 21% FLOPs reduction, demonstrating the potential of HRViT as a strong vision backbone for semantic segmentation.
-
Recent multi-modal detectors based on transformers and modality encoders have successfully achieved impressive results on end-to-end visual object detection conditioned on a raw text query. However, they require a large model size and an enormous amount of computations to achieve high performance, which makes it difficult to deploy mobile applications that are limited by tight hardware resources. In this paper, we present a Lightweight modulated detector, Lite-MDETR, to facilitate efficient end-to-end multi-modal understanding on mobile devices. The key primitive is that Dictionary-Lookup-Transformormations (DLT) is proposed to replace Linear Transformation (LT) in multi-modal detectors where each weight in Linear Transformation (LT) is approximately factorized into a smaller dictionary, index, and coefficient. This way, the enormous linear projection with weights is converted into lite linear projection with dictionaries, a few lookups and scalings with indices and coefficients. DLT can be directly applied to pre-trained detectors, removing the need to perform expensive training from scratch. To tackle the challenging training of DLT due to the non-differentiable index, we convert the index and coefficient into a sparse matrix, train this sparse matrix during the fine-tuning phase, and recover it back to index and coefficient during the inference phase. Extensive experiments on several tasks such as phrase grounding, referring expression comprehension and segmentation show that our Lite-MDETR achieves similar detection accuracy to the prior multi-modal detectors with ~ 4.1xmodel size reduction.
-
Recent advances show that Generative Adversarial Networks (GANs) can synthesize images with smooth variations along semantically meaningful latent directions, such as pose, expression, layout, etc. While this indicates that GANs implicitly learn pixel-level correspondences across images, few studies explored how to extract them explicitly. In this work, we introduce Coordinate GAN (CoordGAN), a structure-texture disentangled GAN that learns a dense correspondence map for each generated image. We represent the correspondence maps of different images as warped coordinate frames transformed from a canonical coordinate frame, i.e., the correspondence map, which describes the structure (e.g., the shape of a face), is controlled via a transformation. Hence, finding correspondences boils down to locating the same coordinate in different correspondence maps. In CoordGAN, we sample a transformation to represent the structure of a synthesized instance, while an independent texture branch is responsible for rendering appearance details orthogonal to the structure. Our approach can also extract dense correspondence maps for real images by adding an encoder on top of the generator. We quantitatively demonstrate the quality of the learned dense correspondences through segmentation mask transfer on multiple datasets. We also show that the proposed generator achieves better structure and texture disentanglement compared to existing approaches.
-
This paper proposes a simple transfer learning baseline for sign language translation. Existing sign language datasets (e.g. PHOENIX-2014T, CSL-Daily) contain only about 10K-20K pairs of sign videos, gloss annotations and texts, which are an order of magnitude smaller than typical parallel data for training spoken language translation models. Data is thus a bottleneck for training effective sign language translation models. To mitigate this problem, we propose to progressively pretrain the model from general-domain datasets that include a large amount of external supervision to within-domain datasets. Concretely, we pretrain the sign-to-gloss visual network on the general domain of human actions and the within-domain of a sign-to-gloss dataset, and pretrain the gloss-to-text translation network on the general domain of a multilingual corpus and the within-domain of a gloss-to-text corpus. The joint model is fine-tuned with an additional module named the visual-language mapper that connects the two networks. This simple baseline surpasses the previous state-of-the-art results on two sign language translation benchmarks, demonstrating the effectiveness of transfer learning. With its simplicity and strong performance, this approach can serve as a solid baseline for future research.
-
Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination. The main challenge resides in clustering since prevalent clustering methods (e.g., k-means) have to run in a batch mode. Besides, there can be a trivial solution consisting of a dominating cluster. To address these challenges, we first investigate the objective of clustering-based representation learning. Based on this, we propose a novel clustering-based pretext task with online Constrained K-means (CoKe). Compared with the balanced clustering that each cluster has exactly the same size, we only constrain the minimal size of each cluster to flexibly capture the inherent data structure. More importantly, our online assignment method has a theoretical guarantee to approach the global optimum. By decoupling clustering and discrimination, CoKe can achieve competitive performance when optimizing with only a single view from each instance. Extensive experiments on ImageNet and other benchmark data sets verify both the efficacy and efficiency of our proposal.
-
We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud. Combining differentiable volume rendering with learned implicit density representations has made it possible to synthesize photo-realistic images for novel views of small scenes. As neural volumetric rendering methods require dense sampling of the underlying functional scene representation, at hundreds of samples along a ray cast through the volume, they are fundamentally limited to small scenes with the same objects projected to hundreds of training views. Promoting sparse point clouds to neural implicit light fields allows us to represent large scenes effectively with only a single radiance evaluation per ray. These point light fields are as a function of the ray direction, and local point feature neighborhood, allowing us to interpolate the light field conditioned training images without dense object coverage and parallax. We assess the proposed method for novel view synthesis on large driving scenarios, where we synthesize realistic unseen views that existing implicit approaches fail to represent. We validate that Neural Point Light Fields make it possible to predict videos along unseen trajectories previously only feasible to generate by explicitly modeling the scene.
-
Vehicle trajectory prediction is nowadays a fundamental pillar of self-driving cars. Both the industry and research communities have acknowledged the need for such a pillar by providing public benchmarks. While state-of-the-art methods are impressive, i.e., they have no off-road prediction, their generalization to cities outside of the benchmark remains unexplored. In this work, we show that those methods do not generalize to new scenes. We present a novel method that automatically generates realistic scenes causing state-of-the-art models to go off-road. We frame the problem through the lens of adversarial scene generation. The method is a simple yet effective generative model based on atomic scene generation functions along with physical constraints. Our experiments show that more than 60% of existing scenes from the current benchmarks can be modified in a way to make prediction methods fail (i.e., predicting off-road). We further show that the generated scenes (i) are realistic since they do exist in the real world, and (ii) can be used to make existing models more robust, yielding 30-40% reductions in the off-road rate. The code is available online: https://s-attack.github.io/
-
In this paper, we propose a new deep learning-based method for estimating room layout given a pair of 360 panoramas. Our system, called Position-aware Stereo Merging Network or PSMNet, is an end-to-end joint layout-pose estimator. PSMNet consists of a Stereo Pano Pose (SP^2) transformer and a novel Cross-Perspective Projection (CP^2) layer. The stereo-view SP^2 transformer is used to implicitly infer correspondences between views, and can handle noisy poses. The pose-aware CP^2layer is designed to render features from the adjacent view to the anchor (reference) view, in order to perform view fusion and estimate the visible layout. Our experiments and analysis validate our method, which significantly outperforms the state-of-the-art layout estimators, especially for large and complex room spaces.
-
Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to assist 3D detection, but suffer from the additional computational burden and achieve limited performance caused by inaccurate depth priors. To alleviate this, we propose MonoDTR, a novel end-to-end depth-aware transformer network for monocular 3D object detection. It mainly consists of two components: (1) the Depth-Aware Feature Enhancement (DFE) module that implicitly learns depth-aware features with auxiliary supervision without requiring extra computation, and (2) the Depth-Aware Transformer (DTR) module that globally integrates context- and depth-aware features. Moreover, different from conventional pixel-wise positional encodings, we introduce a novel depth positional encoding (DPE) to inject depth positional hints into transformers. Our proposed depth-aware modules can be easily plugged into existing image-only monocular 3D object detectors to improve the performance. Extensive experiments on the KITTI dataset demonstrate that our approach outperforms previous state-of-the-art monocular-based methods and achieves real-time detection. Code is available at https://github.com/kuanchihhuang/MonoDTR.
-
We introduce a novel formulation for guided super-resolution. Its core is a differentiable optimisation layer that operates on a learned affinity graph. The learned graph potentials make it possible to leverage rich contextual information from the guide image, while the explicit graph optimisation within the architecture guarantees rigorous fidelity of the high-resolution target to the low-resolution source. With the decision to employ the source as a constraint rather than only as an input to the prediction, our method differs from state-of-the-art deep architectures for guided super-resolution, which produce targets that, when downsampled, will only approximately reproduce the source. This is not only theoretically appealing, but also produces crisper, more natural-looking images. A key property of our method is that, although the graph connectivity is restricted to the pixel lattice, the associated edge potentials are learned with a deep feature extractor and can encode rich context information over large receptive fields. By taking advantage of the sparse graph connectivity, it becomes possible to propagate gradients through the optimisation layer and learn the edge potentials from data. We extensively evaluate our method on several datasets, and consistently outperform recent baselines in terms of quantitative reconstruction errors, while also delivering visually sharper outputs. Moreover, we demonstrate that our method generalises particularly well to new datasets not seen during training.
-
In this paper, we introduce a new dataset, named InstaOrder, that can be used to understand the spatial relationships of instances in a 3D space. The dataset consists of 2.9M annotations of geometric orderings for class-labeled instances in 101K natural scenes. The scenes were annotated by 3,659 crowd-workers regarding (1) occlusion order that identifies occluder/occludee and (2) depth order that describes ordinal relations that consider relative distance from the camera. The dataset provides joint annotation of two kinds of orderings for the same instances, and we discover that the occlusion order and depth order are complementary. We also introduce a geometric order prediction network called InstaOrderNet, which is superior to state-of-the-art approaches. Moreover, we propose a dense depth prediction network called InstaDepthNet that uses auxiliary geometric order loss to boost the accuracy of the state-of-the-art depth prediction approach, MiDaS [54].
-
Human actions often induce changes of object states such as "cutting an apple", "cleaning shoes" or "pouring coffee". In this paper, we seek to temporally localize object states (e.g. "empty" and "full" cup) together with the corresponding state-modifying actions ("pouring coffee") in long uncurated videos with minimal supervision. The contributions of this work are threefold. First, we develop a self-supervised model for jointly learning state-modifying actions together with the corresponding object states from an uncurated set of videos from the Internet. The model is self-supervised by the causal ordering signal, i.e. initial object state -> manipulating action -> end state. Second, to cope with noisy uncurated training data, our model incorporates a noise adaptive weighting module supervised by a small number of annotated still images, that allows to efficiently filter out irrelevant videos during training. Third, we collect a new dataset with more than 2600 hours of video and 34 thousand changes of object states, and manually annotate a part of this data to validate our approach. Our results demonstrate substantial improvements over prior work in both action and object state-recognition in video.
-
This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a promising alternative to convolutional neural networks for visual recognition. But when there is no sufficient data, it gets stuck in overfitting and shows inferior performance. To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attribute surrogates. The intrinsic image structure is utilized to reduce the ambiguity between foreground content and background noise by spectral tokens pooling. And the attribute surrogate learning scheme is designed to benefit from the rich visual information in image-label pairs instead of simple visual concepts assigned by their labels. Our Hierarchically Cascaded Transformers, called HCTransformers, is built upon a self-supervised learning framework DINO and is tested on several popular few-shot learning benchmarks. In the inductive setting, HCTransformers surpass the DINO baseline by a large margin of 9.7% 5-way 1-shot accuracy and 9.17% 5-way 5-shot accuracy on mini-ImageNet, which demonstrates HCTransformers are efficient to extract discriminative features. Also, HCTransformers show clear advantages over SOTA few-shot classification methods in both 5-way 1-shot and 5-way 5-shot settings on four popular benchmark datasets, including mini-ImageNet, tiered-ImageNet, FC100, and CIFAR-FS. The trained weights and codes are available at https://github.com/StomachCold/HCTransformers.
-
In this paper, we consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set. Here, the unlabelled images may come from labelled classes or from novel ones. Existing recognition methods are not able to deal with this setting, because they make several restrictive assumptions, such as the unlabelled instances only coming from known -- or unknown -- classes, and the number of unknown classes being known a-priori. We address the more unconstrained setting, naming it 'Generalized Category Discovery', and challenge all these assumptions. We first establish strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task. Next, we propose the use of vision transformers with contrastive representation learning for this open-world setting. We then introduce a simple yet effective semi-supervised k-means method to cluster the unlabelled data into seen and unseen classes automatically, substantially outperforming the baselines. Finally, we also propose a new approach to estimate the number of classes in the unlabelled data. We thoroughly evaluate our approach on public datasets for generic object classification and on fine-grained datasets, leveraging the recent Semantic Shift Benchmark suite. Code: https://www.robots.ox.ac.uk/~vgg/research/gcd
-
Maximisation of Consensus (MaxCon) is one of the most widely used robust criteria in computer vision. Tennakoon et al. (CVPR2021), made a connection between MaxCon and estimation of influences of a Monotone Boolean function. In such, there are two distributions involved: the distribution defining the influence measure; and the distribution used for sampling to estimate the influence measure. This paper studies the concept of weighted influences for solving MaxCon. In particular, we study the Bernoulli measures. Theoretically, we prove the weighted influences, under this measure, of points belonging to larger structures are smaller than those of points belonging to smaller structures in general. We also consider another "natural" family of weighting strategies: sampling with uniform measure concentrated on a particular (Hamming) level of the cube. One can choose to have matching distributions: the same for defining the measure as for implementing the sampling. This has the advantage that the sampler is an unbiased estimator of the measure. Based on weighted sampling, we modify the algorithm of Tennakoon et al., and test on both synthetic and real datasets. We show some modest gains of Bernoulli sampling, and we illuminate some of the interactions between structure in data and weighted measures and weighted sampling.
-
Establishing correspondences between images remains a challenging task, especially under large appearance changes due to different viewpoints or intra-class variations. In this work, we introduce a strong semantic image matching learner, dubbed TransforMatcher, which builds on the success of transformer networks in vision domains. Unlike existing convolution- or attention-based schemes for correspondence, TransforMatcher performs global match-to-match attention for precise match localization and dynamic refinement. To handle a large number of matches in a dense correlation map, we develop a light-weight attention architecture to consider the global match-to-match interactions. We also propose to utilize a multi-channel correlation map for refinement, treating the multi-level scores as features instead of a single score to fully exploit the richer layer-wise semantics. In experiments, TransforMatcher sets a new state of the art on SPair-71k while performing on par with existing SOTA methods on the PF-PASCAL dataset.
-
Deep networks often make confident, yet, incorrect, predictions when tested with outlier data that is far removed from their training distributions. Likelihoods computed by deep generative models (DGMs) are a candidate metric for outlier detection with unlabeled data. Yet, previous studies have shown that DGM likelihoods are unreliable and can be easily biased by simple transformations to input data. Here, we examine outlier detection with variational autoencoders (VAEs), among the simplest of DGMs. We propose novel analytical and algorithmic approaches to ameliorate key biases with VAE likelihoods. Our bias corrections are sample-specific, computationally inexpensive, and readily computed for various decoder visible distributions. Next, we show that a well-known image pre-processing technique -- contrast stretching -- extends the effectiveness of bias correction to further improve outlier detection. Our approach achieves state-of-the-art accuracies with nine grayscale and natural image datasets, and demonstrates significant advantages -- both with speed and performance -- over four recent, competing approaches. In summary, lightweight remedies suffice to achieve robust outlier detection with VAEs.
-
We propose an effective and easy-to-implement method for simultaneously performing landmark detection in images and obtaining an ingenious uncertainty measurement for each landmark. Uncertainty measurements for landmarks are particularly useful in medical imaging applications: rather than giving an erroneous reading, a landmark detection system is more useful when it flags its level of confidence in its prediction. When an automated system is unsure of its predictions, the accuracy of the results can be further improved manually by a human. In the medical domain, being able to review an automated system's level of certainty significantly improves a clinician's trust in it. This paper obtains landmark predictions with uncertainty measurements using a three stage method: 1) We train our network on one-hot heatmap images, 2) We calibrate the uncertainty of the network using temperature scaling, 3) We calculate a novel statistic called 'Expected Radial Error' to obtain uncertainty measurements. We find that this method not only achieves localisation results on par with other state-of-the-art methods but also an uncertainty score which correlates with the true error for each landmark thereby bringing an overall step change in what a generic computer vision method for landmark detection should be capable of. In addition, we show that our uncertainty measurement can be used to classify, with good accuracy, what landmark predictions are likely to be inaccurate. Code available at: https://github.com/jfm15/ContourHuggingHeatmaps.git
-
In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion. The proposed approach aims to maintain cross-modality consistency by representing and fusing augmented image features as a ray in the voxel field. To this end, the learnable sampler is first designed to sample vital features from the image plane that are projected to the voxel grid in a point-to-ray manner, which maintains the consistency in feature representation with spatial context. In addition, ray-wise fusion is conducted to fuse features with the supplemental context in the constructed voxel field. We further develop mixed augmentor to align feature-variant transformations, which bridges the modality gap in data augmentation. The proposed framework is demonstrated to achieve consistent gains in various benchmarks and outperforms previous fusion-based methods on KITTI and nuScenes datasets. Code is made available at https://github.com/dvlab-research/VFF.
-
In response to the explosively-increasing requirement of annotated data, Novel Class Discovery (NCD) has emerged as a promising alternative to automatically recognize unknown classes without any annotation. To this end, a model makes use of a base set to learn basic semantic discriminability that can be transferred to recognize novel classes. Most existing works handle the base and novel sets using separate objectives within a two-stage training paradigm. Despite showing competitive performance on novel classes, they fail to generalize to recognizing samples from both base and novel sets. In this paper, we focus on this generalized setting of NCD (GNCD), and propose to divide and conquer it with two groups of Compositional Experts (ComEx). Each group of experts is designed to characterize the whole dataset in a comprehensive yet complementary fashion. With their union, we can solve GNCD in an efficient end-to-end manner. We further look into the drawback in current NCD methods, and propose to strengthen ComEx with global-to-local and local-to-local regularization. ComEx is evaluated on four popular benchmarks, showing clear superiority towards the goal of GNCD.
-
We introduce Programmatic Motion Concepts, a hierarchical motion representation for human actions that captures both low level motion and high level description as motion concepts. This representation enables human motion description, interactive editing, and controlled synthesis of novel video sequences within a single framework. We present an architecture that learns this concept representation from paired video and action sequences in a semi-supervised manner. The compactness of our representation also allows us to present a low-resource training recipe for data-efficient learning. By outperforming established baselines, especially in small data regime, we demonstrate the efficiency and effectiveness of our framework for multiple applications.
-
Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network response to a given input. This is directly related to the huge number of variables and the associated non-linearities of neural models, which are often used as black boxes. When it comes to critical applications as autonomous driving, security and safety, medicine and health, the lack of interpretability of the network behavior tends to induce skepticism and limited trustworthiness, despite the accurate performance of such systems in the given task. Furthermore, a single metric, such as the classification accuracy, provides a non-exhaustive evaluation of most real-world scenarios. In this paper, we want to make a step forward towards interpretability in neural networks, providing new tools to interpret their behavior. We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues and organizing the input distribution matching the conceptual-semantic hierarchical structure between classes. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, providing a more interpretable model than other state-of-the-art approaches.
-
Tensor completion using multiway delay-embedding transform (MDT) (or Hankelization) suffers from the large memory requirement and high computational cost in spite of its high potentiality for the image modeling. Recent studies have shown high completion performance with a relatively small window size, but experiments with large window sizes require huge amount of memory and cannot be easily calculated. In this study, we address this serious computational issue, and propose its fast and efficient algorithm. Key techniques of the proposed method are based on two properties: (1) the signal after MDT can be diagonalized by Fourier transform, (2) an inverse MDT can be represented as a convolutional form. To use the properties, we modify MDT-Tucker, a method using Tucker decomposition with MDT, and introducing the fast and efficient algorithm. Our experiments show more than 100 times acceleration while maintaining high accuracy, and to realize the computation with large window size.
-
This paper presents a novel framework to integrate both semantic and instance contexts for panoptic segmentation. In existing works, it is common to use a shared backbone to extract features for both things (countable classes such as vehicles) and stuff (uncountable classes such as roads). This, however, fails to capture the rich relations among them, which can be utilized to enhance visual understanding and segmentation performance. To address this shortcoming, we propose a novel Panoptic, Instance, and Semantic Relations (PISR) module to exploit such contexts. First, we generate panoptic encodings to summarize key features of the semantic classes and predicted instances. A Panoptic Relational Attention (PRA) module is then applied to the encodings and the global feature map from the backbone. It produces a feature map that captures 1) the relations across semantic classes and instances and 2) the relations between these panoptic categories and spatial features. PISR also automatically learns to focus on the more important instances, making it robust to the number of instances used in the relational attention module. Moreover, PISR is a general module that can be applied to any existing panoptic segmentation architecture. Through extensive evaluations on panoptic segmentation benchmarks like Cityscapes, COCO, and ADE20K, we show that PISR attains considerable improvements over existing approaches.
-
We present a simple and effective framework, named Point2Seq, for 3D object detection from point clouds. In contrast to previous methods that normally predict attributes of 3D objects all at once, we expressively model the interdependencies between attributes of 3D objects, which in turn enables a better detection accuracy. Specifically, we view each 3D object as a sequence of words and reformulate the 3D object detection task as decoding words from 3D scenes in an auto-regressive manner. We further propose a lightweight scene-to-sequence decoder that can auto-regressively generate words conditioned on features from a 3D scene as well as cues from the preceding words. The predicted words eventually constitute a set of sequences that completely describe the 3D objects in the scene, and all the predicted sequences are then automatically assigned to the respective ground truths through similarity-based sequence matching. Our approach is conceptually intuitive and can be readily plugged upon most existing 3D-detection backbones without adding too much computational overhead; the sequential decoding paradigm we proposed, on the other hand, can better exploit information from complex 3D scenes with the aid of preceding predicted words. Without bells and whistles, our method significantly outperforms the previous anchor- and center-based 3D object detection frameworks, yielding the new state-of-the-art on the challenging ONCE dataset as well as the Waymo Open Dataset. Code will be made publicly available.
-
We study the automatic generation of navigation instructions from 360-degree images captured on indoor routes. Existing generators suffer from poor visual grounding, causing them to rely on language priors and hallucinate objects. Our MARKY-MT5 system addresses this by focusing on visual landmarks; it comprises a first stage landmark detector and a second stage generator--a multimodal, multilingual, multitask encoder-decoder. To train it, we bootstrap grounded landmark annotations on top of the Room-across-Room (RxR) dataset. Using text parsers, weak supervision from RxR's pose traces, and a multilingual image-text encoder trained on 1.8b images, we identify 1.1m English, Hindi and Telugu landmark descriptions and ground them to specific regions in panoramas. On Room-to-Room, human wayfinders obtain success rates (SR) of 73% following MARKY-MT5's instructions, just shy of their 76% SR following human instructions---and well above SRs with other generators. Evaluations on RxR's longer, diverse paths obtain 62-64% SRs on three languages. Generating such high-quality navigation instructions in novel environments is a step towards conversational navigation tools and could facilitate larger-scale training of instruction-following agents.
-
We study the problem of few-shot open-set recognition (FSOR), which learns a recognition system capable of both fast adaptation to new classes with limited labeled examples and rejection of unknown negative samples. Traditional large-scale open-set methods have been shown ineffective for FSOR problem due to data limitation. Current FSOR methods typically calibrate few-shot closed-set classifiers to be sensitive to negative samples so that they can be rejected via thresholding. However, threshold tuning is a challenging process as different FSOR tasks may require different rejection powers. In this paper, we instead propose task-adaptive negative class envision for FSOR to integrate threshold tuning into the learning process. Specifically, we augment the few-shot closed-set classifier with additional negative prototypes generated from few-shot examples. By incorporating few-shot class correlations in the negative generation process, we are able to learn dynamic rejection boundaries for FSOR tasks. Besides, we extend our method to generalized few-shot open-set recognition (GFSOR), which requires classification on both many-shot and few-shot classes as well as rejection of negative samples. Extensive experiments on public benchmarks validate our methods on both problems.
-
We introduce Displacement Aware Relation Module (DisARM), a novel neural network module for enhancing the performance of 3D object detection in point cloud scenes. The core idea is extracting the most principal contextual information is critical for detection while the target is incomplete or featureless. We find that relations between proposals provide a good representation to describe the context. However, adopting relations between all the object or patch proposals for detection is inefficient, and an imbalanced combination of local and global relations brings extra noise that could mislead the training. Rather than working with all relations, we find that training with relations only between the most representative ones, or anchors, can significantly boost the detection performance. Good anchors should be semantic-aware with no ambiguity and able to describe the whole layout of a scene with no redundancy. To find the anchors, we first perform a preliminary relation anchor module with an objectness-aware sampling approach and then devise a displacement based module for weighing the relation importance for better utilization of contextual information. This light-weight relation module leads to significantly higher accuracy of object instance detection when being plugged into the state-of- the-art detectors. Evaluations on the public benchmarks of real-world scenes show that our method achieves the state-of-the-art performance on both SUN RGB-D and ScanNet V2. The code and models are publicly available at https://github.com/YaraDuan/DisARM.
-
Waste inspection for packaged waste is an important step in the pipeline of waste disposal. Previous methods either rely on manual visual checking or RGB image-based inspection algorithm, requiring costly preparation procedures (e.g., open the bag and spread the waste items). Moreover, occluded items are very likely to be left out. Inspired by the fact that X-ray has a strong penetrating power to see through the bag and overlapping objects, we propose to perform waste inspection efficiently using X-ray images without the need to open the bag. We introduce a novel problem of instance-level waste segmentation in X-ray image for intelligent waste inspection, and contribute a real dataset consisting of 5,038 X-ray images (totally 30,881 waste items) with high-quality annotations (i.e., waste categories, object boxes, and instance-level masks) as a benchmark for this problem. As existing segmentation methods are mainly designed for natural images and cannot take advantage of the characteristics of X-ray waste images (e.g., heavy occlusions and penetration effect), we propose a new instance segmentation method to explicitly take these image characteristics into account. Specifically, our method adopts an easy-to-hard disassembling strategy to use high confidence predictions to guide the segmentation of highly overlapped objects, and a global structure guidance module to better capture the complex contour information caused by the penetration effect. Extensive experiments demonstrate the effectiveness of the proposed method. Our dataset is released at WIXRayNet.
-
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We propose MixFormer to find a solution. First, we combine local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields. Second, we propose bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions. These two designs are integrated to achieve efficient feature mixing among windows and dimensions. Our MixFormer provides competitive results on image classification with EfficientNet and shows better results than RegNet and Swin Transformer. Performance in downstream tasks outperforms its alternatives by significant margins with less computational costs in 5 dense prediction tasks on MS COCO, ADE20k, and LVIS. Code is available at https://github.com/PaddlePaddle/PaddleClas.
-
Learning discriminative deep feature embeddings by using million-scale in-the-wild datasets and margin-based softmax loss is the current state-of-the-art approach for face recognition. However, the memory and computing cost of the Fully Connected (FC) layer linearly scales up to the number of identities in the training set. Besides, the large-scale training data inevitably suffers from inter-class conflict and long-tailed distribution. In this paper, we propose a sparsely updating variant of the FC layer, named Partial FC (PFC). In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss. All class centers are still maintained throughout the whole training process, but only a subset is selected and updated in each iteration. Therefore, the computing requirement, the probability of inter-class conflict, and the frequency of passive update on tail class centers, are dramatically reduced. Extensive experiments across different training data and backbones (e.g. CNN and ViT) confirm the effectiveness, robustness and efficiency of the proposed PFC.
-
Implicit neural rendering, especially Neural Radiance Field (NeRF), has shown great potential in novel view synthesis of a scene. However, current NeRF-based methods cannot enable users to perform user-controlled shape deformation in the scene. While existing works have proposed some approaches to modify the radiance field according to the user's constraints, the modification is limited to color editing or object translation and rotation. In this paper, we propose a method that allows users to perform controllable shape deformation on the implicit representation of the scene, and synthesizes the novel view images of the edited scene without re-training the network. Specifically, we establish a correspondence between the extracted explicit mesh representation and the implicit neural representation of the target scene. Users can first utilize well-developed mesh-based deformation methods to deform the mesh representation of the scene. Our method then utilizes user edits from the mesh representation to bend the camera rays by introducing a tetrahedra mesh as a proxy, obtaining the rendering results of the edited scene. Extensive experiments demonstrate that our framework can achieve ideal editing results not only on synthetic data, but also on real scenes captured by users.
-
Mean Average Precision (mAP) is the primary evaluation measure for object detection. Although object detection has a broad range of applications, mAP evaluates detectors in terms of the performance of ranked instance retrieval. Such the assumption for the evaluation task does not suit some downstream tasks. To alleviate the gap between downstream tasks and the evaluation scenario, we propose Optimal Correction Cost (OC-cost), which assesses detection accuracy at image level. OC-cost computes the cost of correcting detections to ground truths as a measure of accuracy. The cost is obtained by solving an optimal transportation problem between the detections and the ground truths. Unlike mAP, OC-cost is designed to penalize false positive and false negative detections properly, and every image in a dataset is treated equally. Our experimental result validates that OC-cost has better agreement with human preference than a ranking-based measure, i.e., mAP for a single image. We also show that detectors' rankings by OC-cost are more consistent on different data splits than mAP. Our goal is not to replace mAP with OC-cost but provide an additional tool to evaluate detectors from another aspect. To help future researchers and developers choose a target measure, we provide a series of experiments to clarify how mAP and OC-cost differ.
-
Asymmetric image retrieval, which typically uses small model for query side and large model for database server, is an effective solution for resource-constrained scenarios. However, existing approaches either fail to achieve feature coherence or make strong assumptions, e.g., requiring labeled datasets or classifiers from large model, etc., which limits their practical application. To this end, we propose a flexible contextual similarity distillation framework to enhance the small query model and keep its output feature compatible with that of large gallery model, which is crucial with asymmetric retrieval. In our approach, we learn the small model with a new contextual similarity consistency constraint without any data label. During the small model learning, it preserves the contextual similarity among each training image and its neighbors with the features extracted by the large model. Note that this simple constraint is consistent with simultaneous first-order feature vector preserving and second-order ranking list preserving. Extensive experiments show that the proposed method outperforms the state-of-the-art methods on the Revisited Oxford and Paris datasets.
-
Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability. We argue that understanding both high-level semantics and internal temporal structures of actions in competitive sports videos is the key to making predictions accurate and interpretable. Towards this goal, we construct a new fine-grained dataset, called FineDiving, developed on diverse diving events with detailed annotations on action procedures. We also propose a procedure-aware approach for action quality assessment, learned by a new Temporal Segmentation Attention module. Specifically, we propose to parse pairwise query and exemplar action instances into consecutive steps with diverse semantic and temporal correspondences. The procedure-aware cross-attention is proposed to learn embeddings between query and exemplar steps to discover their semantic, spatial, and temporal correspondences, and further serve for fine-grained contrastive regression to derive a reliable scoring mechanism. Extensive experiments demonstrate that our approach achieves substantial improvements over the state-of-the-art methods with better interpretability. The dataset and code are available at https://github.com/xujinglin/FineDiving.
-
Style transfer has been well studied in recent years with excellent performance processed. While existing methods usually choose CNNs as the powerful tool to accomplish superb stylization, less attention was paid to the latent style space. Rare exploration of underlying dimensions results in the poor style controllability and the limited practical application. In this work, we rethink the internal meaning of style features, further proposing a novel unsupervised algorithm for style discovery and achieving personalized manipulation. In particular, we take a closer look into the mechanism of style transfer and obtain different artistic style components from the latent space consisting of different style features. Then fresh styles can be generated by linear combination according to various style components. Experimental results have shown that our approach is superb in 1) restylizing the original output with the diverse artistic styles discovered from the latent space while keeping the content unchanged, and 2) being generic and compatible for various style transfer methods.
-
This paper presents a novel attention-based neural network for structured reconstruction, which takes a 2D raster image as an input and reconstructs a planar graph depicting an underlying geometric structure. The approach detects corners and classifies edge candidates between corners in an end-to-end manner. Our contribution is a holistic edge classification architecture, which 1) initializes the feature of an edge candidate by a trigonometric positional encoding of its end-points; 2) fuses image feature to each edge candidate by deformable attention; 3) employs two weight-sharing Transformer decoders to learn holistic structural patterns over the graph edge candidates; and 4) is trained with a masked learning strategy. The corner detector is a variant of the edge classification architecture, adapted to operate on pixels as corner candidates. We conduct experiments on two structured reconstruction tasks: outdoor building architecture and indoor floorplan planar graph reconstruction. Extensive qualitative and quantitative evaluations demonstrate the superiority of our approach over the state of the art. Code and pre-trained models are available at https://heat-structured-reconstruction.github.io
-
The inversion of real images into StyleGAN's latent space is a well-studied problem. Nevertheless, applying existing approaches to real-world scenarios remains an open challenge, due to an inherent trade-off between reconstruction and editability: latent space regions which can accurately represent real images typically suffer from degraded semantic control. Recent work proposes to mitigate this trade-off by fine-tuning the generator to add the target image to well-behaved, editable regions of the latent space. While promising, this fine-tuning scheme is impractical for prevalent use as it requires a lengthy training phase for each new image. In this work, we introduce this approach into the realm of encoder-based inversion. We propose HyperStyle, a hypernetwork that learns to modulate StyleGAN's weights to faithfully express a given image in editable regions of the latent space. A naive modulation approach would require training a hypernetwork with over three billion parameters. Through careful network design, we reduce this to be in line with existing encoders. HyperStyle yields reconstructions comparable to those of optimization techniques with the near real-time inference capabilities of encoders. Lastly, we demonstrate HyperStyle's effectiveness on several applications beyond the inversion task, including the editing of out-of-domain images which were never seen during training.
-
The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms of bias. We further introduce a novel semantic alignment loss to establish balanced feature representation to reduce the biased predictions from the classifier. We term the whole framework as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label. We conduct extensive experiments in a wide range of imbalanced benchmarks: CIFAR10/100-LT, STL10-LT, and large-scale long-tailed Semi-Aves with open-set class, and demonstrate that, the proposed DASO framework reliably improves SSL learners with unlabeled data especially when both (1) class imbalance and (2) distribution mismatch dominate.
-
We present Mobile-Former, a parallel design of MobileNet and transformer with a two-way bridge in between. This structure leverages the advantages of MobileNet at local processing and transformer at global interaction. And the bridge enables bidirectional fusion of local and global features. Different from recent works on vision transformer, the transformer in Mobile-Former contains very few tokens (e.g. 6 or fewer tokens) that are randomly initialized to learn global priors, resulting in low computational cost. Combining with the proposed light-weight cross attention to model the bridge, Mobile-Former is not only computationally efficient, but also has more representation power. It outperforms MobileNetV3 at low FLOP regime from 25M to 500M FLOPs on ImageNet classification. For instance, Mobile-Former achieves 77.9% top-1 accuracy at 294M FLOPs, gaining 1.3% over MobileNetV3 but saving 17% of computations. When transferring to object detection, Mobile-Former outperforms MobileNetV3 by 8.6 AP in RetinaNet framework. Furthermore, we build an efficient end-to-end detector by replacing backbone, encoder and decoder in DETR with Mobile-Former, which outperforms DETR by 1.3 AP but saves 52% of computational cost and 36% of parameters. Code will be released at https://github.com/aaboys/mobileformer.
-
We present a novel self-distillation based self-supervised monocular depth estimation (SD-SSMDE) learning framework. In the first step, our network is trained in a self-supervised regime on high-resolution images with the photometric loss. The network is further used to generate pseudo depth labels for all the images in the training set. To improve the performance of our estimates, in the second step, we re-train the network with the scale invariant logarithmic loss supervised by pseudo labels. We resolve scale ambiguity and inter-frame scale consistency by introducing an automatically computed scale in our depth labels. To filter out noisy depth values, we devise a filtering scheme based on the 3D consistency between consecutive views. Extensive experiments demonstrate that each proposed component and the self-supervised learning framework improve the quality of the depth estimation over the baseline and achieve state-of-the-art results on the KITTI and Cityscapes datasets.
-
Self- and cross-attention in Transformers provide for high model capacity, making them viable models for object detection. However, Transformers still lag in performance behind CNN-based detectors. This is, we believe, because: (a) Cross-attention is used for both classification and bounding-box regression tasks; (b) Transformer's decoder poorly initializes content queries; and (c) Self-attention poorly accounts for certain prior knowledge which could help improve inductive bias. These limitations are addressed with the corresponding three contributions. First, we propose a new Detection Split Transformer (DESTR) that separates estimation of cross-attention into two independent branches -- one tailored for classification and the other for box regression. Second, we use a mini-detector to initialize the content queries in the decoder with classification and regression embeddings of the respective heads in the mini-detector. Third, we augment self-attention in the decoder to additionally account for pairs of adjacent object queries. Our experiments on the MS-COCO dataset show that DESTR outperforms DETR and its successors.
-
The reasonable trajectory prediction of surrounding traffic participants is crucial for autonomous driving. Especially, how to predict multiple plausible trajectories is still a challenging problem because of the multiple possibilities of the future. Proposal-based prediction methods address the multi-modality issues with a two-stage approach, commonly using intention classification followed by motion regression. This paper proposes a two-stage proposal-based motion forecasting method that exploits the sliced lane segments as fine-grained, shareable, and interpretable proposals. We use Graph neural network and Transformer to encode the shape and interaction information among the map sub-graphs and the agents sub-graphs. In addition, we propose a variance-based non-maximum suppression strategy to select representative trajectories that ensure the diversity of the final output. Experiments on the Argoverse dataset show that the proposed method outperforms state-of-the-art methods, and the lane segments-based proposals as well as the variance-based non-maximum suppression strategy both contribute to the performance improvement. Moreover, we demonstrate that the proposed method can achieve reliable performance with a lower collision rate and fewer off-road scenarios in the closed-loop simulation.
-
Curating a large set of fully annotated training data can be costly, especially for the tasks of medical image segmentation. Scribble, a weaker form of annotation, is more obtainable in practice, but training segmentation models from limited supervision of scribbles is still challenging. To address the difficulties, we propose a new framework for scribble learning-based medical image segmentation, which is composed of mix augmentation and cycle consistency and thus is referred to as CycleMix. For augmentation of supervision, CycleMix adopts the mixup strategy with a dedicated design of random occlusion, to perform increments and decrements of scribbles. For regularization of supervision, CycleMix intensifies the training objective with consistency losses to penalize inconsistent segmentation, which results in significant improvement of segmentation performance. Results on two open datasets, i.e., ACDC and MSCMRseg, showed that the proposed method achieved exhilarating performance, demonstrating comparable or even better accuracy than the fully-supervised methods. The code and expert-made scribble annotations for MSCMRseg are publicly available at https://github.com/BWGZK/CycleMIx.
-
Videos typically record the streaming and continuous visual data as discrete consecutive frames. Since the storage cost is expensive for videos of high fidelity, most of them are stored in a relatively low resolution and frame rate. Recent works of Space-Time Video Super-Resolution (STVSR) are developed to incorporate temporal interpolation and spatial super-resolution in a unified framework. However, most of them only support a fixed up-sampling scale, which limits their flexibility and applications. In this work, instead of following the discrete representations, we propose Video Implicit Neural Representation (VideoINR), and we show its applications for STVSR. The learned implicit neural representation can be decoded to videos of arbitrary spatial resolution and frame rate. We show that VideoINR achieves competitive performances with state-of-the-art STVSR methods on common up-sampling scales and significantly outperforms prior works on continuous and out-of-training-distribution scales. Our project page is at http://zeyuan-chen.com/VideoINR/ and code is available at https://github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution.
-
Scene text detection and document layout analysis have long been treated as two separate tasks in different image domains. In this paper, we bring them together and introduce the task of unified scene text detection and layout analysis. The first hierarchical scene text dataset is introduced to enable this novel research task. We also propose a novel method that is able to simultaneously detect scene text and form text clusters in a unified way. Comprehensive experiments show that our unified model achieves better performance than multiple well-designed baseline methods. Additionally, this model achieves state-of-the-art results on multiple scene text detection datasets without the need of complex post-processing. Dataset and code: https://github.com/google-research-datasets/hiertext.
-
In this work, we present a solution to the challenging problem of reconstructing liquids from image data. The challenges in reconstructing liquids, which is not faced in previous reconstruction works on rigid and deforming surfaces, lies in the inability to use depth sensing and color features due the variable index of refraction, opacity, and environmental reflections. Therefore, we limit ourselves to only surface detections (i.e. binary mask) of liquids as observations and do not assume any prior knowledge on the liquids properties. A novel optimization problem is posed which reconstructs the liquid as particles by minimizing the error between a rendered surface from the particles and the surface detections while satisfying liquid constraints. Our solvers to this optimization problem are presented and no training data is required to apply them. We also propose a dynamic prediction to seed the reconstruction optimization from the previous time-step. We test our proposed methods in simulation and on two new liquid datasets which we open source so the broader research community can continue developing in this under explored area.
-
We study the problem of contextual outpainting, which aims to hallucinate the missing background contents based on the remaining foreground contents. Existing image outpainting methods focus on completing object shapes or extending existing scenery textures, neglecting the semantically meaningful relationship between the missing and remaining contents. To explore the semantic cues provided by the remaining foreground contents, we propose a novel ConTextual Outpainting GAN (CTO-GAN), leveraging the semantic layout as a bridge to synthesize coherent and diverse background contents. To model the contextual correlation between foreground and background contents, we incorporate an object-level contrastive loss to regularize the learning of cross-modal representations of foreground contents and the corresponding background semantic layout, facilitating accurate semantic reasoning. Furthermore, we improve the realism of the generated background contents via detecting generated context in adversarial training. Extensive experiments demonstrate that the proposed method achieves superior performance compared with existing solutions on the challenging COCO-stuff dataset.
-
Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical assumptions like pixel-wise independent noise. Hence, it is challenging to deal with spatially correlated real-world noise using self-supervised BSN. Recently, pixel-shuffle downsampling (PD) has been proposed to remove the spatial correlation of real-world noise. However, it is not trivial to integrate PD and BSN directly, which prevents the fully self-supervised denoising model on real-world images. We propose an Asymmetric PD (AP) to address this issue, which introduces different PD stride factors for training and inference. We systematically demonstrate that the proposed AP can resolve inherent trade-offs caused by specific PD stride factors and make BSN applicable to practical scenarios. To this end, we develop AP-BSN, a state-of-the-art self-supervised denoising method for real-world sRGB images. We further propose random-replacing refinement, which significantly improves the performance of our AP-BSN without any additional parameters. Extensive studies demonstrate that our method outperforms the other self-supervised and even unpaired denoising methods by a large margin, without using any additional knowledge, e.g., noise level, regarding the underlying unknown noise.
-
Powerful priors allow us to perform inference with insufficient information. In this paper, we propose an autoregressive prior for 3D shapes to solve multimodal 3D tasks such as shape completion, reconstruction, and generation. We model the distribution over 3D shapes as a non-sequential autoregressive distribution over a discretized, low-dimensional, symbolic grid-like latent representation of 3D shapes. This enables us to represent distributions over 3D shapes conditioned on information from an arbitrary set of spatially anchored query locations and thus perform shape completion in such arbitrary settings (e.g. generating a complete chair given only a view of the back leg). We also show that the learned autoregressive prior can be leveraged for conditional tasks such as single-view reconstruction and language-based generation. This is achieved by learning task-specific 'naive' conditionals which can be approximated by light-weight models trained on minimal paired data. We validate the effectiveness of the proposed method using both quantitative and qualitative evaluation and show that the proposed method outperforms the specialized state-of-the-art methods trained for individual tasks. The project page with code and video visualizations can be found at https://yccyenchicheng.github.io/AutoSDF/.
-
Recent works show that convolutional neural network (CNN) architectures have a spectral bias towards lower frequencies, which has been leveraged for various image restoration tasks in the Deep Image Prior (DIP) framework. The benefit of the inductive bias the network imposes in the DIP framework depends on the architecture. Therefore, researchers have studied how to automate the search to determine the best-performing model. However, common neural architecture search (NAS) techniques are resource and time-intensive. Moreover, best-performing models are determined for a whole dataset of images instead of for each image independently, which would be prohibitively expensive. In this work, we first show that optimal neural architectures in the DIP framework are image-dependent. Leveraging this insight, we then propose an image-specific NAS strategy for the DIP framework that requires substantially less training than typical NAS approaches, effectively enabling image-specific NAS. We justify the proposed strategy's effectiveness by (1) demonstrating its performance on a NAS Dataset for DIP that includes 522 models from a particular search space (2) conducting extensive experiments on image denoising, inpainting, and super-resolution tasks. Our experiments show that image-specific metrics can reduce the search space to a small cohort of models, of which the best model outperforms current NAS approaches for image restoration. Codes and datasets are available at https://github.com/ozgurkara99/ISNAS-DIP.
-
Existing approaches for Structure from Motion (SfM) produce impressive 3D reconstruction results especially when using imagery captured with large parallax. However, to create engaging video-content in movies and TV shows, the amount by which a camera can be moved while filming a particular shot is often limited. The resulting small-motion parallax between video frames makes standard geometry-based SfM approaches not as effective for movies and TV shows. To address this challenge, we propose a simple yet effective approach that uses single-frame depth-prior obtained from a pretrained network to significantly improve geometry-based SfM for our small-parallax setting. To this end, we first use the depth-estimates of the detected keypoints to reconstruct the point cloud and camera-pose for initial two-view reconstruction. We then perform depth-regularized optimization to register new images and triangulate the new points during incremental reconstruction. To comprehensively evaluate our approach, we introduce a new dataset (StudioSfM) consisting of 130 shots with 21K frames from 15 studio-produced videos that are manually annotated by a professional CG studio. We demonstrate that our approach: (a) significantly improves the quality of 3D reconstruction for our small-parallax setting, (b) does not cause any degradation for data with large-parallax, and (c) maintains the generalizability and scalability of geometry-based sparse SfM. Our dataset can be obtained at github.com/amazon-research/small-baseline-camera-tracking.
-
The referring video object segmentation task (RVOS) involves segmentation of a text-referred object instance in the frames of a given video. Due to the complex nature of this multimodal task, which combines text reasoning, video understanding, instance segmentation and tracking, existing approaches typically rely on sophisticated pipelines in order to tackle it. In this paper, we propose a simple Transformer-based approach to RVOS. Our framework, termed Multimodal Tracking Transformer (MTTR), models the RVOS task as a sequence prediction problem. Following recent advancements in computer vision and natural language processing, MTTR is based on the realization that video and text can be processed together effectively and elegantly by a single multimodal Transformer model. MTTR is end-to-end trainable, free of text-related inductive bias components and requires no additional mask-refinement post-processing steps. As such, it simplifies the RVOS pipeline considerably compared to existing methods. Evaluation on standard benchmarks reveals that MTTR significantly outperforms previous art across multiple metrics. In particular, MTTR shows impressive +5.7 and +5.0 mAP gains on the A2D-Sentences and JHMDB-Sentences datasets respectively, while processing 76 frames per second. In addition, we report strong results on the public validation set of Refer-YouTube-VOS, a more challenging RVOS dataset that has yet to receive the attention of researchers. The code to reproduce our experiments is available at https://github.com/mttr2021/MTTR
-
In this paper, we present a general-purpose solution to cartoon image synthesis with unpaired training data. In contrast to previous works learning pre-defined cartoon styles for specified usage scenarios (portrait or scene), we aim to train a common cartoon translator which can not only simultaneously render exaggerated anime faces and realistic cartoon scenes, but also provide flexible user controls for desired cartoon styles. It is challenging due to the complexity of the task and the absence of paired data. The core idea of the proposed method is to introduce gated cycle mapping, that utilizes a novel gated mapping unit to produce the category-specific style code and embeds this code into cycle networks to control the translation process. For the concept of category, we classify images into different categories (e.g., 4 types: photo/cartoon portrait/scene) and learn finer-grained category translations rather than overall mappings between two domains (e.g., photo and cartoon). Furthermore, the proposed method can be easily extended to cartoon video generation with an auxiliary dataset and a new adaptive style loss. Experimental results demonstrate the superiority of the proposed method over the state of the art and validate its effectiveness in the brand-new task of general cartoon image synthesis.
-
We present IterMVS, a new data-driven method for high-resolution multi-view stereo. We propose a novel GRU-based estimator that encodes pixel-wise probability distributions of depth in its hidden state. Ingesting multi-scale matching information, our model refines these distributions over multiple iterations and infers depth and confidence. To extract the depth maps, we combine traditional classification and regression in a novel manner. We verify the efficiency and effectiveness of our method on DTU, Tanks&Temples and ETH3D. While being the most efficient method in both memory and run-time, our model achieves competitive performance on DTU and better generalization ability on Tanks&Temples as well as ETH3D than most state-of-the-art methods. Code is available at https://github.com/FangjinhuaWang/IterMVS.
-
We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection. In particular, the foreground points are inherently more important than background points for object detectors. Motivated by this, we propose a highly-efficient single-stage point-based 3D detector in this paper, termed IA-SSD. The key of our approach is to exploit two learnable, task-oriented, instance-aware downsampling strategies to hierarchically select the foreground points belonging to objects of interest. Additionally, we also introduce a contextual centroid perception module to further estimate precise instance centers. Finally, we build our \nickname following the encoder-only architecture for efficiency. Extensive experiments conducted on several large-scale detection benchmarks demonstrate the competitive performance of our IA-SSD. Thanks to the low memory footprint and a high degree of parallelism, it achieves a superior speed of 80+ frames-per-second on the KITTI dataset with a single RTX2080Ti GPU. The code is available at https://github.com/yifanzhang713/IA-SSD.
-
Federated learning (FL) is a privacy-preserving distributed learning paradigm that enables clients to jointly train a global model. In real-world FL implementations, client data could have label noise, and different clients could have vastly different label noise levels. Although there exist methods in centralized learning for tackling label noise, such methods do not perform well on heterogeneous label noise in FL settings, due to the typically smaller sizes of client datasets and data privacy requirements in FL. In this paper, we propose FedCorr, a general multi-stage framework to tackle heterogeneous label noise in FL, without making any assumptions on the noise models of local clients, while still maintaining client data privacy. In particular, (1) FedCorr dynamically identifies noisy clients by exploiting the dimensionalities of the model prediction subspaces independently measured on all clients, and then identifies incorrect labels on noisy clients based on per-sample losses. To deal with data heterogeneity and to increase training stability, we propose an adaptive local proximal regularization term that is based on estimated local noise levels. (2) We further finetune the global model on identified clean clients and correct the noisy labels for the remaining noisy clients after finetuning. (3) Finally, we apply the usual training on all clients to make full use of all local data. Experiments conducted on CIFAR-10/100 with federated synthetic label noise, and on a real-world noisy dataset, Clothing1M, demonstrate that FedCorr is robust to label noise and substantially outperforms the state-of-the-art methods at multiple noise levels.
-
Camouflaged object detection (COD) aims to identify objects that are perfectly embedded in their environment, which has various downstream applications in fields such as medicine, art, and agriculture. However, it is an extremely challenging task to spot camouflaged objects with the perception ability of human eyes. Hence, we claim that the goal of COD task is not just to mimic the human visual ability in a single RGB domain, but to go beyond the human biological vision. We then introduce the frequency domain as an additional clue to better detect camouflaged objects from backgrounds. To well involve the frequency clues into the CNN models, we present a powerful network with two special components. We first design a novel frequency enhancement module (FEM) to dig clues of camouflaged objects in the frequency domain. It contains the offline discrete cosine transform followed by the learnable enhancement. Then we use a feature alignment to fuse the features from RGB domain and frequency domain. Moreover, to further make full use of the frequency information, we propose the high-order relation module (HOR) to handle the rich fusion feature. Comprehensive experiments on three widely-used COD datasets show the proposed method significantly outperforms other state-of-the-art methods by a large margin. The code and results are released in https://github.com/luckybird1994/FDCOD.
-
Volumetric neural rendering methods, such as neural ra-diance fields (NeRFs), have enabled photo-realistic novel view synthesis. However, in their standard form, NeRFs do not support the editing of objects, such as a human head,within a scene. In this work, we propose RigNeRF, a system that goes beyond just novel view synthesis and enables full control of head pose and facial expressions learned from a single portrait video. We model changes in head pose and facial expressions using a deformation field that is guided by a 3D morphable face model (3DMM). The 3DMM effectively acts as a prior for RigNeRF that learns to predict only residuals to the 3DMM deformations and allows us to render novel (rigid) poses and (non-rigid) expressions that were not present in the input sequence. Using only a smartphone-captured short video of a subject for training,we demonstrate the effectiveness of our method on free view synthesis of a portrait scene with explicit head pose and expression controls.
-
Generating shapes using natural language can enable new ways of imagining and creating the things around us. While significant recent progress has been made in text-to-image generation, text-to-shape generation remains a challenging problem due to the unavailability of paired text and shape data at a large scale. We present a simple yet effective method for zero-shot text-to-shape generation that circumvents such data scarcity. Our proposed method, named CLIP-Forge, is based on a two-stage training process, which only depends on an unlabelled shape dataset and a pre-trained image-text network such as CLIP. Our method has the benefits of avoiding expensive inference time optimization, as well as the ability to generate multiple shapes for a given text. We not only demonstrate promising zero-shot generalization of the CLIP-Forge model qualitatively and quantitatively, but also provide extensive comparative evaluations to better understand its behavior.
-
Image-based virtual try-on aims to fit an in-shop garment into a clothed person image. To achieve this, a key step is garment warping which spatially aligns the target garment with the corresponding body parts in the person image. Prior methods typically adopt a local appearance flow estimation model. They are thus intrinsically susceptible to difficult body poses/occlusions and large mis-alignments between person and garment images. To overcome this limitation, a novel global appearance flow estimation model is proposed in this work. For the first time, a StyleGAN based architecture is adopted for appearance flow estimation. This enables us to take advantage of a global style vector to encode a whole-image context to cope with the aforementioned challenges. To guide the StyleGAN flow generator to pay more attention to local garment deformation, a flow refinement module is introduced to add local context. Experiment results on a popular virtual try-on benchmark show that our method achieves new state-of-the-art performance. It is particularly effective in a 'in-the-wild' application scenario where the reference image is full-body resulting in a large mis-alignment with the garment image.
-
Source-free object detection (SFOD) needs to adapt a detector pre-trained on a labeled source domain to a target domain, with only unlabeled training data from the target domain. Existing SFOD methods typically adopt the pseudo labeling paradigm with model adaption alternating between predicting pseudo labels and fine-tuning the model. This approach suffers from both unsatisfactory accuracy of pseudo labels due to the presence of domain shift and limited use of target domain training data. In this work, we present a novel Learning to Overlook Domain Style (LODS) method with such limitations solved in a principled manner. Our idea is to reduce the domain shift effect by enforcing the model to overlook the target domain style, such that model adaptation is simplified and becomes easier to carry on. To that end, we enhance the style of each target domain image and leverage the style degree difference between the original image and the enhanced image as a self-supervised signal for model adaptation. By treating the enhanced image as an auxiliary view, we exploit a student-teacher architecture for learning to overlook the style degree difference against the original image, also characterized with a novel style enhancement algorithm and graph alignment constraint. Extensive experiments demonstrate that our LODS yields new state-of-the-art performance on four benchmarks.
-
Existing active learning studies typically work in the closed-set setting by assuming that all data examples to be labeled are drawn from known classes. However, in real annotation tasks, the unlabeled data usually contains a large amount of examples from unknown classes, resulting in the failure of most active learning methods. To tackle this open-set annotation (OSA) problem, we propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation. The LfOSA framework introduces an auxiliary network to model the per-example max activation value (MAV) distribution with a Gaussian Mixture Model, which can dynamically select the examples with highest probability from known classes in the unlabeled set. Moreover, by reducing the temperature T of the loss function, the detection model will be further optimized by exploiting both known and unknown supervision. The experimental results show that the proposed method can significantly improve the selection quality of known classes, and achieve higher classification accuracy with lower annotation cost than state-of-the-art active learning methods. To the best of our knowledge, this is the first work of active learning for open-set annotation.
-
Standard visual localization methods build a priori 3D model of a scene which is used to establish correspondences against the 2D keypoints in a query image. Storing these pre-built 3D scene models can be prohibitively expensive for large-scale environments, especially on mobile devices with limited storage and communication bandwidth. We design a novel framework that compresses a scene while still maintaining localization accuracy. The scene is compressed in three stages: first, the database frames are clustered using pairwise co-visibility information. Then, a learned point selection module prunes the points in each cluster taking into account the final pose estimation accuracy. In the final stage, the features of the selected points are further compressed using learned quantization. Query image registration is done using only the compressed scene points. To the best of our knowledge, we are the first to propose learned scene compression for visual localization. We also demonstrate the effectiveness and efficiency of our method on various outdoor datasets where it can perform accurate localization with low memory consumption.
-
We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods require a predefined template mesh for a given sequence, while the template is hard to acquire for a specific subject. Meanwhile, the fixed topology limits the reconstruction accuracy and clothing types. Implicit representation supports arbitrary topology and can represent high-fidelity geometry shapes due to its continuous nature. However, it is difficult to integrate multi-frame information to produce a consistent registration sequence for downstream applications. We propose to combine the advantages of both representations. We utilize differential mask loss of the explicit mesh to obtain the coherent overall shape, while the details on the implicit surface are refined with the differentiable neural rendering. Meanwhile, the explicit mesh is updated periodically to adjust its topology changes, and a consistency loss is designed to match both representations. Compared with existing methods, SelfRecon can produce high-fidelity surfaces for arbitrary clothed humans with self-supervised optimization. Extensive experimental results demonstrate its effectiveness on real captured monocular videos. The source code is available at https://github.com/jby1993/SelfReconCode.
-
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers. However, it is very challenging to estimate the transition matrix T(x), where T(x) denotes the instance, because it is unidentifiable under the instance-dependent noise (IDN). To address this problem, we have noticed that, there are psychological and physiological evidences showing that we humans are more likely to annotate instances of similar appearances to the same classes, and thus poor-quality or ambiguous instances of similar appearances are easier to be mislabeled to the correlated or same noisy classes. Therefore, we propose assumption on the geometry of T(x) that "the closer two instances are, the more similar their corresponding transition matrices should be". More specifically, we formulate above assumption into the manifold embedding, to effectively reduce the degree of freedom of T(x) and make it stably estimable in practice. This proposed manifold-regularized technique works by directly reducing the estimation error without hurting the approximation error about the estimation problem of T(x) Experimental evaluations on four synthetic and two real-world datasets demonstrate our method is superior to state-of-the-art approaches for label-noise learning under the challenging IDN.
-
A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the pre-determined composition of multiple data augmentations brings two drawbacks. First, the artificial choice of augmentation types brings specific representational invariances to the model, which have different degrees of positive and negative effects on different downstream tasks. Treating each type of augmentation equally during training makes the model learn non-optimal representations for various downstream tasks and limits the flexibility to choose augmentation types beforehand. Second, the strong data augmentations used in classic contrastive learning methods may bring too much invariance in some cases, and fine-grained information that is essential to some downstream tasks may be lost. This paper proposes a general method to alleviate these two problems by considering "where" and "what" to contrast in a general contrastive learning framework. We first propose to learn different augmentation invariances at different depths of the model according to the importance of each data augmentation instead of learning representational invariances evenly in the backbone. We then propose to expand the contrast content with augmentation embeddings to reduce the misleading effects of strong data augmentations. Experiments based on several baseline methods demonstrate that we learn better representations for various benchmarks on classification, detection, and segmentation downstream tasks.
-
Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically reduced in a Continual Learning (CL) scenario where data is presented to the model sequentially. In this paper, we show that self-supervised loss functions can be seamlessly converted into distillation mechanisms for CL by adding a predictor network that maps the current state of the representations to their past state. This enables us to devise a framework for Continual self-supervised visual representation Learning that (i) significantly improves the quality of the learned representations, (ii) is compatible with several state-of-the-art self-supervised objectives, and (iii) needs little to no hyperparameter tuning. We demonstrate the effectiveness of our approach empirically by training six popular self-supervised models in various CL settings. Code: github.com/DonkeyShot21/cassle
-
Convolutional image deraining networks have achieved great success while suffering from tremendous computational and memory costs. Most model compression methods require original data for iterative fine-tuning, which is limited in real-world applications due to storage, privacy, and transmission constraints. We note that it is overstretched to fine-tune the compressed model using self-collected data, as it exhibits poor generalization over images with different degradation characteristics. To address this problem, we propose a novel data-free compression framework for deraining networks. It is based on our observation that deep degradation representations can be clustered by degradation characteristics (types of rain) while independent of image content. Therefore, in our framework, we "dream" diverse in-distribution degraded images using a deep inversion paradigm, thus leveraging them to distill the pruned model. Specifically, we preserve the performance of the pruned model in a dual-branch way. In one branch, we invert the pre-trained model (teacher) to reconstruct the degraded inputs that resemble the original distribution and employ the orthogonal regularization for deep features to yield degradation diversity. In the other branch, the pruned model (student) is distilled to fit the teacher's original statistical modeling on these dreamed inputs. Further, an adaptive pruning scheme is proposed to determine the hierarchical sparsity, which alleviates the regression drift of the initial pruned model. Experiments on various deraining datasets demonstrate that our method can reduce about 40% FLOPs of the state-of-the-art models while maintaining comparable performance without original data.
-
Equivariance has been a long-standing concern in various fields ranging from computer vision to physical modeling. Most previous methods struggle with generality, simplicity, and expressiveness --- some are designed ad hoc for specific data types, some are too complex to be accessible, and some sacrifice flexible transformations. In this work, we propose a novel and simple framework to achieve equivariance for point cloud analysis based on the message passing (graph neural network) scheme. We find the equivariant property could be obtained by introducing an orientation for each point to decouple the relative position for each point from the global pose of the entire point cloud. Therefore, we extend current message passing networks with a module that learns orientations for each point. Before aggregating information from the neighbors of a point, the networks transforms the neighbors' coordinates based on the point's learned orientations. We provide formal proofs to show the equivariance of the proposed framework. Empirically, we demonstrate that our proposed method is competitive on both point cloud analysis and physical modeling tasks. Code is available at https://github.com/luost26/Equivariant-OrientedMP.
-
Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well understood, the field still lacks widely accepted best practices for replicating this success on other datasets. As a first step in this direction, we study contrastive self-supervised learning on four diverse large-scale datasets. By looking through the lenses of data quantity, data domain, data quality, and task granularity, we provide new insights into the necessary conditions for successful self-supervised learning. Our key findings include observations such as: (i) the benefit of additional pretraining data beyond 500k images is modest, (ii) adding pretraining images from another domain does not lead to more general representations, (iii) corrupted pretraining images have a disparate impact on supervised and self-supervised pretraining, and (iv) contrastive learning lags far behind supervised learning on fine-grained visual classification tasks.
-
We study the problem of developing autonomous agents that can follow human instructions to infer and perform a sequence of actions to complete the underlying task. Significant progress has been made in recent years, especially for tasks with short horizons. However, when it comes to long-horizon tasks with extended sequences of actions, an agent can easily ignore some instructions or get stuck in the middle of the long instructions and eventually fail the task. To address this challenge, we propose a model-agnostic milestone-based task tracker (M-Track) to guide the agent and monitor its progress. Specifically, we propose a milestone builder that tags the instructions with navigation and interaction milestones which the agent needs to complete step by step, and a milestone checker that systemically checks the agent's progress in its current milestone and determines when to proceed to the next. On the challenging ALFRED dataset, our M-Track leads to a notable 33% and 52% relative improvement in unseen success rate over two competitive base models.
-
The key towards learning informative node representations in graphs lies in how to gain contextual information from the neighbourhood. In this work, we present a simple-yet-effective self-supervised node representation learning strategy via directly maximizing the mutual information between the hidden representations of nodes and their neighbourhood, which can be theoretically justified by its link to graph smoothing. Following InfoNCE, our framework is optimized via a surrogate contrastive loss, where the positive selection underpins the quality and efficiency of representation learning. To this end, we propose a topology-aware positive sampling strategy, which samples positives from the neighbourhood by considering the structural dependencies between nodes and thus enables positive selection upfront. In the extreme case when only one positive is sampled, we fully avoid expensive neighbourhood aggregation. Our methods achieve promising performance on various node classification datasets. It is also worth mentioning by applying our loss function to MLP based node encoders, our methods can be orders of faster than existing solutions. Our codes and supplementary materials are available at https://github.com/dongwei156/n2n.
-
The construction of 3D point cloud datasets requires a great deal of human effort. Therefore, constructing a largescale 3D point clouds dataset is difficult. In order to remedy this issue, we propose a newly developed point cloud fractal database (PC-FractalDB), which is a novel family of formula-driven supervised learning inspired by fractal geometry encountered in natural 3D structures. Our research is based on the hypothesis that we could learn representations from more real-world 3D patterns than conventional 3D datasets by learning fractal geometry. We show how the PC-FractalDB facilitates solving several recent dataset-related problems in 3D scene understanding, such as 3D model collection and labor-intensive annotation. The experimental section shows how we achieved the performance rate of up to 61.9% and 59.0% for the ScanNetV2 and SUN RGB-D datasets, respectively, over the current highest scores obtained with the PointContrast, contrastive scene contexts (CSC), and RandomRooms. Moreover, the PC-FractalDB pre-trained model is especially effective in training with limited data. For example, in 10% of training data on ScanNetV2, the PC-FractalDB pre-trained VoteNet performs at 38.3%, which is +14.8% higher accuracy than CSC. Of particular note, we found that the proposed method achieves the highest results for 3D object detection pre-training in limited point cloud data.
-
A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene boundary from the long-term video is a challenging task, since a model must understand the storyline of the video to figure out where a scene starts and ends. To this end, we propose an effective Self-Supervised Learning (SSL) framework to learn better shot representations from unlabeled long-term videos. More specifically, we present an SSL scheme to achieve scene consistency, while exploring considerable data augmentation and shuffling methods to boost the model generalizability. Instead of explicitly learning the scene boundary features as in the previous methods, we introduce a vanilla temporal model with less inductive bias to verify the quality of the shot features. Our method achieves the state-of-the-art performance on the task of Video Scene Segmentation. Additionally, we suggest a more fair and reasonable benchmark to evaluate the performance of Video Scene Segmentation methods. The code is made available.
-
Correctly classifying adversarial examples is an essential but challenging requirement for safely deploying machine learning models. As reported in RobustBench, even the state-of-the-art adversarially trained models struggle to exceed 67% robust test accuracy on CIFAR-10, which is far from practical. A complementary way towards robustness is to introduce a rejection option, allowing the model to not return predictions on uncertain inputs, where confidence is a commonly used certainty proxy. Along with this routine, we find that confidence and a rectified confidence (R-Con) can form two coupled rejection metrics, which could provably distinguish wrongly classified inputs from correctly classified ones. This intriguing property sheds light on using coupling strategies to better detect and reject adversarial examples. We evaluate our rectified rejection (RR) module on CIFAR-10, CIFAR-10-C, and CIFAR-100 under several attacks including adaptive ones, and demonstrate that the RR module is compatible with different adversarial training frameworks on improving robustness, with little extra computation.
-
Explaining the generalization characteristics of deep learning is an emerging topic in advanced machine learning. There are several unanswered questions about how learning under stochastic optimization really works and why certain strategies are better than others. In this paper, we address the following question: can we probe intermediate layers of a deep neural network to identify and quantify the learning quality of each layer? With this question in mind, we propose new explainability metrics that measure the redundant information in a network's layers using a low-rank factorization framework and quantify a complexity measure that is highly correlated with the generalization performance of a given optimizer, network, and dataset. We subsequently exploit these metrics to augment the Stochastic Gradient Descent (SGD) optimizer by adaptively adjusting the learning rate in each layer to improve in generalization performance. Our augmented SGD -- dubbed RMSGD -- introduces minimal computational overhead compared to SOTA methods and outperforms them by exhibiting strong generalization characteristics across application, architecture, and dataset.
-
One major challenge for semantic segmentation in real-world scenarios is only limited pixel-level labels available due to high expense of human labor though a vast volume of video data is provided. Existing semi-supervised methods attempt to exploit unlabeled data in model training, but they just regard video as a set of independent images. To better explore semi-supervised segmentation problem with video data, we formulate a semi-supervised video semantic segmentation task in this paper. For this task, we observe that the overfitting is surprisingly severe between labeled and unlabeled frames within a training video although they are very similar in style and contents. This is called inner-video overfitting, and it would actually lead to inferior performance. To tackle this issue, we propose a novel inter-frame feature reconstruction (IFR) technique to leverage the ground-truth labels to supervise the model training on unlabeled frames. IFR is essentially to utilize the internal relevance of different frames within a video. During training, IFR would enforce the feature distributions between labeled and unlabeled frames to be narrowed. Consequently, the inner-video overfitting issue can be effectively alleviated. We conduct extensive experiments on Cityscapes and CamVid, and the results demonstrate the superiority of our proposed method to previous state-of-the-art methods. The code is available at https://github.com/jfzhuang/IFR.
-
In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formalize the requirements for each component.We instantiate our general differentiable renderer, which generalizes existing differentiable renderers like SoftRas and DIB-R, with an array of different smoothing distributions to cover a large spectrum of reasonable settings. We evaluate an array of differentiable renderer instantiations on the popular ShapeNet 3D reconstruction benchmark and analyze the implications of our results. Surprisingly, the simple uniform distribution yields the best overall results when averaged over 13 classes; in general, however, the optimal choice of distribution heavily depends on the task.
-
Neural implicit surfaces have become an important technique for multi-view 3D reconstruction but their accuracy remains limited. In this paper, we argue that this comes from the difficulty to learn and render high frequency textures with neural networks. We thus propose to add to the standard neural rendering optimization a direct photo-consistency term across the different views. Intuitively, we optimize the implicit geometry so that it warps views on each other in a consistent way. We demonstrate that two elements are key to the success of such an approach: (i) warping entire patches, using the predicted occupancy and normals of the 3D points along each ray, and measuring their similarity with a robust structural similarity (SSIM); (ii) handling visibility and occlusion in such a way that incorrect warps are not given too much importance while encouraging a reconstruction as complete as possible. We evaluate our approach, dubbed NeuralWarp, on the standard DTU and EPFL benchmarks and show it outperforms state of the art unsupervised implicit surfaces reconstructions by over 20% on both datasets.
-
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings. However, most existing approaches utilize the position embeddings to incorporate the sequence information, neglecting the noisy improper reading order obtained by OCR tools. In this paper, we propose a robust layout-aware multimodal network named XYLayoutLM to capture and leverage rich layout information from proper reading orders produced by our Augmented XY Cut. Moreover, a Dilated Conditional Position Encoding module is proposed to deal with the input sequence of variable lengths, and it additionally extracts local layout information from both textual and visual modalities while generating position embeddings. Experiment results show that our XYLayoutLM achieves competitive results on document understanding tasks.
-
Amodal Segmentation Through Out-of-Task and Out-of-Distribution Generalization With a Bayesian Model
Amodal completion is a visual task that humans perform easily but which is difficult for computer vision algorithms. The aim is to segment those object boundaries which are occluded and hence invisible. This task is particularly challenging for deep neural networks because data is difficult to obtain and annotate. Therefore, we formulate amodal segmentation as an out-of-task and out-of-distribution generalization problem. Specifically, we replace the fully connected classifier in neural networks with a Bayesian generative model of the neural network features. The model is trained from non-occluded images using bounding box annotations and class labels only, but is applied to generalize out-of-task to object segmentation and to generalize out-of-distribution to segment occluded objects. We demonstrate how such Bayesian models can naturally generalize beyond the training task labels when they learn a prior that models the object's background context and shape. Moreover, by leveraging an outlier process, Bayesian models can further generalize out-of-distribution to segment partially occluded objects and to predict their amodal object boundaries. Our algorithm outperforms alternative methods that use the same supervision by a large margin, and even outperforms methods where annotated amodal segmentations are used during training, when the amount of occlusion is large. Code is publically available at https://github.com/anonymous-submission-vision/Amodal-Bayesian.
-
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets. Generally, more accurate models on the "upstream" dataset tend to provide better transfer accuracy "downstream". In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned--that is, compressed by sparsifiying their connections. We consider transfer using unstructured pruned models obtained by applying several state-of-the-art pruning methods, including magnitude-based, second-order, re-growth, lottery-ticket, and regularization approaches, in the context of twelve standard transfer tasks. In a nutshell, our study shows that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities, and, while doing so, can lead to significant inference and even training speedups. At the same time, we observe and analyze significant differences in the behaviour of different pruning methods. The code is available at: https://github.com/IST-DASLab/sparse-imagenet-transfer.
-
Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the rationales behind the decisions. As a result, they commonly take advantage of spurious biases instead of actually reasoning on the visual-textual data, and have yet developed the capability to explain their decision making by considering key information from both modalities. This paper aims to close the gap from three distinct perspectives: first, we define a new type of multi-modal explanations that explain the decisions by progressively traversing the reasoning process and grounding keywords in the images. We develop a functional program to sequentially execute different reasoning steps and construct a new dataset with 1,040,830 multi-modal explanations. Second, we identify the critical need to tightly couple important components across the visual and textual modalities for explaining the decisions, and propose a novel explanation generation method that explicitly models the pairwise correspondence between words and regions of interest. It improves the visual grounding capability by a considerable margin, resulting in enhanced interpretability and reasoning performance. Finally, with our new data and method, we perform extensive analyses to study the effectiveness of our explanation under different settings, including multi-task learning and transfer learning. Our code and data are available at https://github.com/szzexpoi/rex
-
Iterative denoising-based generation, also known as denoising diffusion models, has recently been shown to be comparable in quality to other classes of generative models, and even surpass them. Including, in particular, Generative Adversarial Networks, which are currently the state of the art in many sub-tasks of image generation. However, a major drawback of this method is that it requires hundreds of iterations to produce a competitive result. Recent works have proposed solutions that allow for faster generation with fewer iterations, but the image quality gradually deteriorates with increasingly fewer iterations being applied during generation. In this paper, we reveal some of the causes that affect the generation quality of diffusion models, especially when sampling with few iterations, and come up with a simple, yet effective, solution to mitigate them. We consider two opposite equations for the iterative denoising, the first predicts the applied noise, and the second predicts the image directly. Our solution takes the two options and learns to dynamically alternate between them through the denoising process. Our proposed solution is general and can be applied to any existing diffusion model. As we show, when applied to various SOTA architectures, our solution immediately improves their generation quality, with negligible added complexity and parameters. We experiment on multiple datasets and configurations and run an extensive ablation study to support these findings.
-
Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for robustness and fairness, e.g., inability to synthesize the face images of underrepresented demographic groups. In this paper, we introduce a new framework, StyleT2I, to improve the compositionality of text-to-image synthesis. Specifically, we propose a CLIP-guided Contrastive Loss to better distinguish different compositions among different sentences. To further improve the compositionality, we design a novel Semantic Matching Loss and a Spatial Constraint to identify attributes' latent directions for intended spatial region manipulations, leading to better disentangled latent representations of attributes. Based on the identified latent directions of attributes, we propose Compositional Attribute Adjustment to adjust the latent code, resulting in better compositionality of image synthesis. In addition, we leverage the l_2-norm regularization of identified latent directions (norm penalty) to strike a nice balance between image-text alignment and image fidelity. In the experiments, we devise a new dataset split and an evaluation metric to evaluate the compositionality of text-to-image synthesis models. The results show that StyleT2I outperforms previous approaches in terms of the consistency between the input text and synthesized images and achieves higher fidelity.
-
Physical products are often complex assemblies combining a multitude of 3D parts modeled in computer-aided design (CAD) software. CAD designers build up these assemblies by aligning individual parts to one another using constraints called joints. In this paper we introduce JoinABLe, a learning-based method that assembles parts together to form joints. JoinABLe uses the weak supervision available in standard parametric CAD files without the help of object class labels or human guidance. Our results show that by making network predictions over a graph representation of solid models we can outperform multiple baseline methods with an accuracy (79.53%) that approaches human performance (80%). Finally, to support future research we release the AssemblyJoint dataset, containing assemblies with rich information on joints, contact surfaces, holes, and the underlying assembly graph structure.
-
While neural representations for static 3D shapes are widely studied, representations for deformable surfaces are limited to be template-dependent or to lack efficiency. We introduce Canonical Deformation Coordinate Space (CaDeX), a unified representation of both shape and nonrigid motion. Our key insight is the factorization of the deformation between frames by continuous bijective canonical maps (homeomorphisms) and their inverses that go through a learned canonical shape. Our novel deformation representation and its implementation are simple, efficient, and guarantee cycle consistency, topology preservation, and, if needed, volume conservation. Our modelling of the learned canonical shapes provides a flexible and stable space for shape prior learning. We demonstrate state-of-the-art performance in modelling a wide range of deformable geometries: human bodies, animal bodies, and articulated objects.
-
3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations with an additional Multi-Layer-Perceptron network. Both their offset and orientation predictions are not accurate due to the fundamental difficulty in rotation classification. In the work, we disentangle the direct offset into Local Canonical Coordinates (LCC), box scales and box orientations. Only LCC and box scales are regressed, while box orientations are generated by a canonical voting scheme. Finally, an LCC-aware back-projection checking algorithm iteratively cuts out bounding boxes from the generated vote maps, with the elimination of false positives. Our model achieves state-of-the-art performance on three standard real-world benchmarks: ScanNet, SceneNN and SUN RGB-D. Our code is available on https://github.com/qq456cvb/CanonicalVoting.
-
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks. The V-Doc supports generating and using both extractive and abstractive question-answer pairs using documents images. The extractive QA selects a subset of tokens or phrases from the document contents to predict the answers, while the abstractive QA recognises the language in the content and generates the answer based on the trained model. Both aspects are crucial to understanding the documents, especially in an image format. We include a detailed scenario of question generation for the abstractive QA task. V-Doc supports a wide range of datasets and models, and is highly extensible through a declarative, framework-agnostic platform.
-
The best performing learning algorithms devised for event cameras work by first converting events into dense representations that are then processed using standard CNNs. However, these steps discard both the sparsity and high temporal resolution of events, leading to high computational burden and latency. For this reason, recent works have adopted Graph Neural Networks (GNNs), which process events as "static" spatio-temporal graphs, which are inherently "sparse". We take this trend one step further by introducing Asynchronous, Event-based Graph Neural Networks (AEGNNs), a novel event-processing paradigm that generalizes standard GNNs to process events as "evolving" spatio-temporal graphs. AEGNNs follow efficient update rules that restrict recomputation of network activations only to the nodes affected by each new event, thereby significantly reducing both computation and latency for event-by-event processing. AEGNNs are easily trained on synchronous inputs and can be converted to efficient, "asynchronous" networks at test time. We thoroughly validate our method on object classification and detection tasks, where we show an up to a 200-fold reduction in computational complexity (FLOPs), with similar or even better performance than state-of-the-art asynchronous methods. This reduction in computation directly translates to an 8-fold reduction in computational latency when compared to standard GNNs, which opens the door to low-latency event-based processing.
-
Personalized Federated Learning (pFL) not only can capture the common priors from broad range of distributed data, but also support customized models for heterogeneous clients. Researches over the past few years have applied the weighted aggregation manner to produce personalized models, where the weights are determined by calibrating the distance of the entire model parameters or loss values, and have yet to consider the layer-level impacts to the aggregation process, leading to lagged model convergence and inadequate personalization over non-IID datasets. In this paper, we propose a novel pFL training framework dubbed Layer-wised Personalized Federated learning (pFedLA) that can discern the importance of each layer from different clients, and thus is able to optimize the personalized model aggregation for clients with heterogeneous data. Specifically, we employ a dedicated hypernetwork per client on the server side, which is trained to identify the mutual contribution factors at layer granularity. Meanwhile, a parameterized mechanism is introduced to update the layer-wised aggregation weights to progressively exploit the inter-user similarity and realize accurate model personalization. Extensive experiments are conducted over different models and learning tasks, and we show that the proposed methods achieve significantly higher performance than state-of-the-art pFL methods.
-
We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of any pre-trained deep generative network (DGN). Leveraging the fact that DGNs are, or can be approximated by, continuous piecewise affine splines, we derive the analytical DGN output space distribution as a function of the product of the DGN's Jacobian singular values raised to a power rho. We dub rho the polarity parameter and prove that rho focuses the DGN sampling on the modes (rho < 0) or anti-modes (rho > 0) of the DGN output space probability distribution. We demonstrate that nonzero polarity values achieve a better precision-recall (quality-diversity) Pareto frontier than standard methods, such as truncation, for a number of state-of-the-art DGNs. We also present quantitative and qualitative results on the improvement of overall generation quality (e.g., in terms of the Frechet Inception Distance) for a number of state-of-the-art DGNs, including StyleGAN3, BigGAN-deep, NVAE, for different conditional and unconditional image generation tasks. In particular, Polarity Sampling redefines the state-of-the-art for StyleGAN2 on the FFHQ Dataset to FID 2.57, StyleGAN2 on the LSUN Car Dataset to FID 2.27 and StyleGAN3 on the AFHQv2 Dataset to FID 3.95. Colab Demo: bit.ly/polarity-samp
-
In this study, we present a colorization network that generates flat-color icons according to given sketches and semantic colorization styles. Specifically, our network contains a style-structure disentangled colorization module and a normalizing flow. The colorization module transforms a paired sketch image and style image into a flat-color icon. To enhance network generalization and the quality of icons, we present a pixel-wise decoder, a global style code, and a contour loss to reduce color gradients at flat regions and increase color discontinuity at boundaries. The normalizing flow maps Gaussian vectors to diverse style codes conditioned on the given semantic colorization label. This conditional sampling enables users to control attributes and obtain diverse colorization results. Compared to previous colorization methods built upon conditional generative adversarial networks, our approach enjoys the advantages of both high image quality and diversity. To evaluate its effectiveness, we compared the flat-color icons generated by our approach and recent colorization and image-to-image translation methods on various conditions. Experiment results verify that our method outperforms state-of-the-arts qualitatively and quantitatively.
-
Recently, by introducing large-scale dataset and strong transformer network, video-language pre-training has shown great success especially for retrieval. Yet, existing video-language transformer models do not explicitly fine-grained semantic align. In this work, we present Object-aware Transformers, an object-centric approach that extends video-language transformer to incorporate object representations. The key idea is to leverage the bounding boxes and object tags to guide the training process. We evaluate our model on three standard sub-tasks of video-text matching on four widely used benchmarks. We also provide deep analysis and detailed ablation about the proposed method. We show clear improvement in performance across all tasks and datasets considered, demonstrating the value of a model that incorporates object representations into a video-language architecture. The code has been released in https://github.com/FingerRec/OA-Transformer.
-
Rotated object detection is a challenging issue in computer vision field. Inadequate rotated representation and the confusion of parametric regression have been the bottleneck for high performance rotated detection. In this paper, we propose an orientation-sensitive keypoint based rotated detector OSKDet. First, we adopt a set of keypoints to represent the target and predict the keypoint heatmap on ROI to get the rotated box. By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for rotated representation, which improves the localization accuracy and acquires high quality detection results. Second, we explore a new unordered keypoint representation paradigm, which could avoid the confusion of keypoint regression caused by rule based ordering. Furthermore, we propose a localization quality uncertainty module to better predict the classification score by the distribution uncertainty of keypoints heatmap. Experimental results on several public benchmarks show the state-of-the-art performance of OSKDet. Specifically, we achieve an AP of 80.91% on DOTA, 89.98% on HRSC2016, 97.27% on UCAS-AOD, and a F-measure of 92.18% on ICDAR2015, 81.43% on ICDAR2017, respectively.
-
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low resolution in consideration of computational cost. In this paper, we present a novel transformer-based model for large hole inpainting, which unifies the merits of transformers and convolutions to efficiently process high-resolution images. We carefully design each component of our framework to guarantee the high fidelity and diversity of recovered images. Specifically, we customize an inpainting-oriented transformer block, where the attention module aggregates non-local information only from partial valid tokens, indicated by a dynamic mask. Extensive experiments demonstrate the state-of-the-art performance of the new model on multiple benchmark datasets. Code is released at https://github.com/fenglinglwb/MAT.
-
This paper investigates the geometric consistency for monocular 3D object detection, which suffers from the ill-posed depth estimation. We first conduct a thorough analysis to reveal how existing methods fail to consistently localize objects when different geometric shifts occur. In particular, we design a series of geometric manipulations to diagnose existing detectors and then illustrate their vulnerability to consistently associate the depth with object apparent sizes and positions. To alleviate this issue, we propose four geometry-aware data augmentation approaches to enhance the geometric consistency of the detectors. We first modify some commonly used data augmentation methods for 2D images so that they can maintain geometric consistency in 3D spaces. We demonstrate such modifications are important. In addition, we propose a 3D-specific image perturbation method that employs the camera movement. During the augmentation process, the camera system with the corresponding image is manipulated, while the geometric visual cues for depth recovery are preserved. We show that by using the geometric consistency constraints, the proposed augmentation techniques lead to improvements on the KITTI and nuScenes monocular 3D detection benchmarks with state-of-the-art results. In addition, we demonstrate that the augmentation methods are well suited for semi-supervised training and cross-dataset generalization.
-
Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture the relationships between nodes in the graph, we exploit the multi-head attention mechanism to compute a multi-head potential function, which is fed to the networks to output an optimized depth map. Then we build a bottom-up-top-down structure, where this neural window FC-CRFs module serves as the decoder, and a vision transformer serves as the encoder. The experiments demonstrate that our method significantly improves the performance across all metrics on both the KITTI and NYUv2 datasets, compared to previous methods. Furthermore, the proposed method can be directly applied to panorama images and outperforms all previous panorama methods on the MatterPort3D dataset.
-
Transformers have gained much attention by outperforming convolutional neural networks in many 2D vision tasks. However, they are known to have generalization problems and rely on massive-scale pre-training and sophisticated training techniques. When applying to 3D tasks, the irregular data structure and limited data scale add to the difficulty of transformer's application. We propose Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers. On the one hand, we propose the codebook-based attention that projects an attention space into its subspace represented by the combination of "prototypes" in a learnable codebook. It regularizes attention learning and improves generalization. On the other hand, we propose geometry-aware self-attention that utilizes geometric information (geometric pattern, density) to guide attention learning. CodedVTR could be embedded into existing sparse convolution-based methods, and bring consistent performance improvements for indoor and outdoor 3D semantic segmentation tasks.
-
This paper presents a simple and effective solution to the longstanding classical multi-view photometric stereo (MVPS) problem. It is well-known that photometric stereo (PS) is excellent at recovering high-frequency surface details, whereas multi-view stereo (MVS) can help remove the low-frequency distortion due to PS and retain the global geometry of the shape. This paper proposes an approach that can effectively utilize such complementary strengths of PS and MVS. Our key idea is to combine them suitably while considering the per-pixel uncertainty of their estimates. To this end, we estimate per-pixel surface normals and depth using an uncertainty-aware deep-PS network and deep-MVS network, respectively. Uncertainty modeling helps select reliable surface normal and depth estimates at each pixel which then act as a true representative of the dense surface geometry. At each pixel, our approach either selects or discards deep-PS and deep-MVS network prediction depending on the prediction uncertainty measure. For dense, detailed, and precise inference of the object's surface profile, we propose to learn the implicit neural shape representation via a multilayer perceptron (MLP). Our approach encourages the MLP to converge to a natural zero-level set surface using the confident prediction from deep-PS and deep-MVS networks, providing superior dense surface reconstruction. Extensive experiments on the DiLiGenT-MV benchmark dataset show that our method provides high-quality shape recovery with a much lower memory footprint while outperforming almost all of the existing approaches.
-
In this paper, we explore a new type of extrinsic method to directly align two geometric shapes with point-to-point correspondences in ambient space by recovering a deformation, which allows more continuous and smooth maps to be obtained. Specifically, the classic coherent point drift is revisited and generalizations have been proposed. First, by observing that the deformation model is essentially defined with respect to Euclidean space, we generalize the kernel method to non-Euclidean domains. This generally leads to better results for processing shapes, which are known as two-dimensional manifolds. Second, a generalized probabilistic model is proposed to address the sensibility of coherent point drift method to local optima. Instead of directly optimizing over the objective of coherent point drift, the new model allows to focus on a group of most confident ones, thus improves the robustness of the registration system. Experiments are conducted on multiple public datasets with comparison to state-of-the-art competitors, demonstrating the superiority of our method which is both flexible and efficient to improve the matching accuracy due to our extrinsic alignment objective in ambient space.
-
Existing person re-identification (ReID) methods typically directly load the pre-trained ImageNet weights for initialization. However, as a fine-grained classification task, ReID is more challenging and exists a large domain gap between ImageNet classification. Inspired by the great success of self-supervised representation learning with contrastive objectives, in this paper, we design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID. During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images. (2) the fine-grained local features of person images are not fully-explored. Therefore, we introduce an (I^2-)regularization in the UP-ReID, which is instantiated as two constraints coming from global image aspect and local patch aspect: a global consistency is enforced between augmented and original person images to increase robustness to augmentation, while an intrinsic contrastive constraint among local patches of each image is employed to fully explore the local discriminative clues. Extensive experiments on multiple popular Re-ID datasets, including PersonX, Market1501, CUHK03, and MSMT17, demonstrate that our UP-ReID pre-trained model can significantly benefit the downstream ReID fine-tuning and achieve state-of-the-art performance.
-
Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between unimodal video and text features. Besides, learning fine-grained visual-language alignment usually requires off-the-shelf object detectors to provide object information, which is bottlenecked by the detector's limited vocabulary and expensive computation cost. We propose Align and Prompt: an efficient and effective video-and-language pre-training framework with better cross-modal alignment. First, we introduce a video-text contrastive (VTC) loss to align unimodal video-text features at the instance level, which eases the modeling of cross-modal interactions. Then, we propose a new visually-grounded pre-training task, prompting entity modeling (PEM), which aims to learn fine-grained region-entity alignment. To achieve this, we first introduce an entity prompter module, which is trained with VTC to produce the similarity between a video crop and text prompts instantiated with entity names. The PEM task then asks the model to predict the entity pseudo-labels (i.e normalized similarity scores) for randomly-selected video crops. The resulting pre-trained model achieves state-of-the-art performance on both text-video retrieval and videoQA, outperforming prior work by a substantial margin. Our code and pre-trained models are available at https://github.com/salesforce/ALPRO.
-
3D point cloud understanding is an important component in autonomous driving and robotics. In this paper, we present a novel Embedding-Querying paradigm (EQ- Paradigm) for 3D understanding tasks including detection, segmentation and classification. EQ-Paradigm is a unified paradigm that enables combination of existing 3D backbone architectures with different task heads. Under the EQ- Paradigm, the input is first encoded in the embedding stage with an arbitrary feature extraction architecture, which is independent of tasks and heads. Then, the querying stage enables the encoded features for diverse task heads. This is achieved by introducing an intermediate representation, i.e., Q-representation, in the querying stage to bridge the embedding stage and task heads. We design a novel Q-Net as the querying stage network. Extensive experimental results on various 3D tasks show that EQ-Paradigm in tandem with Q-Net is a general and effective pipeline, which enables flexible collaboration of backbones and heads. It further boosts performance of state-of-the-art methods.
-
In this paper, we present a framework for reading analog clocks in natural images or videos. Specifically, we make the following contributions: First, we create a scalable pipeline for generating synthetic clocks, significantly reducing the requirements for the labour-intensive annotations; Second, we introduce a clock recognition architecture based on spatial transformer networks (STN), which is trained end-to-end for clock alignment and recognition. We show that the model trained on the proposed synthetic dataset generalises towards real clocks with good accuracy, advocating a Sim2Real training regime; Third, to further reduce the gap between simulation and real data, we leverage the special property of "time", i.e.uniformity, to generate reliable pseudo-labels on real unlabelled clock videos, and show that training on these videos offers further improvements while still requiring zero manual annotations. Lastly, we introduce three benchmark datasets based on COCO, Open Images, and The Clock movie, with full annotations for time, accurate to the minute.
-
Transformers have offered a new methodology of designing neural networks for visual recognition. Compared to convolutional networks, Transformers enjoy the ability of referring to global features at each stage, yet the attention module brings higher computational overhead that obstructs the application of Transformers to process high-resolution visual data. This paper aims to alleviate the conflict between efficiency and flexibility, for which we propose a specialized token for each region that serves as a messenger (MSG). Hence, by manipulating these MSG tokens, one can flexibly exchange visual information across regions and the computational complexity is reduced. We then integrate the MSG token into a multi-scale architecture named MSG-Transformer. In standard image classification and object detection, MSG-Transformer achieves competitive performance and the inference on both GPU and CPU is accelerated. Code is available at https://github.com/hustvl/MSG-Transformer.
-
Profiting from large-scale training datasets, advances in neural architecture design and efficient inference, joint embeddings have become the dominant approach for tackling cross-modal retrieval. In this work we first show that, despite their effectiveness, state-of-the-art joint embeddings suffer significantly from the longstanding "hubness problem" in which a small number of gallery embeddings form the nearest neighbours of many queries. Drawing inspiration from the NLP literature, we formulate a simple but effective framework called Querybank Normalisation (QB-Norm) that re-normalises query similarities to account for hubs in the embedding space. QB-Norm improves retrieval performance without requiring retraining. Differently from prior work, we show that QB-Norm works effectively without concurrent access to any test set queries. Within the QB-Norm framework, we also propose a novel similarity normalisation method, the Dynamic Inverted Softmax, that is significantly more robust than existing approaches. We showcase QB-Norm across a range of cross modal retrieval models and benchmarks where it consistently enhances strong baselines beyond the state of the art. Code is available at https://vladbogo.github.io/QB-Norm/.
-
Contrastive learning (or its variants) has recently become a promising direction in the self-supervised learning domain, achieving similar performance as supervised learning with minimum fine-tuning. Despite the labeling efficiency, wide and large networks are required to achieve high accuracy, which incurs a high amount of computation and hinders the pragmatic merit of self-supervised learning. To effectively reduce the computation of insignificant features or channels, recent dynamic pruning algorithms for supervised learning employed auxiliary salience predictors. However, we found that such salience predictors cannot be easily trained when they are naively applied to contrastive learning from scratch. To address this issue, we propose contrastive dual gating(CDG), a novel dynamic pruning algorithm that skips the uninformative features during contrastive learning without hurting the trainability of the networks. We demonstrate the superiority of CDG with ResNet models for CIFAR-10, CIFAR-100, and ImageNet-100 datasets. Compared to our implementations of state-of-the-art dynamic pruning algorithms for self-supervised learning, CDG achieves up to 15% accuracy improvement for CIFAR-10 dataset with higher computation reduction.
-
This paper tackles a new photometric stereo task, named universal photometric stereo. Unlike existing tasks that assumed specific physical lighting models; hence, drastically limited their usability, a solution algorithm of this task is supposed to work for objects with diverse shapes and materials under arbitrary lighting variations without assuming any specific models. To solve this extremely challenging task, we present a purely data-driven method, which eliminates the prior assumption of lighting by replacing the recovery of physical lighting parameters with the extraction of the generic lighting representation, named global lighting contexts. We use them like lighting parameters in a calibrated photometric stereo network to recover surface normal vectors pixelwisely. To adapt our network to a wide variety of shapes, materials and lightings, it is trained on a new synthetic dataset which simulates the appearance of objects in the wild. Our method is compared with other state-of-the-art uncalibrated photometric stereo methods on our test data to demonstrate the significance of our method.
-
Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information. Such approach withholds MLPs from getting comparable performance with their transformer-based counterparts and prevents them from becoming a general backbone for computer vision. This paper presents Hire-MLP, a simple yet competitive vision MLP architecture via Hierarchical rearrangement, which contains two levels of rearrangements. Specifically, the inner-region rearrangement is proposed to capture local information inside a spatial region, and the cross-region rearrangement is proposed to enable information communication between different regions and capture global context by circularly shifting all tokens along spatial directions. Extensive experiments demonstrate the effectiveness of Hire-MLP as a versatile backbone for various vision tasks. In particular, Hire-MLP achieves competitive results on image classification, object detection and semantic segmentation tasks, e.g., 83.8% top-1 accuracy on ImageNet, 51.7% box AP and 44.8% mask AP on COCO val2017, and 49.9% mIoU on ADE20K, surpassing previous transformer-based and MLP-based models with better trade-off for accuracy and throughput.
-
In this paper, we propose a novel monocular ray-based 3D (Ray3D) absolute human pose estimation with calibrated camera. Accurate and generalizable absolute 3D human pose estimation from monocular 2D pose input is an ill-posed problem. To address this challenge, we convert the input from pixel space to 3D normalized rays. This conversion makes our approach robust to camera intrinsic parameter changes. To deal with the in-the-wild camera extrinsic parameter variations, Ray3D explicitly takes the camera extrinsic parameters as an input and jointly models the distribution between the 3D pose rays and camera extrinsic parameters. This novel network design is the key to the outstanding generalizability of Ray3D approach. To have a comprehensive understanding of how the camera intrinsic and extrinsic parameter variations affect the accuracy of absolute 3D key-point localization, we conduct in-depth systematic experiments on three single person 3D benchmarks as well as one synthetic benchmark. These experiments demonstrate that our method significantly outperforms existing state-of-the-art models. Our code and the synthetic dataset are available at https://github.com/YxZhxn/Ray3D.
-
Top-down methods for monocular human mesh recovery have two stages: (1) detect human bounding boxes; (2) treat each bounding box as an independent single-human mesh recovery task. Unfortunately, the single-human assumption does not hold in images with multi-human occlusion and crowding. Consequently, top-down methods have difficulties in recovering accurate 3D human meshes under severe person-person occlusion. To address this, we present Occluded Human Mesh Recovery (OCHMR) - a novel top-down mesh recovery approach that incorporates image spatial context to overcome the limitations of the single-human assumption. The approach is conceptually simple and can be applied to any existing top-down architecture. Along with the input image, we condition the top-down model on spatial context from the image in the form of body-center heatmaps. To reason from the predicted body centermaps, we introduce Contextual Normalization (CoNorm) blocks to adaptively modulate intermediate features of the top-down model. The contextual conditioning helps our model disambiguate between two severely overlapping human bounding-boxes, making it robust to multi-person occlusion. Compared with state-of-the-art methods, OCHMR achieves superior performance on challenging multi-person benchmarks like 3DPW, CrowdPose, and OCHuman. Specifically, our proposed contextual reasoning architecture applied to the SPIN model with ResNet-50 backbone results in 75.2 PMPJPE on 3DPW-PC, 23.6 AP on CrowdPose, and 37.7 AP on OCHuman datasets, a significant improvement of 6.9 mm, 6.4 AP, and 20.8 AP respectively over the baseline. Code and models will be released.
-
Multi-object tracking in unmanned aerial vehicle (UAV) videos is an important vision task and can be applied in a wide range of applications. However, conventional multi-object trackers do not work well on UAV videos due to the challenging factors of irregular motion caused by moving camera and view change in 3D directions. In this paper, we propose a UAVMOT network specially for multi-object tracking in UAV views. The UAVMOT introduces an ID feature update module to enhance the object's feature association. To better handle the complex motions under UAV views, we develop an adaptive motion filter module. In addition, a gradient balanced focal loss is used to tackle the imbalance categories and small objects detection problem. Experimental results on the VisDrone2019 and UAVDT datasets demonstrate that the proposed UAVMOT achieves considerable improvement against the state-of-the-art tracking methods on UAV videos.
-
Weakly-supervised temporal action localization aims to recognize and localize action segments in untrimmed videos given only video-level action labels for training. Without the boundary information of action segments, existing methods mostly rely on multiple instance learning (MIL), where the predictions of unlabeled instances (i.e., video snippets) are supervised by classifying labeled bags (i.e., untrimmed videos). However, this formulation typically treats snippets in a video as independent instances, ignoring the underlying temporal structures within and across action segments. To address this problem, we propose \system, a novel WTAL framework that enables explicit, action-aware segment modeling beyond standard MIL-based methods. Our framework entails three segment-centric components: (i) dynamic segment sampling for compensating the contribution of short actions; (ii) intra- and inter-segment attention for modeling action dynamics and capturing temporal dependencies; (iii) pseudo instance-level supervision for improving action boundary prediction. Furthermore, a multi-step refinement strategy is proposed to progressively improve action proposals along the model training process. Extensive experiments on THUMOS-14 and ActivityNet-v1.3 demonstrate the effectiveness of our approach, establishing new state of the art on both datasets. The code and models are publicly available at https://github.com/boheumd/ASM-Loc.
-
A complex action consists of a sequence of atomic actions that interact with each other over a relatively long period of time. This paper introduces a probabilistic model named Uncertainty-Guided Probabilistic Transformer (UGPT) for complex action recognition. The self-attention mechanism of a Transformer is used to capture the complex and long-term dynamics of the complex actions. By explicitly modeling the distribution of the attention scores, we extend the deterministic Transformer to a probabilistic Transformer in order to quantify the uncertainty of the prediction. The model prediction uncertainty is used to improve both training and inference. Specifically, we propose a novel training strategy by introducing a majority model and a minority model based on the epistemic uncertainty. During the inference, the prediction is jointly made by both models through a dynamic fusion strategy. Our method is validated on the benchmark datasets, including Breakfast Actions, MultiTHUMOS, and Charades. The experiment results show that our model achieves the state-of-the-art performance under both sufficient and insufficient data.
-
We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small kernels could be a more powerful paradigm. We suggested five guidelines, e.g., applying re-parameterized large depth-wise convolutions, to design efficient high-performance large-kernel CNNs. Following the guidelines, we propose RepLKNet, a pure CNN architecture whose kernel size is as large as 31x31, in contrast to commonly used 3x3. RepLKNet greatly closes the performance gap between CNNs and ViTs, e.g., achieving comparable or superior results than Swin Transformer on ImageNet and a few typical downstream tasks, with lower latency. RepLKNet also shows nice scalability to big data and large models, obtaining 87.8% top-1 accuracy on ImageNet and 56.0% mIoU on ADE20K, which is very competitive among the state-of-the-arts with similar model sizes. Our study further reveals that, in contrast to small-kernel CNNs, large-kernel CNNs have much larger effective receptive fields and higher shape bias rather than texture bias. Code & models at https://github.com/megvii-research/RepLKNet.
-
Current methods of multi-person pose estimation typically treat the localization and association of body joints separately. In this paper, we propose the first fully end-to-end multi-person Pose Estimation framework with TRansformers, termed PETR. Our method views pose estimation as a hierarchical set prediction problem and effectively removes the need for many hand-crafted modules like RoI cropping, NMS and grouping post-processing. In PETR, multiple pose queries are learned to directly reason a set of full-body poses. Then a joint decoder is utilized to further refine the poses by exploring the kinematic relations between body joints. With the attention mechanism, the proposed method is able to adaptively attend to the features most relevant to target keypoints, which largely overcomes the feature misalignment difficulty in pose estimation and improves the performance considerably. Extensive experiments on the MS COCO and CrowdPose benchmarks show that PETR plays favorably against state-of-the-art approaches in terms of both accuracy and efficiency. The code and models are available at https://github.com/hikvision-research/opera.
-
Despite recent success in incorporating learning into point cloud registration, many works focus on learning feature descriptors and continue to rely on nearest-neighbor feature matching and outlier filtering through RANSAC to obtain the final set of correspondences for pose estimation. In this work, we conjecture that attention mechanisms can replace the role of explicit feature matching and RANSAC, and thus propose an end-to-end framework to directly predict the final set of correspondences. We use a network architecture consisting primarily of transformer layers containing self and cross attentions, and train it to predict the probability each point lies in the overlapping region and its corresponding position in the other point cloud. The required rigid transformation can then be estimated directly from the predicted correspondences without further post-processing. Despite its simplicity, our approach achieves state-of-the-art performance on 3DMatch and ModelNet benchmarks. Our source code can be found at https://github.com/yewzijian/RegTR.
-
This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view images. Many previous works have shown impressive reconstruction results on textured objects, but they still have difficulty in handling low-textured planar regions, which are common in indoor scenes. An approach to solving this issue is to incorporate planer constraints into the depth map estimation in multi-view stereo-based methods, but the per-view plane estimation and depth optimization lack both efficiency and multi-view consistency. In this work, we show that the planar constraints can be conveniently integrated into the recent implicit neural representation-based reconstruction methods. Specifically, we use an MLP network to represent the signed distance function as the scene geometry. Based on the Manhattan-world assumption, planar constraints are employed to regularize the geometry in floor and wall regions predicted by a 2D semantic segmentation network. To resolve the inaccurate segmentation, we encode the semantics of 3D points with another MLP and design a novel loss that jointly optimizes the scene geometry and semantics in 3D space. Experiments on ScanNet and 7-Scenes datasets show that the proposed method outperforms previous methods by a large margin on 3D reconstruction quality. The code and supplementary materials are available at https://zju3dv.github.io/manhattan_sdf.
-
Existing Voice Cloning (VC) tasks aim to convert a paragraph text to a speech with desired voice specified by a reference audio. This has significantly boosted the development of artificial speech applications. However, there also exist many scenarios that cannot be well reflected by these VC tasks, such as movie dubbing, which requires the speech to be with emotions consistent with the movie plots. To fill this gap, in this work we propose a new task named Visual Voice Cloning (V2C), which seeks to convert a paragraph of text to a speech with both desired voice specified by a reference audio and desired emotion specified by a reference video. To facilitate research in this field, we construct a dataset, V2C-Animation, and propose a strong baseline based on existing state-of-the-art (SoTA) VC techniques. Our dataset contains 10,217 animated movie clips covering a large variety of genres (e.g., Comedy, Fantasy) and emotions (e.g., happy, sad). We further design a set of evaluation metrics, named MCD-DTW-SL, which help evaluate the similarity between ground-truth speeches and the synthesised ones. Extensive experimental results show that even SoTA VC methods cannot generate satisfying speeches for our V2C task. We hope the proposed new task together with the constructed dataset and evaluation metric will facilitate the research in the field of voice cloning and broader vision-and-language community. Source code and dataset will be released in https://github.com/chenqi008/V2C.
-
Average precision (AP) loss has recently shown promising performance on the dense object detection task. However, a deep understanding of how AP loss affects the detector from a pairwise ranking perspective has not yet been developed. In this work, we revisit the average precision (AP) loss and reveal that the crucial element is that of selecting the ranking pairs between positive and negative samples. Based on this observation, we propose two strategies to improve the AP loss. The first of these is a novel Adaptive Pairwise Error (APE) loss that focusing on ranking pairs in both positive and negative samples. Moreover, we select more accurate ranking pairs by exploiting the normalized ranking scores and localization scores with a clustering algorithm. Experiments conducted on the MS-COCO dataset support our analysis and demonstrate the superiority of our proposed method compared with current classification and ranking loss. The code is available at https://github.com/Xudangliatiger/APE-Loss.
-
3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these models against real-world deformations must be addressed practically and reliably. In this work, we propose 3DeformRS, a method to certify the robustness of point cloud Deep Neural Networks (DNNs) against real-world deformations. We developed 3DeformRS by building upon recent work that generalized Randomized Smoothing (RS) from pixel-intensity perturbations to vector-field deformations. In particular, we specialized RS to certify DNNs against parameterized deformations (e.g. rotation, twisting), while enjoying practical computational costs. We leverage the virtues of 3DeformRS to conduct a comprehensive empirical study on the certified robustness of four representative point cloud DNNs on two datasets and against seven different deformations. Compared to previous approaches for certifying point cloud DNNs, 3DeformRS is fast, scales well with point cloud size, and provides comparable-to-better certificates. For instance, when certifying a plain PointNet against a 3deg z-rotation on 1024-point clouds, 3DeformRS grants a certificate 3x larger and 20x faster than previous work.
-
Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated motion capture systems. Therefore, we propose an unsupervised approach that learns to predict a 3D human pose from a single image while only being trained with 2D pose data, which can be crowd-sourced and is already widely available. To this end, we estimate the 3D pose that is most likely over random projections, with the likelihood estimated using normalizing flows on 2D poses. While previous work requires strong priors on camera rotations in the training data set, we learn the distribution of camera angles which significantly improves the performance. Another part of our contribution is to stabilize training with normalizing flows on high-dimensional 3D pose data by first projecting the 2D poses to a linear subspace. We outperform state-of-the-art in unsupervised human pose estimation on the benchmark dataset Human3.6M in all metrics.
-
The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques. In comparison, limited effort has been made at assessing the fitness of these datasets for the video-language grounding task. Recent works have begun to discover significant limitations in these datasets, suggesting that state-of-the-art techniques commonly overfit to hidden dataset biases. In this work, we present MAD (Movie Audio Descriptions), a novel benchmark that departs from the paradigm of augmenting existing video datasets with text annotations and focuses on crawling and aligning available audio descriptions of mainstream movies. MAD contains over 384,000 natural language sentences grounded in over 1,200 hours of videos and exhibits a significant reduction in the currently diagnosed biases for video-language grounding datasets. MAD's collection strategy enables a novel and more challenging version of video-language grounding, where short temporal moments (typically seconds long) must be accurately grounded in diverse long-form videos that can last up to three hours. We have released MAD's data and baselines code at https://github.com/Soldelli/MAD.
-
This paper proposes to use neuromorphic events for correcting rolling shutter (RS) images as consecutive global shutter (GS) frames. RS effect introduces edge distortion and region occlusion into images caused by row-wise readout of CMOS sensors. We introduce a novel computational imaging setup consisting of an RS sensor and an event sensor, and propose a neural network called EvUnroll to solve this problem by exploring the high-temporal-resolution property of events. We use events to bridge a spatio-temporal connection between RS and GS, establish a flow estimation module to correct edge distortions, and design a synthesis-based restoration module to restore occluded regions. The results of two branches are fused through a refining module to generate corrected GS images. We further propose datasets captured by a high-speed camera and an RS-Event hybrid camera system for training and testing our network. Experimental results on both public and proposed datasets show a systematic performance improvement compared to state-of-the-art methods.
-
Existing studies for gait recognition are dominated by 2D representations like the silhouette or skeleton of the human body in constrained scenes. However, humans live and walk in the unconstrained 3D space, so projecting the 3D human body onto the 2D plane will discard a lot of crucial information like the viewpoint, shape, and dynamics for gait recognition. Therefore, this paper aims to explore dense 3D representations for gait recognition in the wild, which is a practical yet neglected problem. In particular, we propose a novel framework to explore the 3D Skinned Multi-Person Linear (SMPL) model of the human body for gait recognition, named SMPLGait. Our framework has two elaborately-designed branches of which one extracts appearance features from silhouettes, the other learns knowledge of 3D viewpoints and shapes from the 3D SMPL model. In addition, due to the lack of suitable datasets, we build the first large-scale 3D representation-based gait recognition dataset, named Gait3D. It contains 4,000 subjects and over 25,000 sequences extracted from 39 cameras in an unconstrained indoor scene. More importantly, it provides 3D SMPL models recovered from video frames which can provide dense 3D information of body shape, viewpoint, and dynamics. Based on Gait3D, we comprehensively compare our method with existing gait recognition approaches, which reflects the superior performance of our framework and the potential of 3D representations for gait recognition in the wild. The code and dataset are available at: https://gait3d.github.io.
-
Estimating the articulated 3D hand-object pose from a single RGB image is a highly ambiguous and challenging problem, requiring large-scale datasets that contain diverse hand poses, object types, and camera viewpoints. Most real-world datasets lack these diversities. In contrast, data synthesis can easily ensure those diversities separately. However, constructing both valid and diverse hand-object interactions and efficiently learning from the vast synthetic data is still challenging. To address the above issues, we propose ArtiBoost, a lightweight online data enhancement method. ArtiBoost can cover diverse hand-object poses and camera viewpoints through sampling in a Composited hand-object Configuration and Viewpoint space (CCV-space) and can adaptively enrich the current hard-discernable items by loss-feedback and sample re-weighting. ArtiBoost alternatively performs data exploration and synthesis within a learning pipeline, and those synthetic data are blended into real-world source data for training. We apply ArtiBoost on a simple learning baseline network and witness the performance boost on several hand-object benchmarks. Our models and code are available at https://github.com/lixiny/ArtiBoost.
-
Temporal Context Matters: Enhancing Single Image Prediction With Disease Progression Representations
Clinical outcome or severity prediction from medical images has largely focused on learning representations from single-timepoint or snapshot scans. It has been shown that disease progression can be better characterized by temporal imaging. We therefore hypothesized that outcome predictions can be improved by utilizing the disease progression information from sequential images. We present a deep learning approach that leverages temporal progression information to improve clinical outcome predictions from single-timepoint images. In our method, a self-attention based Temporal Convolutional Network (TCN) is used to learn a representation that is most reflective of the disease trajectory. Meanwhile, a Vision Transformer is pretrained in a self-supervised fashion to extract features from single-timepoint images. The key contribution is to design a recalibration module that employs maximum mean discrepancy loss (MMD) to align distributions of the above two contextual representations. We train our system to predict clinical outcomes and severity grades from single-timepoint images. Experiments on chest and osteoarthritis radiography datasets demonstrate that our approach outperforms other state-of-the-art techniques.
-
While general object detection with deep learning has achieved great success in the past few years, the performance and efficiency of detecting small objects are far from satisfactory. The most common and effective way to promote small object detection is to use high-resolution images or feature maps. However, both approaches induce costly computation since the computational cost grows squarely as the size of images and features increases. To get the best of two worlds, we propose QueryDet that uses a novel query mechanism to accelerate the inference speed of feature-pyramid based object detectors. The pipeline composes two steps: it first predicts the coarse locations of small objects on low-resolution features and then computes the accurate detection results using high-resolution features sparsely guided by those coarse positions. In this way, we can not only harvest the benefit of high-resolution feature maps but also avoid useless computation for the background area. On the popular COCO dataset, the proposed method improves the detection mAP by 1.0 and mAP small by 2.0, and the high-resolution inference speed is improved to 3.0x on average. On VisDrone dataset, which contains more small objects, we create a new state-of-the-art while gaining a 2.3x high-resolution acceleration on average. Code is available at https://github.com/ ChenhongyiYang/QueryDet-PyTorch.
-
This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation. We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) and further reason that temporal irregularity and under-sampling are two major challenges. To tackle the challenges, we propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. Specifically, we propose a temporal consistency learning module to align two consecutive point cloud frames point-wisely, based on which we can employ linear interpolation to obtain coarse trajectories/in-between frames. To compensate the high-order nonlinear components of trajectories, we apply aligned feature embeddings that encode local geometry properties to regress point-wise increments, which are combined with the coarse estimations. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually. Our framework can bring benefits to 3D motion data acquisition. The source code is publicly available at https://github.com/ZENGYIMING-EAMON/IDEA-Net.git.
-
Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization performance of deep neural networks. To combat label noise, recent state-of-the-art methods employ some sort of sample selection mechanism to select a possibly clean subset of data. Next, an off-the-shelf semi-supervised learning method is used for training where rejected samples are treated as unlabeled data. Our comprehensive analysis shows that current selection methods disproportionately select samples from easy (fast learnable) classes while rejecting those from relatively harder ones. This creates class imbalance in the selected clean set and in turn, deteriorates performance under high label noise. In this work, we propose UNICON, a simple yet effective sample selection method which is robust to high label noise. To address the disproportionate selection of easy and hard samples, we introduce a Jensen-Shannon divergence based uniform selection mechanism which does not require any probabilistic modeling and hyperparameter tuning. We complement our selection method with contrastive learning to further combat the memorization of noisy labels. Extensive experimentation on multiple benchmark datasets demonstrates the effectiveness of UNICON; we obtain an 11.4% improvement over the current state-of-the-art on CIFAR100 dataset with a 90% noise rate. Our code is publicly available.
-
In this paper, we present a system to train driving policies from experiences collected not just from the ego-vehicle, but all vehicles that it observes. This system uses the behaviors of other agents to create more diverse driving scenarios without collecting additional data. The main difficulty in learning from other vehicles is that there is no sensor information. We use a set of supervisory tasks to learn an intermediate representation that is invariant to the viewpoint of the controlling vehicle. This not only provides a richer signal at training time but also allows more complex reasoning during inference. Learning how all vehicles drive helps predict their behavior at test time and can avoid collisions. We evaluate this system in closed-loop driving simulations. Our system outperforms all prior methods on the public CARLA Leaderboard by a wide margin, improving driving score by 25 and route completion rate by 24 points.
-
Modelling interactions between humans and objects in natural environments is central to many applications including gaming, virtual and mixed reality, as well as human behavior analysis and human-robot collaboration. This challenging operation scenario requires generalization to vast number of objects, scenes, and human actions. Unfortunately, there exist no such dataset. Moreover, this data needs to be acquired in diverse natural environments, which rules out 4D scanners and marker based capture systems. We present BEHAVE dataset, the first full body human-object interaction dataset with multi-view RGBD frames and corresponding 3D SMPL and object fits along with the annotated contacts between them. We record 15k frames at 5 locations with 8 subjects performing a wide range of interactions with 20 common objects. We use this data to learn a model that can jointly track humans and objects in natural environments with an easy-to-use portable multi-camera setup. Our key insight is to predict correspondences from the human and the object to a statistical body model to obtain human-object contacts during interactions. Our approach can record and track not just the humans and objects but also their interactions, modeled as surface contacts, in 3D. Our code and data can be found at: http://virtualhumans.mpi-inf.mpg.de/behave.
-
Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs which use neural 3D volumetric representations for synthesis. Images are synthesized by rendering the volumes from a given camera. These models can disentangle the 3D scene from the camera viewpoint in any generated image. However, most models do not disentangle other factors of image formation, such as geometry and appearance. In this paper, we design a 3D GAN which can learn a disentangled model of objects, just from monocular observations. Our model can disentangle the geometry and appearance variations in the scene, i.e., we can independently sample from the geometry and appearance spaces of the generative model. This is achieved using a novel non-rigid deformable scene formulation. A 3D volume which represents an object instance is computed as a non-rigidly deformed canonical 3D volume. Our method learns the canonical volume, as well as its deformations, jointly during training. This formulation also helps us improve the disentanglement between the 3D scene and the camera viewpoints using a novel pose regularization loss defined on the 3D deformation field. In addition, we further model the inverse deformations, enabling the computation of dense correspondences between images generated by our model. Finally, we design an approach to embed real images onto the latent space of our disentangled generative model, enabling editing of real images.
-
Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of neural networks. There has been a flurry of algorithms that try to solve this practical problem, each being claimed effective in some ways. Yet, a benchmark to compare those algorithms directly is lacking, mainly due to the complexity of the algorithms and some custom settings such as the particular network configuration or training procedure. A fair benchmark is important for the further development of channel pruning. Meanwhile, recent investigations reveal that the channel configurations discovered by pruning algorithms are at least as important as the pre-trained weights. This gives channel pruning a new role, namely searching the optimal channel configuration. In this paper, we try to determine the channel configuration of the pruned models by random search. The proposed approach provides a new way to compare different methods, namely how well they behave compared with random pruning. We show that this simple strategy works quite well compared with other channel pruning methods. We also show that under this setting, there are surprisingly no clear winners among different channel importance evaluation methods, which then may tilt the research efforts into advanced channel configuration searching methods. Code will be released at https://github.com/ofsoundof/random_channel_pruning.
-
How to achieve better results with fewer labeling costs remains a challenging task. In this paper, we present a new active learning framework, which for the first time incorporates contrastive learning into recently proposed one-bit supervision. Here one-bit supervision denotes a simple Yes or No query about the correctness of the model's prediction, and is more efficient than previous active learning methods requiring assigning accurate labels to the queried samples. We claim that such one-bit information is intrinsically in accordance with the goal of contrastive loss that pulls positive pairs together and pushes negative samples away. Towards this goal, we design an uncertainty metric to actively select samples for query. These samples are then fed into different branches according to the queried results. The Yes query is treated as positive pairs of the queried category for contrastive pulling, while the No query is treated as hard negative pairs for contrastive repelling. Additionally, we design a negative loss that penalizes the negative samples away from the incorrect predicted class, which can be treated as optimizing hard negatives for the corresponding category. Our method, termed as ObCP, produces a more powerful active learning framework, and experiments on several benchmarks demonstrate its superiority.
-
Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can only be trained on synthetic data due to the unavailability of large-scale in-the-wild egocentric datasets. Furthermore, these methods easily fail when the body parts are occluded by or interacting with the surrounding scene. To address the shortage of in-the-wild data, we collect a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW). This dataset is captured by a head-mounted fisheye camera and an auxiliary external camera, which provides an additional observation of the human body from a third-person perspective during training. We present a new egocentric pose estimation method, which can be trained on the new dataset with weak external supervision. Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision. The pseudo labels are then used to train an egocentric pose estimation network. To facilitate the network training, we propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. The experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.
-
Knowledge distillation has shown great effectiveness for improving neural architecture search (NAS). Mutual knowledge distillation (MKD), where a group of models mutually generate knowledge to train each other, has achieved promising results in many applications. In existing MKD methods, mutual knowledge distillation is performed between models without scrutiny: a worse-performing model is allowed to generate knowledge to train a better-performing model, which may lead to collective failures. To address this problem, we propose a performance-aware MKD (PAMKD) approach for NAS, where knowledge generated by model A is allowed to train model B only if the performance of A is better than B. We propose a three-level optimization framework to formulate PAMKD, where three learning stages are performed end-to-end: 1) each model trains an initial model independently; 2) the initial models are evaluated on a validation set and better-performing models generate knowledge to train worse-performing models; 3) architectures are updated by minimizing a validation loss. Experimental results on a variety of datasets demonstrate that our method is effective.
-
E-commerce images are playing a central role in attracting people's attention when retailing and shopping online, and an accurate attention prediction is of significant importance for both customers and retailers, where its research is yet to start. In this paper, we establish the first dataset of saliency e-commerce images (SalECI), which allows for learning to predict saliency on the e-commerce images. We then provide specialized and thorough analysis by highlighting the distinct features of e-commerce images, e.g., non-locality and correlation to text regions. Correspondingly, taking advantages of the non-local and self-attention mechanisms, we propose a salient SWin-Transformer backbone, followed by a multi-task learning with saliency and text detection heads, where an information flow mechanism is proposed to further benefit both tasks. Experimental results have verified the state-of-the-art performances of our work in the e-commerce scenario.
-
We present a new framework to learn dense 3D reconstruction and correspondence from a single 2D image. The shape is represented implicitly as deformation over a category-level occupancy field and learned in an unsupervised manner from an unaligned image collection without using any 3D supervision. However, image collections usually contain large intra-category topological variation, e.g. images of different chair instances, posing a major challenge. Hence, prior methods are either restricted only to categories with no topological variation for estimating shape and correspondence or focus only on learning shape independently for each instance without any correspondence. To address this issue, we propose a topologically-aware deformation field that maps 3D points in object space to a higher-dimensional canonical space. Given a single image, we first implicitly deform a 3D point in the object space to a learned category-specific canonical space using the topologically-aware field and then learn the 3D shape in the canonical space. Both the canonical shape and deformation field are trained end-to-end using differentiable rendering via learned recurrent ray marcher. Our approach, dubbed TARS, achieves state-of-the-art reconstruction fidelity on several datasets: ShapeNet, Pascal3D+, CUB, and Pix3D chairs.
-
Real-world image manipulation has achieved fantastic progress in recent years as a result of the exploration and utilization of GAN latent spaces. GAN inversion is the first step in this pipeline, which aims to map the real image to the latent code faithfully. Unfortunately, the majority of existing GAN inversion methods fail to meet at least one of the three requirements listed below: high reconstruction quality, editability, and fast inference. We present a novel two-phase strategy in this research that fits all requirements at the same time. In the first phase, we train an encoder to map the input image to StyleGAN2 W-space, which was proven to have excellent editability but lower reconstruction quality. In the second phase, we supplement the reconstruction ability in the initial phase by leveraging a series of hypernetworks to recover the missing information during inversion. These two steps complement each other to yield high reconstruction quality thanks to the hypernetwork branch and excellent editability due to the inversion done in the W-space. Our method is entirely encoder-based, resulting in extremely fast inference. Extensive experiments on two challenging datasets demonstrate the superiority of our method.
-
CRF is a classical computer vision model which is also useful for deep learning. There are two common CRF types: sparse and dense. Sparse CRF connects only the nearby pixels, while dense CRF has global connectivity. Therefore dense CRF is a more general model, but it is much harder to optimize compared to sparse CRF. In fact, only a certain form of dense CRF is optimized in practice, and even then approximately. We propose a new sparse non-local CRF: it has a sparse number of connections, but it has both local and non-local ones. Like sparse CRF, the total number of connections is small, and our model is easy to optimize exactly. Like dense CRF, our model is more general than sparse CRF due to non-local connections. We show that our sparse non-local CRF can model properties similar to that of the popular Gaussian edge dense CRF. Besides efficiency, another advantage is that our edge weights are less restricted compared to Gaussian edge dense CRF. We design models that take advantage of this flexibility. We also discuss connection of our model to other CRF models. Finally, to prove the usefulness of our model, we evaluate it on the classical application of segmentation from a bounding box and for deep learning based salient object segmentation. We improve state of the art for both applications.
-
Dataset distillation is the task of synthesizing a small dataset such that a model trained on the synthetic set will match the test accuracy of the model trained on the full dataset. The task is extremely challenging as it often involves backpropagating through the full training process or assuming the strong constraint that a single training step on distilled data can only imitate a single step on real data. In this paper, we propose a new formulation that optimizes our distilled data to guide networks to a similar state as those trained on real data across many training steps. Given a network, we train it for several iterations on our distilled data and optimize the distilled data with respect to the distance between the synthetically trained parameters and the parameters trained on real data. To efficiently obtain the initial and target network parameters for large-scale datasets, we pre-compute and store training trajectories of expert networks trained on the real dataset. Our method handily outperforms existing methods and also allows us to distill with higher-resolution visual data.
-
After the 2017 TuSimple Lane Detection Challenge, its dataset and evaluation based on accuracy and F1 score have become the de facto standard to measure the performance of lane detection methods. While they have played a major role in improving the performance of lane detection methods, the validity of this evaluation method in downstream tasks has not been adequately researched. In this study, we design 2 new driving-oriented metrics for lane detection: End-to-End Lateral Deviation metric (E2E-LD) is directly formulated based on the requirements of autonomous driving, a core task downstream of lane detection; Per-frame Simulated Lateral Deviation metric (PSLD) is a lightweight surrogate metric of E2E-LD. To evaluate the validity of the metrics, we conduct a large-scale empirical study with 4 major types of lane detection approaches on the TuSimple dataset and our newly constructed dataset Comma2k19-LD. Our results show that the conventional metrics have strongly negative correlations (<=-0.55) with E2E-LD, meaning that some recent improvements purely targeting the conventional metrics may not have led to meaningful improvements in autonomous driving, but rather may actually have made it worse by overfitting to the conventional metrics. On the contrary, PSLD shows statistically significant strong positive correlations (>=0.38) with E2E-LD. As a result, the conventional metrics tend to overestimate less robust models. As autonomous driving is a security/safety-critical system, the underestimation of robustness hinders the sound development of practical lane detection models. We hope that our study will help the community achieve more downstream task-aware evaluations for lane detection.
-
Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, so that 2D-3D point correspondences can be partly learned by backpropagating the gradient w.r.t. object pose. Yet, learning the entire set of unrestricted 2D-3D points from scratch fails to converge with existing approaches, since the deterministic pose is inherently non-differentiable. In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose on the SE(3) manifold, essentially bringing categorical Softmax to the continuous domain. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle unifies the existing approaches and resembles the attention mechanism. EPro-PnP significantly outperforms competitive baselines, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation and nuScenes 3D object detection benchmarks.
-
In some scenarios, classifier requires detecting out-of-distribution samples far from its training data. With desirable characteristics, reconstruction autoencoder-based methods deal with this problem by using input reconstruction error as a metric of novelty vs. normality. We formulate the essence of such approach as a quadruplet domain translation with an intrinsic bias to only query for a proxy of conditional data uncertainty. Accordingly, an improvement direction is formalized as maximumly compressing the autoencoder's latent space while ensuring its reconstructive power for acting as a described domain translator. From it, strategies are introduced including semantic reconstruction, data certainty decomposition and normalized L2 distance to substantially improve original methods, which together establish state-of-the-art performance on various benchmarks, e.g., the FPR@95%TPR of CIFAR-100 vs. TinyImagenet-crop on Wide-ResNet is 0.2%. Importantly, our method works without any additional data, hard-to-implement structure, time-consuming pipeline, and even harming the classification accuracy of known classes.
-
Many convolutional neural networks (CNNs) for single image deblurring employ a U-Net structure to estimate latent sharp images. Having long been proven to be effective in image restoration tasks, a single lane of encoder-decoder architecture overlooks the characteristic of deblurring, where a blurry image is generated from complicated blur kernels caused by tangled motions. Toward an effective network architecture, we present complemental sub-solutions learning with a one-encoder-two-decoder architecture for single image deblurring. Observing that multiple decoders successfully learn to decompose information in the encoded features into directional components, we further improve both the network efficiency and the deblurring performance by rotating and sharing kernels exploited in the decoders, which prevents the decoders from separating unnecessary components such as color shift. As a result, our proposed network shows superior results as compared to U-Net while preserving the network parameters, and the use of the proposed network as the base network can improve the performance of existing state-of-the-art deblurring networks.
-
Automated generation of 3D human motions from text is a challenging problem. The generated motions are expected to be sufficiently diverse to explore the text-grounded motion space, and more importantly, accurately depicting the content in prescribed text descriptions. Here we tackle this problem with a two-stage approach: text2length sampling and text2motion generation. Text2length involves sampling from the learned distribution function of motion lengths conditioned on the input text. This is followed by our text2motion module using temporal variational autoencoder to synthesize a diverse set of human motions of the sampled lengths. Instead of directly engaging with pose sequences, we propose motion snippet code as our internal motion representation, which captures local semantic motion contexts and is empirically shown to facilitate the generation of plausible motions faithful to the input text. Moreover, a large-scale dataset of scripted 3D Human motions, HumanML3D, is constructed, consisting of 14,616 motion clips and 44,970 text descriptions. Extensive empirical experiments demonstrate the effectiveness of our approach. Project webpage: https://ericguo5513.github.io/text-to-motion/.
-
A camera begins to sense light the moment we press the shutter button. During the exposure interval, relative motion between the scene and the camera causes motion blur, a common undesirable visual artifact. This paper presents E-CIR, which converts a blurry image into a sharp video represented as a parametric function from time to intensity. E-CIR leverages events as an auxiliary input. We discuss how to exploit the temporal event structure to construct the parametric bases. We demonstrate how to train a deep learning model to predict the function coefficients. To improve the appearance consistency, we further introduce a refinement module to propagate visual features among consecutive frames. Compared to state-of-the-art event-enhanced deblurring approaches, E-CIR generates smoother and more realistic results. The implementation of E-CIR is available at https://github.com/chensong1995/E-CIR.
-
Rain removal aims to remove rain streaks from images/videos and reduce the disruptive effects caused by rain. It not only enhances image/video visibility but also allows many computer vision algorithms to function properly. This paper makes the first attempt to conduct a comprehensive study on the robustness of deep learning-based rain removal methods against adversarial attacks. Our study shows that, when the image/video is highly degraded, rain removal methods are more vulnerable to the adversarial attacks as small distortions/perturbations become less noticeable or detectable. In this paper, we first present a comprehensive empirical evaluation of various methods at different levels of attacks and with various losses/targets to generate the perturbations from the perspective of human perception and machine analysis tasks. A systematic evaluation of key modules in existing methods is performed in terms of their robustness against adversarial attacks. From the insights of our analysis, we construct a more robust deraining method by integrating these effective modules. Finally, we examine various types of adversarial attacks that are specific to deraining problems and their effects on both human and machine vision tasks, including 1) rain region attacks, adding perturbations only in the rain regions to make the perturbations in the attacked rain images less visible; 2) object-sensitive attacks, adding perturbations only in regions near the given objects. Code is available at https://github.com/yuyi-sd/Robust_Rain_Removal.
-
Accurately detecting and tracking pedestrians in 3D space is challenging due to large variations in rotations, poses and scales. The situation becomes even worse for dense crowds with severe occlusions. However, existing benchmarks either only provide 2D annotations, or have limited 3D annotations with low-density pedestrian distribution, making it difficult to build a reliable pedestrian perception system especially in crowded scenes. To better evaluate pedestrian perception algorithms in crowded scenarios, we introduce a large-scale multimodal dataset, STCrowd. Specifically, in STCrowd, there are a total of 219K pedestrian instances and 20 persons per frame on average, with various levels of occlusion. We provide synchronized LiDAR point clouds and camera images as well as their corresponding 3D labels and joint IDs. STCrowd can be used for various tasks, including LiDAR-only, image-only, and sensor-fusion based pedestrian detection and tracking. We provide baselines for most of the tasks. In addition, considering the property of sparse global distribution and density-varying local distribution of pedestrians, we further propose a novel method, Density-aware Hierarchical heatmap Aggregation (DHA), to enhance pedestrian perception in crowded scenes. Extensive experiments show that our new method achieves state-of-the-art performance on the STCrowd dataset, especially on cases with severe occlusion. The dataset and code will be released to facilitate related research when the paper is published.
-
Advection-diffusion equations describe a large family of natural transport processes, e.g., fluid flow, heat transfer, and wind transport. They are also used for optical flow and perfusion imaging computations. We develop a machine learning model, D^2-SONATA, built upon a stochastic advection-diffusion equation, which predicts the velocity and diffusion fields that drive 2D/3D image time-series of transport. In particular, our proposed model incorporates a model of transport atypicality, which isolates abnormal differences between expected normal transport behavior and the observed transport. In a medical context such a normal-abnormal decomposition can be used, for example, to quantify pathologies. Specifically, our model identifies the advection and diffusion contributions from the transport time-series and simultaneously predicts an anomaly value field to provide a decomposition into normal and abnormal advection and diffusion behavior. To achieve improved estimation performance for the velocity and diffusion-tensor fields underlying the advection-diffusion process and for the estimation of the anomaly fields, we create a 2D/3D anomaly-encoded advection-diffusion simulator, which allows for supervised learning. We further apply our model on a brain perfusion dataset from ischemic stroke patients via transfer learning. Extensive comparisons demonstrate that our model successfully distinguishes stroke lesions (abnormal) from normal brain regions, while reconstructing the underlying velocity and diffusion tensor fields.
-
The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) with autoregressive models as generation part has yielded high-quality results on image generation. However, the autoregressive models will strictly follow the progressive scanning order during the sampling phase. This leads the existing VQ series models to hardly escape the trap of lacking global information. Denoising Diffusion Probabilistic Models (DDPM) in the continuous domain have shown a capability to capture the global context, while generating high-quality images. In the discrete state space, some works have demonstrated the potential to perform text generation and low resolution image generation. We show that with the help of a content-rich discrete visual codebook from VQ-VAE, the discrete diffusion model can also generate high fidelity images with global context, which compensates for the deficiency of the classical autoregressive model along pixel space. Meanwhile, the integration of the discrete VAE with the diffusion model resolves the drawback of conventional autoregressive models being oversized, and the diffusion model which demands excessive time in the sampling process when generating images. It is found that the quality of the generated images is heavily dependent on the discrete visual codebook. Extensive experiments demonstrate that the proposed Vector Quantised Discrete Diffusion Model (VQ-DDM) is able to achieve comparable performance to top-tier methods with low complexity. It also demonstrates outstanding advantages over other vectors quantised with autoregressive models in terms of image inpainting tasks without additional training.
-
We propose a keypoint-based object-level SLAM framework that can provide globally consistent 6DoF pose estimates for symmetric and asymmetric objects alike. To the best of our knowledge, our system is among the first to utilize the camera pose information from SLAM to provide prior knowledge for tracking keypoints on symmetric objects - ensuring that new measurements are consistent with the current 3D scene. Moreover, our semantic keypoint network is trained to predict the Gaussian covariance for the keypoints that captures the true error of the prediction, and thus is not only useful as a weight for the residuals in the system's optimization problems, but also as a means to detect harmful statistical outliers without choosing a manual threshold. Experiments show that our method provides competitive performance to the state of the art in 6DoF object pose estimation, and at a real-time speed. Our code, pre-trained models, and keypoint labels are available https://github.com/rpng/suo_slam.
-
Studying the inherent symmetry of data is of great importance in machine learning. Point cloud, the most important data format for 3D environmental perception, is naturally endowed with strong radial symmetry. In this work, we exploit this radial symmetry via a divide-and-conquer strategy to boost 3D perception performance and ease optimization. We propose Azimuth Normalization (AziNorm), which normalizes the point clouds along the radial direction and eliminates the variability brought by the difference of azimuth. AziNorm can be flexibly incorporated into most LiDAR-based perception methods. To validate its effectiveness and generalization ability, we apply AziNorm in both object detection and semantic segmentation. For detection, we integrate AziNorm into two representative detection methods, the one-stage SECOND detector and the state-of-the-art two-stage PV-RCNN detector. Experiments on Waymo Open Dataset demonstrate that AziNorm improves SECOND and PV-RCNN by 7.03 mAPH and 3.01 mAPH respectively. For segmentation, we integrate AziNorm into KPConv. On SemanticKitti dataset, AziNorm improves KPConv by 1.6/1.1 mIoU on val/test set. Besides, AziNorm remarkably improves data efficiency and accelerates convergence, reducing the requirement of data amounts or training epochs by an order of magnitude. SECOND w/ AziNorm can significantly outperform fully trained vanilla SECOND, even trained with only 10% data or 10% epochs. Code and models are available at https://github.com/hustvl/AziNorm.
-
Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation methods either ignore these cases altogether or only deliver a weak performance. We argue that this is due current methods only considering a single "true" depth, even when multiple objects at different depths contributed to the color of a single pixel. Based on the simple idea of outputting a posterior depth distribution instead of only a single estimate, we develop and explore several different deep-learning-based approaches to the problem. Additionally, we contribute the first "multimodal light field depth dataset" that contains the depths of all objects which contribute to the color of a pixel. This allows us to supervise the multimodal depth prediction and also validate all methods by measuring the KL divergence of the predicted posteriors. With our thorough analysis and novel dataset, we aim to start a new line of depth estimation research that overcomes some of the long-standing limitations of this field.
-
In this paper we consider the problem of classifying fine-grained, multi-step activities (e.g., cooking different recipes, making disparate home improvements, creating various forms of arts and crafts) from long videos spanning up to several minutes. Accurately categorizing these activities requires not only recognizing the individual steps that compose the task but also capturing their temporal dependencies. This problem is dramatically different from traditional action classification, where models are typically optimized on videos that span only a few seconds and that are manually trimmed to contain simple atomic actions. While step annotations could enable the training of models to recognize the individual steps of procedural activities, existing large-scale datasets in this area do not include such segment labels due to the prohibitive cost of manually annotating temporal boundaries in long videos. To address this issue, we propose to automatically identify steps in instructional videos by leveraging the distant supervision of a textual knowledge base (wikiHow) that includes detailed descriptions of the steps needed for the execution of a wide variety of complex activities. Our method uses a language model to match noisy, automatically-transcribed speech from the video to step descriptions in the knowledge base. We demonstrate that video models trained to recognize these automatically-labeled steps (without manual supervision) yield a representation that achieves superior generalization performance on four downstream tasks: recognition of procedural activities, step classification, step forecasting and egocentric video classification.
-
Recognition of materials from their visual appearance is essential for computer vision tasks, especially those that involve interaction with the real world. Material segmentation, i.e., dense per-pixel recognition of materials, remains challenging as, unlike objects, materials do not exhibit clearly discernible visual signatures in their regular RGB appearances. Different materials, however, do lead to different radiometric behaviors, which can often be captured with non-RGB imaging modalities. We realize multimodal material segmentation from RGB, polarization, and near-infrared images. We introduce the MCubeS dataset (from MultiModal Material Segmentation) which contains 500 sets of multimodal images capturing 42 street scenes. Ground truth material segmentation as well as semantic segmentation are annotated for every image and pixel. We also derive a novel deep neural network, MCubeSNet, which learns to focus on the most informative combinations of imaging modalities for each material class with a newly derived region-guided filter selection (RGFS) layer. We use semantic segmentation, as a prior to "guide" this filter selection. To the best of our knowledge, our work is the first comprehensive study on truly multimodal material segmentation. We believe our work opens new avenues of practical use of material information in safety critical applications.
-
Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching for self-supervised monocular depth estimation, and propose a novel transformer architecture for cost volume generation. We use depth-discretized epipolar sampling to select matching candidates, and refine predictions through a series of self- and cross-attention layers. These layers sharpen the matching probability between pixel features, improving over standard similarity metrics prone to ambiguities and local minima. The refined cost volume is decoded into depth estimates, and the whole pipeline is trained end-to-end from videos using only a photometric objective. Experiments on the KITTI and DDAD datasets show that our DepthFormer architecture establishes a new state of the art in self-supervised monocular depth estimation, and is even competitive with highly specialized supervised single-frame architectures. We also show that our learned cross-attention network yields representations transferable across datasets, increasing the effectiveness of pre-training strategies.
-
Object rotation is among long-standing, yet still unexplored, hard issues encountered in the task of weakly supervised object detection (WSOD) from aerial images. Existing predominant WSOD approaches built on regular CNNs which are not inherently designed to tackle object rotations without corresponding constraints, thereby leading to rotation-sensitive object detector. Meanwhile, current solutions have been prone to fall into the issue with unstable detectors, as they ignore lower-scored instances and may regard them as backgrounds. To address these issues, in this paper, we construct a novel end-to-end weakly supervised Rotation-Invariant aerial object detection Network (RINet). It is implemented with a flexible multi-branch online detector refinement, to be naturally more rotation-perceptive against oriented objects. Specifically, RINet first performs label propagating from the predicted instances to their rotated ones in a progressive refinement manner. Meanwhile, we propose to couple the predicted instance labels among different rotation-perceptive branches for generating rotation-consistent supervision and meanwhile pursuing all possible instances. With the rotation-consistent supervisions, RINet enforces and encourages consistent yet complementary feature learning for WSOD without additional annotations and hyper-parameters. On the challenging NWPU VHR-10.v2 and DIOR datasets, extensive experiments clearly demonstrate that we significantly boost existing WSOD methods to a new state-of-the-art performance. The code will be available at: https://github.com/XiaoxFeng/RINet.
-
Text-based video segmentation aims to segment the target object in a video based on a describing sentence. Incorporating motion information from optical flow maps with appearance and linguistic modalities is crucial yet has been largely ignored by previous work. In this paper, we design a method to fuse and align appearance, motion, and linguistic features to achieve accurate segmentation. Specifically, we propose a multi-modal video transformer, which can fuse and aggregate multi-modal and temporal features between frames. Furthermore, we design a language-guided feature fusion module to progressively fuse appearance and motion features in each feature level with guidance from linguistic features. Finally, a multi-modal alignment loss is proposed to alleviate the semantic gap between features from different modalities. Extensive experiments on A2D Sentences and J-HMDB Sentences verify the performance and the generalization ability of our method compared to the state-of-the-art methods.
-
Surface reconstruction from point clouds is vital for 3D computer vision. State-of-the-art methods leverage large datasets to first learn local context priors that are represented as neural network-based signed distance functions (SDFs) with some parameters encoding the local contexts. To reconstruct a surface at a specific query location at inference time, these methods then match the local reconstruction target by searching for the best match in the local prior space (by optimizing the parameters encoding the local context) at the given query location. However, this requires the local context prior to generalize to a wide variety of unseen target regions, which is hard to achieve. To resolve this issue, we introduce Predictive Context Priors by learning Predictive Queries for each specific point cloud at inference time. Specifically, we first train a local context prior using a large point cloud dataset similar to previous techniques. For surface reconstruction at inference time, however, we specialize the local context prior into our Predictive Context Prior by learning Predictive Queries, which predict adjusted spatial query locations as displacements of the original locations. This leads to a global SDF that fits the specific point cloud the best. Intuitively, the query prediction enables us to flexibly search the learned local context prior over the entire prior space, rather than being restricted to the fixed query locations, and this improves the generalizability. Our method does not require ground truth signed distances, normals, or any additional procedure of signed distance fusion across overlapping regions. Our experimental results in surface reconstruction for single shapes or complex scenes show significant improvements over the state-of-the-art under widely used benchmarks. Code and data are available at https://github.com/mabaorui/PredictableContextPrior.
-
Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare patches within and across frames. These fixed attention schemes not only have high computational cost but, by comparing patches at predetermined locations, they neglect the motion dynamics in the video. In this paper, we introduce the Deformable Video Transformer (DVT), which dynamically predicts a small subset of video patches to attend for each query location based on motion information, thus allowing the model to decide where to look in the video based on correspondences across frames. Crucially, these motion-based correspondences are obtained at zero-cost from information stored in the compressed format of the video. Our deformable attention mechanism is optimized directly with respect to classification performance, thus eliminating the need for suboptimal hand-design of attention strategies. Experiments on four large-scale video benchmarks (Kinetics-400, Something-Something-V2, EPIC-KITCHENS and Diving-48) demonstrate that, compared to existing video transformers, our model achieves higher accuracy at the same or lower computational cost, and it attains state-of-the-art results on these four datasets.
-
We propose a method for learning the posture and structure of agents from unlabelled behavioral videos. Starting from the observation that behaving agents are generally the main sources of movement in behavioral videos, our method, Behavioral Keypoint Discovery (B-KinD), uses an encoder-decoder architecture with a geometric bottleneck to reconstruct the spatiotemporal difference between video frames. By focusing only on regions of movement, our approach works directly on input videos without requiring manual annotations. Experiments on a variety of agent types (mouse, fly, human, jellyfish, and trees) demonstrate the generality of our approach and reveal that our discovered keypoints represent semantically meaningful body parts, which achieve state-of-the-art performance on keypoint regression among self-supervised methods. Additionally, B-KinD achieve comparable performance to supervised keypoints on downstream tasks, such as behavior classification, suggesting that our method can dramatically reduce model training costs vis-a-vis supervised methods.
-
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible and invisible light sources require reasoning about long-range interactions for inverse rendering, which seeks to recover the components of image formation, namely, shape, material, and lighting. In this work, our intuition is that the long-range attention learned by transformer architectures is ideally suited to solve longstanding challenges in single-image inverse rendering. We demonstrate with a specific instantiation of a dense vision transformer, \Ours , that excels at both single-task and multi-task reasoning required for inverse rendering. Specifically, we propose a transformer architecture to simultaneously estimate depths, normals, spatially-varying albedo, roughness and lighting from a single image of an indoor scene. Our extensive evaluations on benchmark datasets demonstrate state-of-the-art results on each of the above tasks, enabling applications like object insertion and material editing in a single unconstrained real image, with greater photorealism than prior works. Code and data are publicly released at https://github.com/ViLab-UCSD/IRISformer
-
Earth observation is a fundamental tool for monitoring the evolution of land use in specific areas of interest. Observing and precisely defining change, in this context, requires both time-series data and pixel-wise segmentations. To that end, we propose the DynamicEarthNet dataset that consists of daily, multi-spectral satellite observations of 75 selected areas of interest distributed over the globe with imagery from Planet Labs. These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes. DynamicEarthNet is the first dataset that provides this unique combination of daily measurements and high-quality labels. In our experiments, we compare several established baselines that either utilize the daily observations as additional training data (semi-supervised learning) or multiple observations at once (spatio-temporal learning) as a point of reference for future research. Finally, we propose a new evaluation metric SCS that addresses the specific challenges associated with time-series semantic change segmentation. The data is available at: https://mediatum.ub.tum.de/1650201.
-
We attempt to connect the data from complementary views, i.e., top view from drone-mounted cameras in the air, and side view from wearable cameras on the ground. Collaborative analysis of such complementary-view data can facilitate to build the air-ground cooperative visual system for various kinds of applications. This is a very challenging problem due to the large view difference between top and side views. In this paper, we develop a new approach that can simultaneously handle three tasks: i) localizing the side-view camera in the top view; ii) estimating the view direction of the side-view camera; iii) detecting and associating the same subjects on the ground across the complementary views. Our main idea is to explore the spatial position layout of the subjects in two views. In particular, we propose a spatial-aware position representation method to embed the spatial-position distribution of the subjects in different views. We further design a cross-view video collaboration framework composed of a camera identification module and a subject association module to simultaneously perform the above three tasks. We collect a new synthetic dataset consisting of top-view and side-view video sequence pairs for performance evaluation and the experimental results show the effectiveness of the proposed method.
-
In this paper, we aim to forecast a future trajectory distribution of a moving agent in the real world, given the social scene images and historical trajectories. Yet, it is a challenging task because the ground-truth distribution is unknown and unobservable, while only one of its samples can be applied for supervising model learning, which is prone to bias. Most recent works focus on predicting diverse trajectories in order to cover all modes of the real distribution, but they may despise the precision and thus give too much credit to unrealistic predictions. To address the issue, we learn the distribution with symmetric cross-entropy using occupancy grid maps as an explicit and scene-compliant approximation to the ground-truth distribution, which can effectively penalize unlikely predictions. In specific, we present an inverse reinforcement learning based multi-modal trajectory distribution forecasting framework that learns to plan by an approximate value iteration network in an end-to-end manner. Besides, based on the predicted distribution, we generate a small set of representative trajectories through a differentiable Transformer-based network, whose attention mechanism helps to model the relations of trajectories. In experiments, our method achieves state-of-the-art performance on the Stanford Drone Dataset and Intersection Drone Dataset.
-
Previous partial permutation synchronization (PPS) algorithms, which are commonly used for multi-object matching, often involve computation-intensive and memory-demanding matrix operations. These operations become intractable for large scale structure-from-motion datasets. For pure permutation synchronization, the recent Cycle-Edge Message Passing (CEMP) framework suggests a memory-efficient and fast solution. Here we overcome the restriction of CEMP to compact groups and propose an improved algorithm, CEMP-Partial, for estimating the corruption levels of the observed partial permutations. It allows us to subsequently implement a nonconvex weighted projected power method without the need of spectral initialization. The resulting new PPS algorithm, MatchFAME (Fast, Accurate and Memory-Efficient Matching), only involves sparse matrix operations, and thus enjoys lower time and space complexities in comparison to previous PPS algorithms. We prove that under adversarial corruption, though without additive noise and with certain assumptions, CEMP-Partial is able to exactly classify corrupted and clean partial permutations. We demonstrate the state-of-the-art accuracy, speed and memory efficiency of our method on both synthetic and real datasets.
-
Diffractive snapshot hyperspectral imaging based on the deep optics framework has been striving to capture the spectral images of dynamic scenes. However, existing deep optics frameworks all suffer from the mismatch between the optical hardware and the reconstruction algorithm due to the quantization operation in the diffractive optical element (DOE) fabrication, leading to the limited performance of hyperspectral imaging in practice. In this paper, we propose the quantization-aware deep optics for diffractive snapshot hyperspectral imaging. Our key observation is that common lithography techniques used in fabricating DOEs need to quantize the DOE height map to a few levels, and can freely set the height for each level. Therefore, we propose to integrate the quantization operation into the DOE height map optimization and design an adaptive mechanism to adjust the physical height of each quantization level. According to the optimization, we fabricate the quantized DOE directly and build a diffractive hyperspectral snapshot imaging system. Our method develops the deep optics framework to be more practical through the awareness of and adaptation to the quantization operation of the DOE physical structure, making the fabricated DOE and the reconstruction algorithm match each other systematically. Extensive synthetic simulation and real hardware experiments validate the superior performance of our method.
-
Weakly supervised temporal action localization targets at localizing temporal boundaries of actions and simultaneously identify their categories with only video-level category labels. Many existing methods seek to generate pseudo labels for bridging the discrepancy between classification and localization, but usually only make use of limited contextual information for pseudo label generation. To alleviate this problem, we propose a representative snippet summarization and propagation framework. Our method seeks to mine the representative snippets in each video for better propagating information between video snippets. For each video, its own representative snippets and the representative snippets from a memory bank are propagated to update the input features in an intra- and inter-video manner. The pseudo labels are generated from the temporal class activation maps of the updated features to rectify the predictions of the main branch. Our method obtains superior performance in comparison to the existing methods on two benchmarks, THUMOS14 and ActivityNet1.3, achieving gains as high as 1.2% in terms of average mAP on THUMOS14. Our code is available at https://github.com/LeonHLJ/RSKP.
-
The wavelet scattering transform creates geometric invariants and deformation stability. In multiple signal domains, it has been shown to yield more discriminative representations compared to other non-learned representations and to outperform learned representations in certain tasks, particularly on limited labeled data and highly structured signals. The wavelet filters used in the scattering transform are typically selected to create a tight frame via a parameterized mother wavelet. In this work, we investigate whether this standard wavelet filterbank construction is optimal. Focusing on Morlet wavelets, we propose to learn the scales, orientations, and aspect ratios of the filters to produce problem-specific parameterizations of the scattering transform. We show that our learned versions of the scattering transform yield significant performance gains in small-sample classification settings over the standard scattering transform. Moreover, our empirical results suggest that traditional filterbank constructions may not always be necessary for scattering transforms to extract effective representations.
-
Sketch-based image manipulation is an interactive image editing task to modify an image based on input sketches from users. Existing methods typically convert this task into a conditional inpainting problem, which requires an additional mask from users indicating the region to modify. Then the masked regions are regarded as missing and filled by an inpainting model conditioned on the sketch. With this formulation, paired training data can be easily obtained by randomly creating masks and extracting edges or contours. Although this setup simplifies data preparation and model design, it complicates user interaction and discards useful information in masked regions. To this end, we propose a new framework for sketch-based image manipulation that only requires sketch inputs from users and utilizes the entire original image. Given an image and sketch, our model automatically predicts the target modification region and encodes it into a structure agnostic style vector. A generator then synthesizes the new image content based on the style vector and sketch. The manipulated image is finally produced by blending the generator output into the modification region of the original image. Our model can be trained in a self-supervised fashion by learning the reconstruction of an image region from the style vector and sketch. The proposed framework offers simpler and more intuitive user workflows for sketch-based image manipulation and provides better results than previous approaches. The code and interactive demo can be found in the supplementary material.
-
In this paper, we address the problem of estimating scale factors between images. We formulate the scale estimation problem as a prediction of a probability distribution over scale factors. We design a new architecture, ScaleNet, that exploits dilated convolutions as well as self- and cross-correlation layers to predict the scale between images. We demonstrate that rectifying images with estimated scales leads to significant performance improvements for various tasks and methods. Specifically, we show how ScaleNet can be combined with sparse local features and dense correspondence networks to improve camera pose estimation, 3D reconstruction, or dense geometric matching in different benchmarks and datasets. We provide an extensive evaluation on several tasks, and analyze the computational overhead of ScaleNet. The code, evaluation protocols, and trained models are publicly available.
-
Contour-based instance segmentation methods have developed rapidly recently but feature rough and handcrafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label vertex pairing, which contributes to the learning difficulty. In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation. Firstly, E2EC applies a novel learnable contour initialization architecture instead of handcrafted contour initialization. This consists of a contour initialization module for constructing more explicit learning goals and a global contour deformation module for taking advantage of all of the vertices' features better. Secondly, we propose a novel label sampling scheme, named multi-direction alignment, to reduce the learning difficulty. Thirdly, to improve the quality of the boundary details, we dynamically match the most appropriate predicted-ground truth vertex pairs and propose the corresponding loss function named dynamic matching loss. The experiments showed that E2EC can achieve a state-of-the-art performance on the KITTI INStance (KINS) dataset, the Semantic Boundaries Dataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient for use in real-time applications, with an inference speed of 36 fps for 512x512 images on an NVIDIA A6000 GPU. Code will be released at https://github.com/zhang-tao-whu/e2ec.
-
We propose a novel adversarial attack targeting content features in some deep layer, that is, individual neurons in the layer. A naive method that enforces a fixed value/percentage bound for neuron activation values can hardly work and generates very noisy samples. The reason is that the level of perceptual variation entailed by a fixed value bound is non-uniform across neurons and even for the same neuron. We hence propose a novel distribution quantile bound for activation values and a polynomial barrier loss function. Given a benign input, a fixed quantile bound is translated to many value bounds, one for each neuron, based on the distributions of the neuron's activations and the current activation value on the given input. These individualized bounds enable fine-grained regulation, allowing content feature mutations with bounded perceptional variations. Our evaluation on ImageNet and five different model architectures demonstrates that our attack is effective. Compared to seven other latest adversarial attacks in both the pixel space and the feature space, our attack can achieve the state-of-the-art trade-off between attack success rate and imperceptibility.
-
Despite the success of deep neural networks, there are still many challenges in deep representation learning due to the data scarcity issues such as data imbalance, unseen distribution, and domain shift. To address the above-mentioned issues, a variety of methods have been devised to explore the sample relationships in a vanilla way (i.e., from the perspectives of either the input or the loss function), failing to explore the internal structure of deep neural networks for learning with sample relationships. Inspired by this, we propose to enable deep neural networks themselves with the ability to learn the sample relationships from each mini-batch. Specifically, we introduce a batch transformer module or BatchFormer, which is then applied into the batch dimension of each mini-batch to implicitly explore sample relationships during training. By doing this, the proposed method enables the collaboration of different samples, e.g., the head-class samples can also contribute to the learning of the tail classes for long-tailed recognition. Furthermore, to mitigate the gap between training and testing, we share the classifier between with or without the BatchFormer during training, which can thus be removed during testing. We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications without any bells and whistles, including the tasks of long-tailed recognition, compositional zero-shot learning, domain generalization, and contrastive learning. Code is made publicly available at https://github.com/zhihou7/BatchFormer.
-
Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has attracted much attention due to low annotation costs. Existing methods often rely on Class Activation Mapping (CAM) that measures the correlation between image pixels and classifier weight. However, the classifier focuses only on the discriminative regions while ignoring other useful information in each image, resulting in incomplete localization maps. To address this issue, we propose a Self-supervised Image-specific Prototype Exploration (SIPE) that consists of an Image-specific Prototype Exploration (IPE) and a General-Specific Consistency (GSC) loss. Specifically, IPE tailors prototypes for every image to capture complete regions, formed our Image-Specific CAM (IS-CAM). GSC is proposed to construct the consistency of general CAM and our specific IS-CAM, which further optimizes the feature representation and empowers a self-correction ability of prototype exploration. Extensive experiments are conducted on PASCAL VOC 2012 and MS COCO 2014 segmentation benchmark and results show our SIPE achieves new state-of-the-art performance using only image-level labels. The code is available at https://github.com/chenqi1126/SIPE.
-
Few-shot classification is a challenging problem that aims to learn a model that can adapt to unseen classes given a few labeled samples. Recent approaches pre-train a feature extractor, and then fine-tune for episodic meta-learning. Other methods leverage spatial features to learn pixel-level correspondence while jointly training a classifier. However, results using such approaches show marginal improvements. In this paper, inspired by the transformer style self-attention mechanism, we propose a strategy to cross-attend and re-weight discriminative features for few-shot classification. Given a base representation of support and query images after global pooling, we introduce a single shared module that projects features and cross-attends in two aspects: (i) query to support, and (ii) support to query. The module computes attention scores between features to produce an attention pooled representation of features in the same class that is later added to the original representation followed by a projection head. This effectively re-weights features in both aspects (i & ii) to produce features that better facilitate improved metric-based meta-learning. Extensive experiments on public benchmarks show our approach outperforms state-of-the-art methods by 3% 5%.
-
In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks. Our key insight is that the profile of a DNN model's decision boundary can be uniquely characterized by its Universal Adversarial Perturbations (UAPs). UAPs belong to a low-dimensional subspace and piracy models' subspaces are more consistent with victim model's subspace compared with non-piracy model. Based on this, we propose a UAP fingerprinting method for DNN models and train an encoder via contrastive learning that takes fingerprint as inputs, outputs a similarity score. Extensive studies show that our framework can detect model IP breaches with confidence > 99.99% within only 20 fingerprints of the suspect model. It has good generalizability across different model architectures and is robust against post-modifications on stolen models.
-
Recent works on 3D semantic segmentation propose to exploit the synergy between images and point clouds by processing each modality with a dedicated network and projecting learned 2D features onto 3D points. Merging large-scale point clouds and images raises several challenges, such as constructing a mapping between points and pixels, and aggregating features between multiple views. Current methods require mesh reconstruction or specialized sensors to recover occlusions, and use heuristics to select and aggregate available images. In contrast, we propose an end-to-end trainable multi-view aggregation model leveraging the viewing conditions of 3D points to merge features from images taken at arbitrary positions. Our method can combine standard 2D and 3D networks and outperforms both 3D models operating on colorized point clouds and hybrid 2D/3D networks without requiring colorization, meshing, or true depth maps. We set a new state-of-the-art for large-scale indoor/outdoor semantic segmentation on S3DIS (74.7 mIoU 6-Fold) and on KITTI-360 (58.3 mIoU). Our full pipeline is accessible at https://github.com/drprojects/DeepViewAgg, and only requires raw 3D scans and a set of images and poses.
-
Existing text-guided image manipulation methods aim to modify the appearance of the image or to edit a few objects in a virtual or simple scenario, which is far from practical application. In this work, we study a novel task on text-guided image manipulation on the entity level in the real world. The task imposes three basic requirements, (1) to edit the entity consistent with the text descriptions, (2) to preserve the text-irrelevant regions, and (3) to merge the manipulated entity into the image naturally. To this end, we propose a new transformer-based framework based on the two-stage image synthesis method, namely ManiTrans, which can not only edit the appearance of entities but also generate new entities corresponding to the text guidance. Our framework incorporates a semantic alignment module to locate the image regions to be manipulated, and a semantic loss to help align the relationship between the vision and language. We conduct extensive experiments on the real datasets, CUB, Oxford, and COCO datasets to verify that our method can distinguish the relevant and irrelevant regions and achieve more precise and flexible manipulation compared with baseline methods.
-
Temporal modeling is an essential element in video understanding. While deep convolution-based architectures have been successful at solving large-scale video recognition datasets, recent work has pointed out that they are biased towards modeling short-range relations, often failing to capture long-term temporal structures in the videos, leading to poor transfer and generalization to new datasets. In this work, the problem of dynamic representation learning (DRL) is studied. We propose dynamic score, a measure of video dynamic modeling that describes the additional amount of information learned by a video network that cannot be captured by pure spatial student through knowledge distillation. DRL is then formulated as an adversarial learning problem between the video and spatial models, with the objective of maximizing the dynamic score of learned spatiotemporal classifier. The quality of learned video representations are evaluated on a diverse set of transfer learning problems concerning many-shot and few-shot action classification. Experimental results show that models learned with DRL outperform baselines in dynamic modeling, demonstrating higher transferability and generalization capacity to novel domains and tasks.
-
Intrinsic image decomposition is the process of recovering the image formation components (reflectance and shading) from an image. Previous methods employ either explicit priors to constrain the problem or implicit constraints as formulated by their losses (deep learning). These methods can be negatively influenced by strong illumination conditions causing shading-reflectance leakages. Therefore, in this paper, an end-to-end edge-driven hybrid CNN approach is proposed for intrinsic image decomposition. Edges correspond to illumination invariant gradients. To handle hard negative illumination transitions, a hierarchical approach is taken including global and local refinement layers. We make use of attention layers to further strengthen the learning process. An extensive ablation study and large scale experiments are conducted showing that it is beneficial for edge-driven hybrid IID networks to make use of illumination invariant descriptors and that separating global and local cues helps in improving the performance of the network. Finally, it is shown that the proposed method obtains state of the art performance and is able to generalise well to real world images. The project page with pretrained models, finetuned models and network code can be found at: https://ivi.fnwi.uva.nl/cv/pienet/
-
The key to address clothes-changing person re-identification (re-id) is to extract clothes-irrelevant features, e.g., face, hairstyle, body shape, and gait. Most current works mainly focus on modeling body shape from multi-modality information (e.g., silhouettes and sketches), but do not make full use of the clothes-irrelevant information in the original RGB images. In this paper, we propose a Clothes-based Adversarial Loss (CAL) to mine clothes-irrelevant features from the original RGB images by penalizing the predictive power of re-id model w.r.t. clothes. Extensive experiments demonstrate that using RGB images only, CAL outperforms all state-of-the-art methods on widely-used clothes-changing person re-id benchmarks. Besides, compared with images, videos contain richer appearance and additional temporal information, which can be used to model proper spatiotemporal patterns to assist clothes-changing re-id. Since there is no publicly available clothes-changing video re-id dataset, we contribute a new dataset named CCVID and show that there exists much room for improvement in modeling spatiotemporal information. The code and new dataset are available at: https://github.com/guxinqian/Simple-CCReID.
-
Current stereo matching techniques are challenged by restricted searching space, occluded regions and sheer size. While single image depth estimation is spared from these challenges and can achieve satisfactory results with the extracted monocular cues, the lack of stereoscopic relationship renders the monocular prediction less reliable on its own, especially in highly dynamic or cluttered environments. To address these issues in both scenarios, we present an optic-chiasm-inspired self-supervised binocular depth estimation method, wherein a vision transformer (ViT) with gated positional cross-attention (GPCA) layers is designed to enable feature-sensitive pattern retrieval between views while retaining the extensive context information aggregated through self-attentions. Monocular cues from a single view are thereafter conditionally rectified by a blending layer with the retrieved pattern pairs. This crossover design is biologically analogous to the optic-chasma structure in the human visual system and hence the name, ChiTransformer. Our experiments show that this architecture yields substantial improvements over state-of-the-art self-supervised stereo approaches by 11%, and can be used on both rectilinear and non-rectilinear (e.g., fisheye) images.
-
The increasing abuse of image editing softwares, such as Photoshop and Meitu, causes the authenticity of digital images questionable. Meanwhile, the widespread availability of online social networks (OSNs) makes them the dominant channels for transmitting forged images to report fake news, propagate rumors, etc. Unfortunately, various lossy operations adopted by OSNs, e.g., compression and resizing, impose great challenges for implementing the robust image forgery detection. To fight against the OSN-shared forgeries, in this work, a novel robust training scheme is proposed. We first conduct a thorough analysis of the noise introduced by OSNs, and decouple it into two parts, i.e., predictable noise and unseen noise, which are modelled separately. The former simulates the noise introduced by the disclosed (known) operations of OSNs, while the latter is designed to not only complete the previous one, but also take into account the defects of the detector itself. We then incorporate the modelled noise into a robust training framework, significantly improving the robustness of the image forgery detector. Extensive experimental results are presented to validate the superiority of the proposed scheme compared with several state-of-the-art competitors. Finally, to promote the future development of the image forgery detection, we build a public forgeries dataset based on four existing datasets and three most popular OSNs. The designed detector recently won the top ranking in a certificate forgery detection competition. The source code and dataset are available at https://github.com/HighwayWu/ImageForensicsOSN.
-
Unpaired image-to-image (I2I) translation often requires to maximize the mutual information between the source and the translated images across different domains, which is critical for the generator to keep the source content and prevent it from unnecessary modifications. The self-supervised contrastive learning has already been successfully applied in the I2I. By constraining features from the same location to be closer than those from different ones, it implicitly ensures the result to take content from the source. However, previous work uses the features from random locations to impose the constraint, which may not be appropriate since some locations contain less information of source domain. Moreover, the feature itself does not reflect the relation with others. This paper deals with these problems by intentionally selecting significant anchor points for contrastive learning. We design a query-selected attention (QS-Attn) module, which compares feature distances in the source domain, giving an attention matrix with a probability distribution in each row. Then we select queries according to their measurement of significance, computed from the distribution. The selected ones are regarded as anchors for contrastive loss. At the same time, the reduced attention matrix is employed to route features in both domains, so that source relations maintain in the synthesis. We validate our proposed method in three different I2I datasets, showing that it increases the image quality without adding learnable parameters.
-
Learning-based image dehazing methods have achieved marvelous progress during the past few years. On one hand, most approaches heavily rely on synthetic data and may face difficulties to generalize well in real scenes, due to the huge domain gap between synthetic and real images. On the other hand, very few works have considered the varicolored haze, caused by chromatic casts in real scenes. In this work, our goal is to handle the new task: real-world varicolored haze removal. To this end, we propose a physically disentangled joint intra- and inter-domain adaptation paradigm, in which intra-domain adaptation focuses on color correction and inter-domain procedure transfers knowledge between synthetic and real domains. We first learn to physically disentangle haze images into three components complying with the scattering model: background, transmission map, and atmospheric light. Since haze color is determined by atmospheric light, we perform intra-domain adaptation by specifically translating atmospheric light from varicolored space to unified color-balanced space, and then reconstructing color-balanced haze image through the scattering model. Consequently, we perform inter-domain adaptation between the synthetic and real images by mutually exchanging the background and other two components. Then we can reconstruct both identity and domain-translated haze images with self-consistency and adversarial loss. Extensive experiments demonstrate the superiority of the proposed method over the state-of-the-art for real varicolored image dehazing.
-
Fusion of multiple sensor modalities such as camera, Lidar, and Radar, which are commonly found on autonomous vehicles, not only allows for accurate detection but also robustifies perception against adverse weather conditions and individual sensor failures. Due to inherent sensor characteristics, Radar performs well under extreme weather conditions (snow, rain, fog) that significantly degrade camera and Lidar. Recently, a few works have developed vehicle detection methods fusing Lidar and Radar signals, i.e., MVDNet. However, these models are typically developed under the assumption that the models always have access to two error-free sensor streams. If one of the sensors is unavailable or missing, the model may fail catastrophically. To mitigate this problem, we propose the Self-Training Multimodal Vehicle Detection Network (ST-MVDNet) which leverages a Teacher-Student mutual learning framework and a simulated sensor noise model used in strong data augmentation for Lidar and Radar. We show that by (1) enforcing output consistency between a Teacher network and a Student network and by (2) introducing missing modalities (strong augmentations) during training, our learned model breaks away from the error-free sensor assumption. This consistency enforcement enables the Student model to handle missing data properly and improve the Teacher model by updating it with the Student model's exponential moving average. Our experiments demonstrate that our proposed learning framework for multi-modal detection is able to better handle missing sensor data during inference. Furthermore, our method achieves new state-of-the-art performance (5% gain) on the Oxford Radar Robotcar dataset under various evaluation settings.
-
Real-world data often exhibits class-imbalanced distributions, where a few classes (a.k.a. majority classes) occupy most instances and lots of classes (a.k.a. minority classes) have few instances. Neural classification models usually perform poorly on minority classes when training on such imbalanced datasets. To improve the performance on minority classes, existing methods typically re-balance the data distribution at the class level, i.e., assigning higher weights to minority classes and lower weights to majority classes during the training process. However, we observe that even the majority classes contain difficult instances to learn. By reducing the weights of the majority classes, such instances would become more difficult to learn and hurt the overall performance consequently. To tackle this problem, we propose a novel instance-level re-balancing strategy, which dynamically adjusts the sampling probabilities of instances according to the instance difficulty. Here the instance difficulty is measured based on the learning speed of instance, which is inspired by the human-leaning process (i.e., easier instances will be learned faster). We theoretically prove the correctness and convergence of our re-sampling algorithm. Empirical experiments demonstrate that our method significantly outperforms state-of-the-art re-balancing methods on the class-imbalanced datasets.
-
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-parameterization mechanism, named representation compensation (RC) module, to decouple the representation learning of both old and new knowledge. The RC module consists of two dynamically evolved branches with one frozen and one trainable. Besides, we design a pooled cube knowledge distillation strategy on both spatial and channel dimensions to further enhance the plasticity and stability of the model. We conduct experiments on two challenging continual semantic segmentation scenarios, continual class segmentation and continual domain segmentation. Without any extra computational overhead and parameters during inference, our method outperforms state-of-the-art performance. The code is available at https://github.com/zhangchbin/RCIL.
-
Single-photon avalanche diodes (SPADs) are growing in popularity for depth sensing tasks. However, SPADs still struggle in the presence of high ambient light due to the effects of pile-up. Conventional techniques leverage fixed or asynchronous gating to minimize pile-up effects, but these gating schemes are all non-adaptive, as they are unable to incorporate factors such as scene priors and previous photon detections into their gating strategy. We propose an adaptive gating scheme built upon Thompson sampling. Adaptive gating periodically updates the gate position based on prior photon observations in order to minimize depth errors. Our experiments show that our gating strategy results in significantly reduced depth reconstruction error and acquisition time, even when operating outdoors under strong sunlight conditions.
-
We present an approach for tracking people in monocular videos by predicting their future 3D representations. To achieve this, we first lift people to 3D from a single frame in a robust manner. This lifting includes information about the 3D pose of the person, their location in the 3D space, and the 3D appearance. As we track a person, we collect 3D observations over time in a tracklet representation. Given the 3D nature of our observations, we build temporal models for each one of the previous attributes. We use these models to predict the future state of the tracklet, including 3D appearance, 3D location, and 3D pose. For a future frame, we compute the similarity between the predicted state of a tracklet and the single frame observations in a probabilistic manner. Association is solved with simple Hungarian matching, and the matches are used to update the respective tracklets. We evaluate our approach on various benchmarks and report state-of-the-art results. Code and models are available at: https://brjathu.github.io/PHALP.
-
In this work, we develop intuitive controls for editing the style of 3D objects. Our framework, Text2Mesh, stylizes a 3D mesh by predicting color and local geometric details which conform to a target text prompt. We consider a disentangled representation of a 3D object using a fixed mesh input (content) coupled with a learned neural network, which we term a neural style field network (NSF). In order to modify style, we obtain a similarity score between a text prompt (describing style) and a stylized mesh by harnessing the representational power of CLIP. Text2Mesh requires neither a pre-trained generative model nor a specialized 3D mesh dataset. It can handle low-quality meshes (non-manifold, boundaries, etc.) with arbitrary genus, and does not require UV parameterization. We demonstrate the ability of our technique to synthesize a myriad of styles over a wide variety of 3D meshes. Our code and results are available in our project webpage: https://threedle.github.io/text2mesh/.
-
We present an approach to solving hard geometric optimization problems in the RANSAC framework. The hard minimal problems arise from relaxing the original geometric optimization problem into a minimal problem with many spurious solutions. Our approach avoids computing large numbers of spurious solutions. We design a learning strategy for selecting a starting problem-solution pair that can be numerically continued to the problem and the solution of interest. We demonstrate our approach by developing a RANSAC solver for the problem of computing the relative pose of three calibrated cameras, via a minimal relaxation using four points in each view. On average, we can solve a single problem in under 70 microseconds. We also benchmark and study our engineering choices on the very familiar problem of computing the relative pose of two calibrated cameras, via the minimal case of five points in two views.
-
Despite the impressive results achieved by deep learning based 3D reconstruction, the techniques of directly learning to model 4D human captures with detailed geometry have been less studied. This work presents a novel framework that can effectively learn a compact and compositional representation for dynamic human by exploiting the human body prior from the widely used SMPL parametric model. Particularly, our representation, named H4D, represents a dynamic 3D human over a temporal span with the SMPL parameters of shape and initial pose, and latent codes encoding motion and auxiliary information. A simple yet effective linear motion model is proposed to provide a rough and regularized motion estimation, followed by per-frame compensation for pose and geometry details with the residual encoded in the auxiliary code. Technically, we introduce novel GRU-based architectures to facilitate learning and improve the representation capability. Extensive experiments demonstrate our method is not only efficacy in recovering dynamic human with accurate motion and detailed geometry, but also amenable to various 4D human related tasks, including motion retargeting, motion completion and future prediction.
-
Novel view synthesis (NVS) is a challenging task requiring systems to generate photorealistic images of scenes from new viewpoints, where both quality and speed are important for applications. Previous image-based rendering (IBR) methods are fast, but have poor quality when input views are sparse. Recent Neural Radiance Fields (NeRF) and generalizable variants give impressive results but are not real-time. In our paper, we propose a generalizable NVS method with sparse inputs, called \FWDds, which gives high-quality synthesis in real-time. With explicit depth and differentiable rendering, it achieves competitive results to the SOTA methods with 130-1000xspeedup and better perceptual quality. If available, we can seamlessly integrate sensor depth during either training or inference to improve image quality while retaining real-time speed. With the growing prevalence of depths sensors, we hope that methods making use of depth will become increasingly useful.
-
Synthesizing pseudo samples is currently the most effective way to solve the Generalized Zero Shot Learning (GZSL) problem. Most models achieve competitive performance but still suffer from two problems: (1) Feature confounding, the overall representations confound task-correlated and task-independent features, and existing models disentangle them in a generative way, but they are unreasonable to synthesize reliable pseudo samples with limited samples; (2) Distribution uncertainty, that massive data is needed when existing models synthesize samples from the uncertain distribution, which causes poor performance in limited samples of seen classes. In this paper, we propose a non-generative model to address these problems correspondingly in two modules: (1) Task-correlated feature disentanglement, to exclude the task-correlated features from task-independent ones by adversarial learning of domain adaption towards reasonable synthesis; (2) Controllable pseudo sample synthesis, to synthesize edge-pseudo and center-pseudo samples with certain characteristics towards more diversity generated and intuitive transfer. In addation, to describe the new scene that is the limit seen class samples in the training process, we further formulate a new ZSL task named the 'Few-shot Seen class and Zero-shot Unseen class learning' (FSZU). Extensive experiments on four benchmarks verify that the proposed method is competitive in the GZSL and the FSZU tasks.
-
Recently, many excellent weakly supervised semantic segmentation (WSSS) works are proposed based on class activation mapping (CAM). However, there are few works that consider the characteristics of medical images. In this paper, we find that there are mainly two challenges of medical images in WSSS: i) the boundary of object foreground and background is not clear; ii) the co-occurrence phenomenon is very severe in training stage. We thus propose a Causal CAM (C-CAM) method to overcome the above challenges. Our method is motivated by two cause-effect chains including category-causality chain and anatomy-causality chain. The category-causality chain represents the image content (cause) affects the category (effect). The anatomy-causality chain represents the anatomical structure (cause) affects the organ segmentation (effect). Extensive experiments were conducted on three public medical image data sets. Our C-CAM generates the best pseudo masks with the DSC of 77.26%, 80.34% and 78.15% on ProMRI, ACDC and CHAOS compared with other CAM-like methods. The pseudo masks of C-CAM are further used to improve the segmentation performance for organ segmentation tasks. Our C-CAM achieves DSC of 83.83% on ProMRI and DSC of 87.54% on ACDC, which outperforms state-of-the-art WSSS methods. Our code is available at https://github.com/Tian-lab/C-CAM.
-
One of the most pressing challenges for the detection of face-manipulated videos is generalising to forgery methods not seen during training while remaining effective under common corruptions such as compression. In this paper, we examine whether we can tackle this issue by harnessing videos of real talking faces, which contain rich information on natural facial appearance and behaviour and are readily available in large quantities online. Our method, termed RealForensics, consists of two stages. First, we exploit the natural correspondence between the visual and auditory modalities in real videos to learn, in a self-supervised cross-modal manner, temporally dense video representations that capture factors such as facial movements, expression, and identity. Second, we use these learned representations as targets to be predicted by our forgery detector along with the usual binary forgery classification task; this encourages it to base its real/fake decision on said factors. We show that our method achieves state-of-the-art performance on cross-manipulation generalisation and robustness experiments, and examine the factors that contribute to its performance. Our results suggest that leveraging natural and unlabelled videos is a promising direction for the development of more robust face forgery detectors.
-
Novel classes frequently arise in our dynamically changing world, e.g., new users in the authentication system, and a machine learning model should recognize new classes without forgetting old ones. This scenario becomes more challenging when new class instances are insufficient, which is called few-shot class-incremental learning (FSCIL). Current methods handle incremental learning retrospectively by making the updated model similar to the old one. By contrast, we suggest learning prospectively to prepare for future updates, and propose ForwArd Compatible Training (FACT) for FSCIL. Forward compatibility requires future new classes to be easily incorporated into the current model based on the current stage data, and we seek to realize it by reserving embedding space for future new classes. In detail, we assign virtual prototypes to squeeze the embedding of known classes and reserve for new ones. Besides, we forecast possible new classes and prepare for the updating process. The virtual prototypes allow the model to accept possible updates in the future, which act as proxies scattered among embedding space to build a stronger classifier during inference. FACT efficiently incorporates new classes with forward compatibility and meanwhile resists forgetting of old ones. Extensive experiments validate FACT's state-of-the-art performance. Code is available at: https://github.com/zhoudw-zdw/CVPR22-Fact
-
Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation. However, more recent works find that existing differentiable NAS techniques struggle to outperform naive baselines, yielding deteriorative architectures as the search proceeds. Rather than directly optimizing the architecture parameters, this paper formulates the neural architecture search as a distribution learning problem through relaxing the architecture weights into Gaussian distributions. By leveraging the natural-gradient variational inference (NGVI), the architecture distribution can be easily optimized based on existing codebases without incurring more memory and computational consumption. We demonstrate how the differentiable NAS benefits from Bayesian principles, enhancing exploration and improving stability. The experimental results on NAS benchmark datasets confirm the significant improvements the proposed framework can make. In addition, instead of simply applying the argmax on the learned parameters, we further leverage the recently-proposed training-free proxies in NAS to select the optimal architecture from a group architectures drawn from the optimized distribution, where we achieve state-of-the-art results on the NAS-Bench-201 and NAS-Bench-1shot1 benchmarks. Our best architecture in the DARTS search space also obtains competitive test errors with 2.37%, 15.72%, and 24.2% on CIFAR-10, CIFAR-100, and ImageNet, respectively.
-
Recently, both long-tailed recognition and object tracking have made great advances individually. TAO benchmark presented a mixture of the two, long-tailed object tracking, in order to further reflect the aspect of the real-world. To date, existing solutions have adopted detectors showing robustness in long-tailed distributions, which derive per-frame results. Then, they used tracking algorithms that combine the temporally independent detections to finalize tracklets. However, as the approaches did not take temporal changes in scenes into account, inconsistent classification results in videos led to low overall performance. In this paper, we present a set classifier that improves accuracy of classifying tracklets by aggregating information from multiple viewpoints contained in a tracklet. To cope with sparse annotations in videos, we further propose augmentation of tracklets that can maximize data efficiency. The set classifier is plug-and-playable to existing object trackers, and highly improves the performance of long-tailed object tracking. By simply attaching our method to QDTrack on top of ResNet-101, we achieve the new state-of-the-art, 19.9% and 15.7% TrackAP50 on TAO validation and test sets, respectively.
-
Canonical correlation analysis (CCA) matters in multiview representation learning. But, CCA and its most variants are essentially based on explicit or implicit covariance matrices. It means that they have no ability to model the nonlinear relationship among features due to intrinsic linearity of covariance. In this paper, we address the preceding problem and propose a novel canonical F-correlation framework by exploring and exploiting the nonlinear relationship between different features. The framework projects each feature rather than observation into a certain new space by an arbitrary nonlinear mapping, thus resulting in more flexibility in real applications. With this framework as a tool, we propose a correlative covariation projection (CCP) method by using an explicit nonlinear mapping. Moreover, we further propose a multiset version of CCP dubbed MCCP for learning compact representation of more than two views. The proposed MCCP is solved by an iterative method, and we prove the convergence of this iteration. A series of experimental results on six benchmark datasets demonstrate the effectiveness of our proposed CCP and MCCP methods.
-
Current Image captioning (IC) methods predict textual words sequentially based on the input visual information from the visual feature extractor and the partially generated sentence information. However, for most cases, the partially generated sentence may dominate the target word prediction due to the insufficiency of visual information, making the generated descriptions irrelevant to the content of the given image. In this paper, we propose a Dual Information Flow Network (DIFNet) to address this issue, which takes segmentation feature as another visual information source to enhance the contribution of visual information for prediction. To maximize the use of two information flows, we also propose an effective feature fusion module termed Iterative Independent Layer Normalization (IILN) which can condense the most relevant inputs while retraining modality-specific information in each flow. Experiments show that our method is able to enhance the dependence of prediction on visual information, making word prediction more focused on the visual content, and thus achieve new state-of-the-art performance on the MSCOCO dataset, e.g., 136.2 CIDEr on COCO Karpathy test split.
-
Weakly supervised object localization (WSOL) focuses on localizing objects only with the supervision of image-level classification masks. Most previous WSOL methods follow the classification activation map (CAM) that localizes objects based on the classification structure with the multi-instance learning (MIL) mechanism. However, the MIL mechanism makes CAM only activate discriminative object parts rather than the whole object, weakening its performance for localizing objects. To avoid this problem, this work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects. Under this perspective, a DA-WSOL pipeline is designed to better engage DA approaches into WSOL to enhance localization performance. It utilizes a proposed target sampling strategy to select different types of target samples. Based on these types of target samples, domain adaption localization (DAL) loss is elaborated. It aligns the feature distribution between the two domains by DA and makes the estimator perceive target domain cues by Universum regularization. Experiments show that our pipeline outperforms SOTA methods on multi benchmarks. Code are released at https://github.com/zh460045050/DA-WSOL_CVPR2022.
-
Multi-modal video similarity evaluation is important for video recommendation systems such as video de-duplication, relevance matching, ranking, and diversity control. However, there still lacks a benchmark dataset that can support supervised training and accurate evaluation. In this paper, we propose the Tencent-MVSE dataset, which is the first benchmark dataset for the multi-modal video similarity evaluation task. The Tencent-MVSE dataset contains video pairs similarity annotations, and diverse metadata including Chinese title, automatic speech recognition (ASR) text, as well as human-annotated categories/tags. We provide a simple baseline with a multi-modal Transformer architecture to perform supervised multi-modal video similarity evaluation. We also explore pre-training strategies to make use of the unpaired data. The whole dataset as well as our baseline will be released to promote the development of the multi-modal video similarity evaluation. The dataset has been released in https://tencent-mvse.github.io/.
-
The key challenge for few-shot semantic segmentation (FSS) is how to tailor a desirable interaction among support and query features and/or their prototypes, under the episodic training scenario. Most existing FSS methods implement such support/query interactions by solely leveraging \it plain operations -- e.g., cosine similarity and feature concatenation -- for segmenting the query objects. However, these interaction approaches usually cannot well capture the intrinsic object details in the query images that are widely encountered in FSS, e.g., if the query object to be segmented has holes and slots, inaccurate segmentation almost always happens. To this end, we propose a dynamic prototype convolution network (DPCN) to fully capture the aforementioned intrinsic details for accurate FSS. Specifically, in DPCN, a dynamic convolution module (DCM) is firstly proposed to generate dynamic kernels from support foreground, then information interaction is achieved by convolution operations over query features using these kernels. Moreover, we equip DPCN with a support activation module (SAM) and a feature filtering module (FFM) to generate pseudo mask and filter out background information for the query images, respectively. SAM and FFM together can mine enriched context information from the query features. Our DPCN is also flexible and efficient under the k-shot FSS setting. Extensive experiments on PASCAL-5^i and COCO-20^i show that DPCN yields superior performances under both 1-shot and 5-shot settings.
-
State-of-the-art fully intrinsic network for non-rigid shape matching are unable to disambiguate between shape inner symmetries. Meanwhile, recent advances in the functional map framework allow to enforce orientation preservation using a functional representation for tangent vector field transfer, through so-called complex functional maps. Using this representation, we propose a new deep learning approach to learn orientation-aware features in a fully unsupervised setting. Our architecture is built on DiffusionNet, which makes our method robust to discretization changes, while adding a vector-field-based loss, which promotes orientation preservation without using (often unstable) extrinsic descriptors. Our source code is available at: https://github.com/nicolasdonati/DUO-FM
-
Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network with coarse-grained (i.e.,point-, scribble-, and block-wise) supervisions, where only a small proportion of pixels are labeled in each image. In this paper, we propose a novel tree energy loss for SASS by providing semantic guidance for unlabeled pixels. The tree energy loss represents images as minimum spanning trees to model both low-level and high-level pair-wise affinities. By sequentially applying these affinities to the network prediction, soft pseudo labels for unlabeled pixels are generated in a coarse-to-fine manner, resulting in dynamic online self-training. The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss. Compared with previous SASS methods, our method requires no multi-stage training strategies, alternating optimization procedures, additional supervised data, or time-consuming post-processing while outperforming them in all types of supervised settings. Code is available at https://github.com/megvii-research/TreeEnergyLoss.
-
Post-training quantization compresses a neural network within few hours with only a small unlabeled calibration set. However, so far it has been only discussed and empirically demonstrated in the context of uniform quantization on convolutional neural networks. We thus propose a new post-training non-uniform quantization method, called Mr.BiQ, allowing low bit-width quantization even on Transformer models. In particular, we leverage multi-level binarization for weights while allowing activations to be represented as various data formats (e.g., INT8, bfloat16, binary-coding, and FP32). Unlike conventional methods which optimize full-precision weights first, then decompose the weights into quantization parameters, Mr.BiQ recognizes the quantization parameters (i.e., scaling factors and bit-code) as directly and jointly learnable parameters during the optimization. To verify the superiority of the proposed quantization scheme, we test Mr.BiQ on various models including convolutional neural networks and Transformer models. According to experimental results, Mr.BiQ shows significant improvement in terms of accuracy when the bit-width of weights is equal to 2: up to 5.35 p.p. improvement in CNNs, up to 4.23 p.p. improvement in Vision Transformers, and up to 3.37 point improvement in Transformers for NLP.
-
In this paper, we propose a transformer-based image matting model called MatteFormer, which takes full advantage of trimap information in the transformer block. Our method first introduces a prior-token which is a global representation of each trimap region (e.g. foreground, background and unknown). These prior-tokens are used as global priors and participate in the self-attention mechanism of each block. Each stage of the encoder is composed of PAST (Prior-Attentive Swin Transformer) block, which is based on the Swin Transformer block, but differs in a couple of aspects: 1) It has PA-WSA (Prior-Attentive Window Self-Attention) layer, performing self-attention not only with spatial-tokens but also with prior-tokens. 2) It has prior-memory which saves prior-tokens accumulatively from the previous blocks and transfers them to the next block. We evaluate our MatteFormer on the commonly used image matting datasets: Composition-1k and Distinctions-646. Experiment results show that our proposed method achieves state-of-the-art performance with a large margin. Our codes are available at https://github.com/webtoon/matteformer.
-
It is challenging to annotate large-scale datasets for supervised video shadow detection methods. Using a model trained on labeled images to the video frames directly may lead to high generalization error and temporal inconsistent results. In this paper, we address these challenges by proposing a Spatio-Temporal Interpolation Consistency Training (STICT) framework to rationally feed the unlabeled video frames together with the labeled images into an image shadow detection network training. Specifically, we propose the Spatial and Temporal ICT, in which we define two new interpolation schemes, i.e., the spatial interpolation and the temporal interpolation. We then derive the spatial and temporal interpolation consistency constraints accordingly for enhancing generalization in the pixel-wise classification task and for encouraging temporal consistent predictions, respectively. In addition, we design a Scale-Aware Network for multi-scale shadow knowledge learning in images, and propose a scale-consistency constraint to minimize the discrepancy among the predictions at different scales. Our proposed approach is extensively validated on the ViSha dataset and a self-annotated dataset. Experimental results show that, even without video labels, our approach is better than most state of the art supervised, semi-supervised or unsupervised image/video shadow detection methods and other methods in related tasks. Code and dataset are available at https://github.com/yihong-97/STICT.
-
Recent progress in few-shot learning promotes a more realistic cross-domain setting, where the source and target datasets are in different domains. Due to the domain gap and disjoint label spaces between source and target datasets, their shared knowledge is extremely limited. This encourages us to explore more information in the target domain rather than to overly elaborate training strategies on the source domain as in many existing methods. Hence, we start from a generic representation pre-trained by a cross-entropy loss and a conventional distance-based classifier, along with an image retrieval view, to employ a re-ranking process to calibrate a target distance matrix by discovering the k-reciprocal neighbours within the task. Assuming the pre-trained representation is biased towards the source, we construct a non-linear subspace to minimise task-irrelevant features therewithin while keep more transferrable discriminative information by a hyperbolic tangent transformation. The calibrated distance in this target-aware non-linear sub-space is complementary to that in the pre-trained representation. To impose such distance calibration information onto the pre-trained representation, a Kullback-Leibler divergence loss is employed to gradually guide the model towards the calibrated distance-based distribution. Extensive evaluations on eight target domains show that this target ranking calibration process can improve conventional distance-based classifiers in few-shot learning.
-
Interpreting objects with basic geometric primitives has long been studied in computer vision. Among geometric primitives, superquadrics are well known for their ability to represent a wide range of shapes with few parameters. However, as the first and foremost step, recovering superquadrics accurately and robustly from 3D data still remains challenging. The existing methods are subject to local optima and sensitive to noise and outliers in real-world scenarios, resulting in frequent failure in capturing geometric shapes. In this paper, we propose the first probabilistic method to recover superquadrics from point clouds. Our method builds a Gaussian-uniform mixture model (GUM) on the parametric surface of a superquadric, which explicitly models the generation of outliers and noise. The superquadric recovery is formulated as a Maximum Likelihood Estimation (MLE) problem. We propose an algorithm, Expectation, Maximization, and Switching (EMS), to solve this problem, where: (1) outliers are predicted from the posterior perspective; (2) the superquadric parameter is optimized by the trust-region reflective algorithm; and (3) local optima are avoided by globally searching and switching among parameters encoding similar superquadrics. We show that our method can be extended to the multi-superquadrics recovery for complex objects. The proposed method outperforms the state-of-the-art in terms of accuracy, efficiency, and robustness on both synthetic and real-world datasets. The code is at http://github.com/bmlklwx/EMS-superquadric_fitting.git.
-
We combine neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions. Our method, Dream Fields, can generate the geometry and color of a wide range of objects without 3D supervision. Due to the scarcity of diverse, captioned 3D data, prior methods only generate objects from a handful of categories, such as ShapeNet. Instead, we guide generation with image-text models pre-trained on large datasets of captioned images from the web. Our method optimizes a Neural Radiance Field from many camera views so that rendered images score highly with a target caption according to a pre-trained CLIP model. To improve fidelity and visual quality, we introduce simple geometric priors, including sparsityinducing transmittance regularization, scene bounds, and new MLP architectures. In experiments, Dream Fields produce realistic, multi-view consistent object geometry and color from a variety of natural language captions.
-
A range of video modeling tasks, from optical flow to multiple object tracking, share the same fundamental challenge: establishing space-time correspondence. Yet, approaches that dominate each space differ. We take a step towards bridging this gap by extending the recent contrastive random walk formulation to much more dense, pixel-level space-time graphs. The main contribution is introducing hierarchy into the search problem by computing the transition matrix in a coarse-to-fine manner, forming a multiscale contrastive random walk. This establishes a unified technique for self-supervised learning of optical flow, keypoint tracking, and video object segmentation. Experiments demonstrate that, for each of these tasks, our unified model achieves performance competitive with strong self-supervised approaches specific to that task.
-
Person image generation aims to perform non-rigid deformation on source images, which generally requires unaligned data pairs for training. Recently, self-supervised methods express great prospects in this task by merging the disentangled representations for self-reconstruction. However, such methods fail to exploit the spatial correlation between the disentangled features. In this paper, we propose a Self-supervised Correlation Mining Network (SCM-Net) to rearrange the source images in the feature space, in which two collaborative modules are integrated, Decomposed Style Encoder (DSE) and Correlation Mining Module (CMM). Specifically, the DSE first creates unaligned pairs at the feature level. Then, the CMM establishes the spatial correlation field for feature rearrangement. Eventually, a translation module transforms the rearranged features to realistic results. Meanwhile, for improving the fidelity of cross-scale pose transformation, we propose a graph based Body Structure Retaining Loss (BSR Loss) to preserve reasonable body structures on half body to full body generation. Extensive experiments conducted on DeepFashion dataset demonstrate the superiority of our method compared with other supervised and unsupervised approaches. Furthermore, satisfactory results on face generation show the versatility of our method in other deformation tasks.
-
Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We analyze our dataset and compare it with five VQA-Grounding datasets to demonstrate what makes it similar and different. We then evaluate the SOTA VQA and VQA-Grounding models and demonstrate that current SOTA algorithms often fail to identify the correct visual evidence where the answer is located. These models regularly struggle when the visual evidence occupies a small fraction of the image, for images that are higher quality, as well as for visual questions that require skills in text recognition. The dataset, evaluation server, and leaderboard all can be found at the following link: https://vizwiz.org/tasks-and-datasets/answer-grounding-for-vqa/.
-
Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial memory cost. To efficiently learn multiple downstream tasks we introduce Task Adaptive Parameter Sharing (TAPS), a simple method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. This enables multi-task learning while minimizing the resources used and avoids catastrophic forgetting and competition between tasks. TAPS solves a joint optimization problem which determines both the layers that are shared with the base model and the value of the task-specific weights. Further, a sparsity penalty on the number of active layers promotes weight sharing with the base model. Compared to other methods, TAPS retains a high accuracy on the target tasks while still introducing only a small number of task-specific parameters. Moreover, TAPS is agnostic to the particular architecture used and requires only minor changes to the training scheme. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
-
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we propose a sparse set of instance activation maps, as a new object representation, to highlight informative regions for each foreground object. Then instance-level features are obtained by aggregating features according to the highlighted regions for recognition and segmentation. Moreover, based on bipartite matching, the instance activation maps can predict objects in a one-to-one style, thus avoiding non-maximum suppression (NMS) in post-processing. Owing to the simple yet effective designs with instance activation maps, SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark, which significantly outperforms the counterparts in terms of speed and accuracy. Code and models are available at https://github.com/hustvl/SparseInst.
-
Color image stitching is a challenging task in real-world applications. This paper first proposes a quaternion rank-1 alignment (QR1A) model for high-precision color image alignment. To solve the optimization problem of QR1A, we develop a nested iterative algorithm under the framework of complex-valued alternating direction method of multipliers. To quantitatively evaluate image stitching performance, we propose a perceptual seam quality (PSQ) measure to calculate misalignments of local regions along the seamline. Using QR1A and PSQ, we further propose an automatic color image stitching (ACIS-QR1A) framework. In this framework, the automatic strategy and iterative learning strategy are developed to simultaneously learn the optimal seamline and local alignment. Extensive experiments on challenging datasets demonstrate that the proposed ACIS-QR1A is able to obtain high-quality stitched images under several difficult scenarios including large parallax, low textures, moving objects, large occlusions or/and their combinations.
-
The limited availability of annotated data often hinders real-world applications of machine learning. To efficiently learn from small quantities of multimodal data, we leverage the linguistic knowledge from a large pre-trained language model (PLM) and quickly adapt it to new domains of image captioning. To effectively utilize a pretrained model, it is critical to balance the visual input and prior linguistic knowledge from pretraining. We propose VisualGPT, which employs a novel self-resurrecting encoder-decoder attention mechanism to quickly adapt the PLM with a small amount of in-domain image-text data. The proposed self-resurrecting activation unit produces sparse activations that prevent accidental overwriting of linguistic knowledge. When trained on 0.1%, 0.5% and 1% of the respective training sets, VisualGPT surpasses the best baseline by up to 10.0% CIDEr on MS COCO and 17.9% CIDEr on Conceptual Captions. Furthermore, VisualGPT achieves the state-of-the-art result on IU X-ray, a medical report generation dataset. Our code is available at https://github.com/Vision-CAIR/VisualGPT.
-
This paper aims to address the single image gaze target detection problem. Conventional methods either focus on 2D visual cues or exploit additional depth information in a very coarse manner. In this work, we propose to explicitly and effectively model 3D geometry under challenging scenario where only 2D annotations are available. We first obtain 3D point clouds of given scene with estimated depth and reference objects. Then we figure out the front-most points in all possible 3D directions of given person. These points are later leveraged in our ESCNet model. Specifically, ESCNet consists of geometry and scene parsing modules. The former produces an initial heatmap inferring the probability that each front-most point has been looking at according to estimated 3D gaze direction. And the latter further explores scene contextual cues to regulate detection results. We validate our idea on two publicly available dataset, GazeFollow and VideoAttentionTarget, and demonstrate the state-of-the-art performance. Our method also beats the human in terms of AUC on GazeFollow.
-
Co-salient object detection (CoSOD) has recently achieved significant progress and played a key role in retrieval-related tasks. However, it inevitably poses an entirely new safety and security issue, i.e., highly personal and sensitive content can potentially be extracting by powerful CoSOD methods. In this paper, we address this problem from the perspective of adversarial attacks and identify a novel task: adversarial co-saliency attack. Specially, given an image selected from a group of images containing some common and salient objects, we aim to generate an adversarial version that can mislead CoSOD methods to predict incorrect co-salient regions. Note that, compared with general white-box adversarial attacks for classification, this new task faces two additional challenges: (1) low success rate due to the diverse appearance of images in the group; (2) low transferability across CoSOD methods due to the considerable difference between CoSOD pipelines. To address these challenges, we propose the very first black-box joint adversarial exposure and noise attack (Jadena), where we jointly and locally tune the exposure and additive perturbations of the image according to a newly designed high-feature-level contrast-sensitive loss function. Our method, without any information on the state-of-the-art CoSOD methods, leads to significant performance degradation on various co-saliency detection datasets and makes the co-salient objects undetectable. This can have strong practical benefits in properly securing the large number of personal photos currently shared on the Internet. Moreover, our method is potential to be utilized as a metric for evaluating the robustness of CoSOD methods.
-
As lovely as bunnies are, your sketched version would probably not do it justice (Fig. 1). This paper recognises this very problem and studies sketch quality measurement for the first time -- letting you find these badly drawn ones. Our key discovery lies in exploiting the magnitude (L2 norm) of a sketch feature as a quantitative quality metric. We propose Geometry-Aware Classification Layer (GACL), a generic method that makes feature-magnitude-as-quality-metric possible and importantly does it without the need for specific quality annotations from humans. GACL sees feature magnitude and recognisability learning as a dual task, which can be simultaneously optimised under a neat cross-entropy classification loss. GACL is lightweight with theoretic guarantees and enjoys a nice geometric interpretation to reason its success. We confirm consistent quality agreements between our GACL-induced metric and human perception through a carefully designed human study. Last but not least, we demonstrate three practical sketch applications enabled for the first time using our quantitative quality metric. Code will be made publicly available.
-
We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a set of extrusion cylinders. Reverse engineering from a raw geometry to a CAD model is an essential task to enable manipulation of the 3D data in shape editing software and thus expand their usages in many downstream applications. Particularly, the form of CAD models having a sequence of extrusion cylinders --- a 2D sketch plus an extrusion axis and range --- and their boolean combinations is not only widely used in the CAD community/software but also has great expressivity of shapes, compared to having limited types of primitives (e.g., planes, spheres, and cylinders). In this work, we introduce a neural network that solves the extrusion cylinder decomposition problem in a geometry-grounded way by first learning underlying geometric proxies. Precisely, our approach first predicts per-point segmentation, base/barrel labels and normals, then estimates for the underlying extrusion parameters in differentiable and closed-form formulations. Our experiments show that our approach demonstrates the best performance on two recent CAD datasets, Fusion Gallery and DeepCAD, and we further showcase our approach on reverse engineering and editing.
-
Time-of-flight (ToF) sensors provide an image modality fueling applications across domains, including lidar in autonomous driving, robotics, and augmented reality. Conventional ToF imaging methods estimate the depth of a scene point by sending pulses of light into a scene and measuring the time of flight of the first arriving photons that are returned from the scene, the ones directly reflected from a scene surface without any temporal delay. As such, all photons following this first response are typically considered as unwanted noise, including multi-bounce and sub-surface scattering of real-world materials. While multi-bounce scene interreflections have been extensively in recent work on non-line-of-sight imaging, we investigate temporally resolved sub-surface scattering in this work. We depart from the principle of first arrival and instead propose an all-photon ToF imaging method relying on polarization changes that analyzes both first- and late-arriving photons for shape and material scene understanding. To this end, we propose a novel capture method, reflectance model, and a reconstruction algorithm that exploits the polarization state of light changes after reflection in addition to ToF information. The proposed temporal-polarimetric imaging method allows for accurate geometric and material information of the scene by utilizing all photons captured by the system, decoded by polarization cues, outperforming all tested existing methods in simulation and experimentally.
-
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are available at https://github.com/Vegetebird/MHFormer.
-
We propose a new method for reconstructing controllable implicit 3D human models from sparse multi-view RGB videos. Our method defines the neural scene representation on the mesh surface points and signed distances from the surface of a human body mesh. We identify an indistinguishability issue that arises when a point in 3D space is mapped to its nearest surface point on a mesh for learning surface-aligned neural scene representation. To address this issue, we propose projecting a point onto a mesh surface using a barycentric interpolation with modified vertex normals. Experiments with the ZJU-MoCap and Human3.6M datasets show that our approach achieves a higher quality in a novel-view and novel-pose synthesis than existing methods. We also demonstrate that our method easily supports the control of body shape and clothes. Project page: https://pfnet-research.github.io/surface-aligned-nerf/.
-
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g., FixMatch). Without specifically utilizing the temporal dynamics and inherent multimodal attributes, their results could be suboptimal. To better leverage the encoded temporal information in videos, we introduce temporal gradient as an additional modality for more attentive feature extraction in this paper. To be specific, our method explicitly distills the fine-grained motion representations from temporal gradient (TG) and imposes consistency across different modalities (i.e., RGB and TG). The performance of semi-supervised action recognition is significantly improved without additional computation or parameters during inference. Our method achieves the state-of-the-art performance on three video action recognition benchmarks (i.e., Kinetics-400, UCF-101, and HMDB-51) under several typical semi-supervised settings (i.e., different ratios of labeled data).
-
In this work, we explore the challenging task of generating 3D shapes from text. Beyond the existing works, we propose a new approach for text-guided 3D shape generation, capable of producing high-fidelity shapes with colors that match the given text description. This work has several technical contributions. First, we decouple the shape and color predictions for learning features in both texts and shapes, and propose the word-level spatial transformer to correlate word features from text with spatial features from shape. Also, we design a cyclic loss to encourage consistency between text and shape, and introduce the shape IMLE to diversify the generated shapes. Further, we extend the framework to enable text-guided shape manipulation. Extensive experiments on the largest existing text-shape benchmark manifest the superiority of this work. The code and the models are available at https://github.com/liuzhengzhe/Towards-Implicit Text-Guided-Shape-Generation.
-
Human speech is often accompanied by body gestures including arm and hand gestures. We present a method that reenacts a high-quality video with gestures matching a target speech audio. The key idea of our method is to split and re-assemble clips from a reference video through a novel video motion graph encoding valid transitions between clips. To seamlessly connect different clips in the reenactment, we propose a pose-aware video blending network which synthesizes video frames around the stitched frames between two clips. Moreover, we developed an audio-based gesture searching algorithm to find the optimal order of the reenacted frames. Our system generates reenactments that are consistent with both the audio rhythms and the speech content. We evaluate our synthesized video quality quantitatively, qualitatively, and with user studies, demonstrating that our method produces videos of much higher quality and consistency with the target audio compared to previous work and baselines.
-
Image collage task aims to create an informative and visual-aesthetic visual summarization for an image collection. While several recent works exploit tree-based algorithm to preserve image content better, all of them resort to hand-crafted adjustment rules to optimize the collage tree structure, leading to the failure of fully exploring the structure space of collage tree. Our key idea is to soften the discrete tree structure space into a continuous probability space. We propose SoftCollage, a novel method that employs a neural-based differentiable probabilistic tree generator to produce the probability distribution of correlation-preserving collage tree conditioned on deep image feature, aspect ratio and canvas size. The differentiable characteristic allows us to formulate the tree-based collage generation as a differentiable process and directly exploit gradient to optimize the collage layout in the level of probability space in an end-to-end manner. To facilitate image collage research, we propose AIC, a large-scale public-available annotated dataset for image collage evaluation. Extensive experiments on the introduced dataset demonstrate the superior performance of the proposed method. Data and codes are available at https://github.com/ChineseYjh/SoftCollage.
-
Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function. While this inductive bias integrates valuable domain knowledge, it limits the expressivity of the tracking network. In this work, we therefore propose a tracker architecture employing a Transformer-based model prediction module. Transformers capture global relations with little inductive bias, allowing it to learn the prediction of more powerful target models. We further extend the model predictor to estimate a second set of weights that are applied for accurate bounding box regression. The resulting tracker relies on training and on test frame information in order to predict all weights transductively. We train the proposed tracker end-to-end and validate its performance by conducting comprehensive experiments on multiple tracking datasets. Our tracker sets a new state of the art on three benchmarks, achieving an AUC of 68.5% on the challenging LaSOT dataset.
-
The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields. One major reason is its ease of integration into deep learning frameworks. To allow for an efficient training of respective neural networks, we propose an algorithm that obtains analytical gradients of a Sinkhorn layer via implicit differentiation. In comparison to prior work, our framework is based on the most general formulation of the Sinkhorn operator. It allows for any type of loss function, while both the target capacities and cost matrices are differentiated jointly. We further construct error bounds of the resulting algorithm for approximate inputs. Finally, we demonstrate that for a number of applications, simply replacing automatic differentiation with our algorithm directly improves the stability and accuracy of the obtained gradients. Moreover, we show that it is computationally more efficient, particularly when resources like GPU memory are scarce.
-
Monocular 6D pose estimation is a fundamental task in computer vision. Existing works often adopt a twostage pipeline by establishing correspondences and utilizing a RANSAC algorithm to calculate 6 degrees-of-freedom (6DoF) pose. Recent works try to integrate differentiable RANSAC algorithms to achieve an end-to-end 6D pose estimation. However, most of them hardly consider the geometric features in 3D space, and ignore the topology cues when performing differentiable RANSAC algorithms. To this end, we proposed a Depth-Guided Edge Convolutional Network (DGECN) for 6D pose estimation task. We have made efforts from the following three aspects: 1) We take advantages of estimated depth information to guide both the correspondences-extraction process and the cascaded differentiable RANSAC algorithm with geometric information. 2)We leverage the uncertainty of the estimated depth map to improve accuracy and robustness of the output 6D pose. 3) We propose a differentiable Perspective-n-Point(PnP) algorithm via edge convolution to explore the topology relations between 2D-3D correspondences. Experiments demonstrate that our proposed network outperforms current works on both effectiveness and efficiency.
-
Understanding realistic visual scene images together with language descriptions is a fundamental task towards generic visual understanding. Previous works have shown compelling comprehensive results by building hierarchical structures for visual scenes (e.g., scene graphs) and natural languages (e.g., dependency trees), individually. However, how to construct a joint vision-language (VL) structure has barely been investigated. More challenging but worthwhile, we introduce a new task that targets on inducing such a joint VL structure in an unsupervised manner. Our goal is to bridge the visual scene graphs and linguistic dependency trees seamlessly. Due to the lack of VL structural data, we start by building a new dataset VLParse. Rather than using labor-intensive labeling from scratch, we propose an automatic alignment procedure to produce coarse structures followed by human refinement to produce high-quality ones. Moreover, we benchmark our dataset by proposing a contrastive learning (CL)-based framework VLGAE, short for Vision-Language Graph Autoencoder. Our model obtains superior performance on two derived tasks, i.e., language grammar induction and VL phrase grounding. Ablations show the effectiveness of both visual cues and dependency relationships on fine-grained VL structure construction.
-
Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captioned images covering many novel classes and then finetune it on limited base classes with mask annotations. However, the high-level textual information learned from caption pretraining alone cannot effectively encode the details required for pixel-wise segmentation. To address this, we propose a cross-modal pseudo-labeling framework, which generates training pseudo masks by aligning word semantics in captions with visual features of object masks in images. Thus, our framework is capable of labeling novel classes in captions via their word semantics to self-train a student model. To account for noises in pseudo masks, we design a robust student model that selectively distills mask knowledge by estimating the mask noise levels, hence mitigating the adverse impact of noisy pseudo masks. By extensive experiments, we show the effectiveness of our framework, where we significantly improve mAP score by 4.5% on MS-COCO and 5.1% on the large-scale Open Images & Conceptual Captions datasets compared to the state-of-the-art.
-
Our target is to learn visual correspondence from unlabeled videos. We develop LIIR, a locality-aware inter-and intra-video reconstruction framework that fills in three missing pieces, i.e., instance discrimination, location awareness, and spatial compactness, of self-supervised correspondence learning puzzle. First, instead of most existing efforts focusing on intra-video self-supervision only, we exploit cross video affinities as extra negative samples within a unified, inter-and intra-video reconstruction scheme. This enables instance discriminative representation learning by contrasting desired intra-video pixel association against negative inter-video correspondence. Second, we merge position information into correspondence matching, and design a position shifting strategy to remove the side-effect of position encoding during inter-video affinity computation, making our LIIR location-sensitive. Third, to make full use of the spatial continuity nature of video data, we impose a compactness-based constraint on correspondence matching, yielding more sparse and reliable solutions. The learned representation surpasses self-supervised state-of-the-arts on label propagation tasks including objects, semantic parts, and keypoints.
-
3D object detection using LiDAR data is an indispensable component for autonomous driving systems. Yet, only a few LiDAR-based 3D object detection methods leverage segmentation information to further guide the detection process. In this paper, we propose a novel multi-task framework that jointly performs 3D object detection and panoptic segmentation. In our method, the 3D object detection backbone, which is in Bird's-Eye-View (BEV) plane, is augmented by the injection of Range-View (RV) feature maps from the 3D panoptic segmentation backbone. This enables the detection backbone to leverage multi-view information to address the shortcomings of each projection view. Furthermore, foreground semantic information is incorporated to ease the detection task by highlighting the locations of each object class in the feature maps. Finally, a new center density heatmap generated based on the instance-level information further guides the detection backbone by suggesting possible box center locations for objects in the BEV plane. Our method works with any BEV-based 3D object detection method, and as shown by extensive experiments on the nuScenes dataset, it provides significant performance gains. Notably, the proposed method based on a single-stage CenterPoint 3D object detection network achieved state-of-the-art performance on nuScenes 3D Detection Benchmark with 67.3 NDS.
-
Explainable visual question answering (VQA) models have been developed with neural modules and query-based knowledge incorporation to answer knowledge-requiring questions. Yet, most reasoning methods cannot effectively generate queries or incorporate external knowledge during the reasoning process, which may lead to suboptimal results. To bridge this research gap, we present Query and Attention Augmentation, a general approach that augments neural module networks to jointly reason about visual and external knowledge. To take both knowledge sources into account during reasoning, it parses the input question into a functional program with queries augmented through a novel reinforcement learning method, and jointly directs augmented attention to visual and external knowledge based on intermediate reasoning results. With extensive experiments on multiple VQA datasets, our method demonstrates significant performance, explainability, and generalizability over state-of-the-art models in answering questions requiring different extents of knowledge. Our source code is available at https://github.com/SuperJohnZhang/QAA.
-
We present a novel task and dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning, which we call Winoground. Given two images and two captions, the goal is to match them correctly--but crucially, both captions contain a completely identical set of words, only in a different order. The dataset was carefully hand-curated by expert annotators and is labeled with a rich set of fine-grained tags to assist in analyzing model performance. We probe a diverse range of state-of-the-art vision and language models and find that, surprisingly, none of them do much better than chance. Evidently, these models are not as skilled at visio-linguistic compositional reasoning as we might have hoped. We perform an extensive analysis to obtain insights into how future work might try to mitigate these models' shortcomings. We aim for Winoground to serve as a useful evaluation set for advancing the state of the art and driving further progress in the field. The dataset is available at https://huggingface.co/datasets/facebook/winoground.
-
In this paper, we propose a novel method to realize multi-modal image registration and fusion in a mutually reinforcing framework, termed as RFNet. We handle the registration in a coarse-to-fine fashion. For the first time, we exploit the feedback of image fusion to promote the registration accuracy rather than treating them as two separate issues. The fine-registered results also improve the fusion performance. Specifically, for image registration, we solve the bottlenecks of defining registration metrics applicable for multi-modal images and facilitating the network convergence. The metrics are defined based on image translation and image fusion respectively in the coarse and fine stages. The convergence is facilitated by the designed metrics and a deformable convolution-based network. For image fusion, we focus on texture preservation, which not only increases the information amount and quality of fusion results but also improves the feedback of fusion results. The proposed method is evaluated on multi-modal images with large global parallaxes, images with local misalignments and aligned images to validate the performances of registration and fusion. The results in these cases demonstrate the effectiveness of our method.
-
Generic event boundary detection is an important yet challenging task in video understanding, which aims at detecting the moments where humans naturally perceive event boundaries. The main challenge of this task is perceiving various temporal variations of diverse event boundaries. To this end, this paper presents an effective and end-to-end learnable framework (DDM-Net). To tackle the diversity and complicated semantics of event boundaries, we make three notable improvements. First, we construct a feature bank to store multi-level features of space and time, prepared for difference calculation at multiple scales. Second, to alleviate inadequate temporal modeling of previous methods, we present dense difference maps (DDM) to comprehensively characterize the motion pattern. Finally, we exploit progressive attention on multi-level DDM to jointly aggregate appearance and motion clues. As a result, DDM-Net respectively achieves a significant boost of 14% and 8% on Kinetics-GEBD and TAPOS benchmark, and outperforms the top-1 winner solution of LOVEU Challenge@CVPR 2021 without bells and whistles. The state-of-the-art result demonstrates the effectiveness of richer motion representation and more sophisticated aggregation, in handling the diversity of generic event boundary detection. The code is made available at https://github.com/MCG-NJU/DDM.
-
Over the years various methods have been proposed for the problem of object detection. Recently, we have witnessed great strides in this domain owing to the emergence of powerful deep neural networks. However, there are typically two main assumptions common among these approaches. First, the model is trained on a fixed training set and is evaluated on a pre-recorded test set. Second, the model is kept frozen after the training phase, so no further updates are performed after the training is finished. These two assumptions limit the applicability of these methods to real-world settings. In this paper, we propose Interactron, a method for adaptive object detection in an interactive setting, where the goal is to perform object detection in images observed by an embodied agent navigating in different environments. Our idea is to continue training during inference and adapt the model at test time without any explicit supervision via interacting with the environment. Our adaptive object detection model provides a 11.8 point improvement in AP (and 19.1 points in AP50) over DETR, a recent, high-performance object detector. Moreover, we show that our object detection model adapts to environments with completely different appearance characteristics, and its performance is on par with a model trained with full supervision for those environments. We will release the code to help ease future research in this domain.
-
We propose a novel approach to 3D scene painting using a configurable 3D scene layout. Our approach takes a 3D scene with semantic class labels as input and trains a 3D scene painting network that synthesizes color values for the input 3D scene. We exploit an off-the-shelf 2D semantic image synthesis method to teach the 3D painting network without explicit color supervision. Experiments show that our approach produces images with geometrically correct structures and supports scene manipulation, such as the change of viewpoint, object poses, and painting style. Our approach provides rich controllability to synthesized images in the aspect of 3D geometry.
-
We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects, and by adaptively referencing and aggregating useful information from the memory as needed. Our model, called MeMOT, consists of three main modules that are all Transformer-based: 1) Hypothesis Generation that produce object proposals in the current video frame; 2) Memory Encoding that extracts the core information from the memory for each tracked object; and 3) Memory Decoding that solves the object detection and data association tasks simultaneously for multi-object tracking. When evaluated on widely adopted MOT benchmark datasets, MeMOT observes very competitive performance.
-
Model pre-training is a cornerstone of modern visual recognition systems. Although fully supervised pre-training on datasets like ImageNet is still the de-facto standard, recent studies suggest that large-scale weakly supervised pre-training can outperform fully supervised approaches. This paper revisits weakly-supervised pre-training of models using hashtag supervision with modern versions of residual networks and the largest-ever dataset of images and corresponding hashtags. We study the performance of the resulting models in various transfer-learning settings including zero-shot transfer. We also compare our models with those obtained via large-scale self-supervised learning. We find our weakly-supervised models to be very competitive across all settings, and find they substantially outperform their self-supervised counterparts. We also include an investigation into whether our models learned potentially troubling associations or stereotypes. Overall, our results provide a compelling argument for the use of weakly supervised learning in the development of visual recognition systems. Our models, Supervised Weakly through hashtAGs (SWAG), are available publicly.
-
This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. The unlabeled images are usually assigned pseudo labels to be used in training, which however often causes the risk of performance degradation due to the confirmation bias towards errors on the pseudo labels. We present a novel method that resolves this chronic issue of pseudo labeling. At the heart of our method lies error localization network (ELN), an auxiliary module that takes an image and its segmentation prediction as input and identifies pixels whose pseudo labels are likely to be wrong. ELN enables semi-supervised learning to be robust against inaccurate pseudo labels by disregarding label noises during training and can be naturally integrated with self-training and contrastive learning. Moreover, we introduce a new learning strategy for ELN that simulates plausible and diverse segmentation errors during training of ELN to enhance its generalization. Our method is evaluated on PASCAL VOC 2012 and Cityscapes, where it outperforms all existing methods in every evaluation setting.
-
In single domain generalization, models trained with data from only one domain are required to perform well on many unseen domains. In this paper, we propose a new model, termed meta convolutional neural network, to solve the single domain generalization problem in image recognition. The key idea is to decompose the convolutional features of images into meta features. Acting as "visual words", meta features are defined as universal and basic visual elements for image representations (like words for documents in language). Taking meta features as reference, we propose compositional operations to eliminate irrelevant features of local convolutional features by an addressing process and then to reformulate the convolutional feature maps as a composition of related meta features. In this way, images are universally coded without biased information from the unseen domain, which can be processed by following modules trained in the source domain. The compositional operations adopt a regression analysis technique to learn the meta features in an online batch learning manner. Extensive experiments on multiple benchmark datasets verify the superiority of the proposed model in improving single domain generalization ability.
-
Recent advances of deep learning-based approaches have achieved remarkable performance on appearance-based gaze estimation. However, due to the shortage of target domain data and absence of target labels, generalizing gaze estimation algorithm to unseen environments is still challenging. In this paper, we discover the rotation-consistency property in gaze estimation and introduce the 'sub-label' for unsupervised domain adaptation. Consequently, we propose the Rotation-enhanced Unsupervised Domain Adaptation (RUDA) for gaze estimation. First, we rotate the original images with different angles for training. Then we conduct domain adaptation under the constraint of rotation consistency. The target domain images are assigned with sub-labels, derived from relative rotation angles rather than untouchable real labels. With such sub-labels, we propose a novel distribution loss that facilitates the domain adaptation. We evaluate the RUDA framework on four cross-domain gaze estimation tasks. Experimental results demonstrate that it improves the performance over the baselines with gains ranging from 12.2% to 30.5%. Our framework has the potential to be used in other computer vision tasks with physical constraints.
-
Knowledge distillation (KD) achieves promising results on the challenging problem of unsupervised anomaly detection (AD). The representation discrepancy of anomalies in the teacher-student (T-S) model provides essential evidence for AD. However, using similar or identical architectures to build the teacher and student models in previous studies hinders the diversity of anomalous representations. To tackle this problem, we propose a novel T-S model consisting of a teacher encoder and a student decoder and introduce a simple yet effective "reverse distillation" paradigm accordingly. Instead of receiving raw images directly, the student network takes teacher model's one-class embedding as input and targets to restore the teacher's multi-scale representations. Inherently, knowledge distillation in this study starts from abstract, high-level presentations to low-level features. In addition, we introduce a trainable one-class bottleneck embedding (OCBE) module in our T-S model. The obtained compact embedding effectively preserves essential information on normal patterns, but abandons anomaly perturbations. Extensive experimentation on AD and one-class novelty detection benchmarks shows that our method surpasses SOTA performance, demonstrating our proposed approach's effectiveness and generalizability.
-
Semantic patterns of fine-grained objects are determined by subtle appearance difference of local parts, which thus inspires a number of part-based methods. However, due to uncontrollable object poses in images, distinctive details carried by local regions can be spatially distributed or even self-occluded, leading to a large variation on object representation. For discounting pose variations, this paper proposes to learn a novel graph based object representation to reveal a global configuration of local parts for self-supervised pose alignment across classes, which is employed as an auxiliary feature regularization on a deep representation learning network. Moreover, a coarse-to-fine supervision together with the proposed pose-insensitive constraint on shallow-to-deep sub-networks encourages discriminative features in a curriculum learning manner. We evaluate our method on three popular fine-grained object classification benchmarks, consistently achieving the state-of-the-art performance. Source codes are available at https://github.com/yangxh11/P2P-Net.
-
Predicting future motion based on historical motion sequence is a fundamental problem in computer vision, and it has wide applications in autonomous driving and robotics. Some recent works have shown that Graph Convolutional Networks(GCN) are instrumental in modeling the relationship between different joints. However, considering the variants and diverse action types in human motion data, the cross-dependency of the spatio-temporal relationships will be difficult to depict due to the decoupled modeling strategy, which may also exacerbate the problem of insufficient generalization. Therefore, we propose the Spatio-Temporal Gating-Adjacency GCN(GAGCN) to learn the complex spatio-temporal dependencies over diverse action types. Specifically, we adopt gating networks to enhance the generalization of GCN via the trainable adaptive adjacency matrix obtained by blending the candidate spatio-temporal adjacency matrices. Moreover, GAGCN addresses the cross-dependency of space and time by balancing the weights of spatio-temporal modeling and fusing the decoupled spatio-temporal features. Extensive experiments on Human 3.6M, AMASS, and 3DPW demonstrate that GAGCN achieves state-of-the-art performance in both short-term and long-term predictions.
-
Classifying all cells in an organ is a relevant and difficult problem from plant developmental biology. We here abstract the problem into a new benchmark for node classification in a geo-referenced graph. Solving it requires learning the spatial layout of the organ including symmetries. To allow the convenient testing of new geometrical learning methods, the benchmark of Arabidopsis thaliana ovules is made available as a PyTorch data loader, along with a large number of precomputed features. Finally, we benchmark eight recent graph neural network architectures, finding that DeeperGCN currently works best on this problem.
-
Clustering is a popular approach to detecting patterns in unlabeled data. Existing clustering methods typically treat samples in a dataset as points in a metric space and compute distances to group together similar points. In this paper, we present a different way of clustering points in 2-dimensional space, inspired by how humans cluster data: by training neural networks to perform instance segmentation on plotted data. Our approach, Visual Clustering, has several advantages over traditional clustering algorithms: it is much faster than most existing clustering algorithms (making it suitable for very large datasets), it agrees strongly with human intuition for clusters, and it is by default hyperparameter free (although additional steps with hyperparameters can be introduced for more control of the algorithm). We describe the method and compare it to ten other clustering methods on synthetic data to illustrate its advantages and disadvantages. We then demonstrate how our approach can be extended to higher-dimensional data and illustrate its performance on real-world data. Our implementation of Visual Clustering is publicly available as a python package that can be installed and used on any dataset in a few lines of code. A demo on synthetic datasets is provided.
-
Understanding animals' behaviors is significant for a wide range of applications. However, existing animal behavior datasets have limitations in multiple aspects, including limited numbers of animal classes, data samples and provided tasks, and also limited variations in environmental conditions and viewpoints. To address these limitations, we create a large and diverse dataset, Animal Kingdom, that provides multiple annotated tasks to enable a more thorough understanding of natural animal behaviors. The wild animal footages used in our dataset record different times of the day in extensive range of environments containing variations in backgrounds, viewpoints, illumination and weather conditions. More specifically, our dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes. Such a challenging and comprehensive dataset shall be able to facilitate the community to develop, adapt, and evaluate various types of advanced methods for animal behavior analysis. Moreover, we propose a Collaborative Action Recognition (CARe) model that learns general and specific features for action recognition with unseen new animals. This method achieves promising performance in our experiments. Our dataset can be found at https://sutdcv.github.io/Animal-Kingdom.
-
Convolutional Neural Networks have achieved remarkable success in face recognition, in part due to the abundant availability of data. However, the data used for training CNNs is often imbalanced. Prior works largely focus on the long-tailed nature of face datasets in data volume per identity, or focus on single bias variation. In this paper, we show that many bias variations such as ethnicity, head pose, occlusion and blur can jointly affect the accuracy significantly. We propose a sample level weighting approach termed Multi-variation Cosine Margin (MvCoM), to simultaneously consider the multiple variation factors, which orthogonally enhances the face recognition losses to incorporate the importance of training samples. Further, we leverage a learning to learn approach, guided by a held-out meta learning set and use an additive modeling to predict the MvCoM. Extensive experiments on challenging face recognition benchmarks demonstrate the advantages of our method in jointly handling imbalances due to multiple variations.
-
In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i.e. annotations of object centers). In order to remedy the information loss from box annotations to centers, our method, namely Back to Reality (BR), makes use of synthetic 3D shapes to convert the weak labels into fully-annotated virtual scenes as stronger supervision, and in turn utilizes the perfect virtual labels to complement and refine the real labels. Specifically, we first assemble 3D shapes into physically reasonable virtual scenes according to the coarse scene layout extracted from position-level annotations. Then we go back to reality by applying a virtual-to-real domain adaptation method, which refine the weak labels and additionally supervise the training of detector with the virtual scenes. With less than 5% of the labeling labor, we achieve comparable detection performance with some popular fully-supervised approaches on the widely used ScanNet dataset.
-
In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem via training-free knowledge transfer. Our objective is to transfer knowledge acquired from information-rich common classes to semantically similar, and yet data-hungry, rare classes in order to obtain stronger tail class representations. We leverage the fact that class prototypes and learned cosine classifiers provide two different, complementary representations of class cluster centres in feature space, and use an attention mechanism to select and recompose learned classifiers features from common classes to obtain higher quality rare class representations. Our knowledge transfer process is training free, reducing overfitting risks, and can afford continual extension of classifiers to new classes. Experiments show that our approach can achieve significant performance boosts on rare classes while maintaining robust common class performance, outperforming directly comparable state-of-the-art models.
-
recommendation, and marketing services. Extensive efforts have been made to conquer the cross-modal retrieval problem in the general domain. When it comes to E-commerce, a common practice is to adopt the pretrained model and finetune on E-commerce data. Despite its simplicity, the performance is sub-optimal due to overlooking the uniqueness of E-commerce multimodal data. A few recent efforts have shown significant improvements over generic methods with customized designs for handling product images. Unfortunately, to the best of our knowledge, no existing method has addressed the unique challenges in the e-commerce language. This work studies the outstanding one, where it has a large collection of special meaning entities, e.g., "Dissel (brand)", "Top (category)", "relaxed (fit)" in the fashion clothing business. By formulating such out-of-distribution finetuning process in the Causal Inference paradigm, we view the erroneous semantics of these special entities as confounders to cause the retrieval failure. To rectify these semantics for aligning with e-commerce domain knowledge, we propose an intervention-based entity-aware contrastive learning framework with two modules, i.e., the Confounding Entity Selection Module and Entity-Aware Learning Module. Our method achieves competitive performance on the E-commerce benchmark Fashion-Gen. Particularly, in top-1 accuracy (R@1), we observe 10.3% and 10.5% relative improvements over the closest baseline in image-to-text and text-to-image retrievals, respectively.
-
Humans can perceive multiple expressions, each one with varying intensity, in the picture of a face. We propose a methodology for collecting and modeling multidimensional modulated expression annotations from human annotators. Our data reveals that the perception of some expressions can be quite different across observers; thus, our model is designed to represent ambiguity alongside intensity. An empirical exploration of how many dimensions are necessary to capture the perception of facial expression suggests six principal expression dimensions are sufficient. Using our method, we collected multidimensional modulated expression annotations for 1,000 images culled from the popular ExpW in-the-wild dataset. As a proof of principle of our improved measurement technique, we used these annotations to benchmark four public domain algorithms for automated facial expression prediction.
-
The development of computational tools allows the advancement of research in behavioral neuroscience and elevates the limits of experiment design. Many behavioral experiments need to determine the animal's position from its tracking, which is crucial for real-time decision-making and further analysis of experimental data. Modern experimental designs usually generate the recording of a large amount of data, requiring the development of automatic computational tools and intelligent algorithms for timely data acquisition and processing. The proposed tool in this study initially operates with the acquisition of images. Then the animal tracking step begins with background subtraction, followed by the animal contour detection and morphological operations to remove noise in the detected shapes. Finally, in the final stage of the algorithm, the principal components analysis (PCA) is applied in the obtained shape, resulting in the animal's gaze direction.
-
We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted relations as pseudo labels. At the heart of our framework lies an algorithm that investigates contexts of data on the embedding space to predict their class-equivalence relations as pseudo labels. The algorithm enables efficient end-to-end training since it demands no off-the-shelf module for pseudo labeling. Also, the class-equivalence relations provide rich supervisory signals for learning an embedding space. On standard benchmarks for metric learning, it clearly outperforms existing unsupervised learning methods and sometimes even beats supervised learning models using the same backbone network. It is also applied to semi-supervised metric learning as a way of exploiting additional unlabeled data, and achieves the state of the art by boosting performance of supervised learning substantially.
-
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without hitting the computation or memory bottlenecks. In this paper, we propose a new strategy to overcome this challenge. Instead of trying to process more frames at once like most existing methods, we propose to process videos in an online fashion and cache "memory" at each iteration. Through the memory, the model can reference prior context for long-term modeling, with only a marginal cost. Based on this idea, we build MeMViT, a Memory-augmented Multiscale Vision Transformer, that has a temporal support 30x longer than existing models with only 4.5 more compute; traditional methods need >3,000% more compute to do the same. On a wide range of settings, the increased temporal support enabled by MeMViT brings large gains in recognition accuracy consistently. MeMViT obtains state-of-the-art results on the AVA, EPIC-Kitchens-100 action classification, and action anticipation datasets.
-
We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training. Despite the recent progress, existing methods mainly embrace a localization-by-classification paradigm and overlook the fruitful fine-grained temporal distinctions between video sequences, thus suffering from severe ambiguity in classification learning and classification-to-localization adaption. This paper argues that learning by contextually comparing sequence-to-sequence distinctions offers an essential inductive bias in WSAL and helps identify coherent action instances. Specifically, under a differentiable dynamic programming formulation, two complementary contrastive objectives are designed, including Fine-grained Sequence Distance (FSD) contrasting and Longest Common Subsequence (LCS) contrasting, where the first one considers the relations of various action/background proposals by using match, insert, and delete operators and the second one mines the longest common subsequences between two videos. Both contrasting modules can enhance each other and jointly enjoy the merits of discriminative action-background separation and alleviated task gap between classification and localization. Extensive experiments show that our method achieves state-of-the-art performance on two popular benchmarks. Our code is available at https://github.com/MengyuanChen21/CVPR2022-FTCL.
-
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. In this paper, we start by rethinking how such multi-stride stereotype affects the LiDAR-based 3D object detectors. Our experiments point out that the downsampling operations bring few advantages, and lead to inevitable information loss. To remedy this issue, we propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network. Armed with transformers, our method addresses the problem of insufficient receptive field in single-stride architectures. It also cooperates well with the sparsity of point clouds and naturally avoids expensive computation. Eventually, our SST achieves state-of-the-art results on the large-scale Waymo Open Dataset. It is worth mentioning that our method can achieve exciting performance (83.8 LEVEL_1 AP on validation split) on small object (pedestrian) detection due to the characteristic of single stride. Our codes will be public soon.
-
Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few samples introduces uncertainty, and quantifying model confidence for few-shot predictions is essential for many critical domains. Furthermore, few-shot tasks used in meta training are usually sampled randomly from a task distribution for an iterative model update, leading to high labeling costs and computational overhead in meta-training. We propose a novel uncertainty-aware task selection model for label efficient meta-learning. The proposed model formulates a multidimensional belief measure, which can quantify the known uncertainty and lower bound the unknown uncertainty of any given task. Our theoretical result establishes an important relationship between the conflicting belief and the incorrect belief. The theoretical result allows us to estimate the total uncertainty of a task, which provides a principled criterion for task selection. A novel multi-query task formulation is further developed to improve both the computational and labeling efficiency of meta-learning. Experiments conducted over multiple real-world few-shot image classification tasks demonstrate the effectiveness of the proposed model.
-
Visual Dialog aims to answer multi-round, interactive questions based on the dialog history and image content. Existing methods either consider answer ranking and generating individually or only weakly capture the relation across the two tasks implicitly by two separate models. The research on a universal framework that jointly learns to rank and generate answers in a single model is seldom explored. In this paper, we propose a contrastive learning-based framework UTC to unify and facilitate both discriminative and generative tasks in visual dialog with a single model. Specifically, considering the inherent limitation of the previous learning paradigm, we devise two inter-task contrastive losses i.e., context contrastive loss and answer contrastive loss to make the discriminative and generative tasks mutually reinforce each other. These two complementary contrastive losses exploit dialog context and target answer as anchor points to provide representation learning signals from different perspectives. We evaluate our proposed UTC on the VisDial v1.0 dataset, where our method outperforms the state-of-the-art on both discriminative and generative tasks and surpasses previous state-of-the-art generative methods by more than 2 absolute points on Recall@1.
-
Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to appropriately define and alleviate the bias" one of the most important issues. Prior works mainly use label distribution or mean score information to indicate a coarse-grained bias. In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one. To this end, we propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences. PCB generates fightback soft labels for regularization during training. Besides, an iterative learning paradigm is developed to support a progressive and smooth regularization in such debiasing. PCB can be plugged and played to any existing methods as a complement. Experiments results on LVIS demonstrate that our method achieves state-of-the-art performance without bells and whistles. Superior results across various architectures show the generalization ability. The code and trained models are available at https://github.com/megvii-research/PCB.
-
Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inference-time cost. Though efficient during inference, such models rely heavily on the complicated training-time blocks to achieve high accuracy, leading to large extra training cost. In this paper, we present online convolutional re-parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. To achieve this goal, we introduce a linear scaling layer for better optimizing the online blocks. Assisted with the reduced training cost, we also explore some more effective re-param components. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. Meanwhile, equipped with OREPA, the models outperform previous methods on ImageNet by up to +0.6%. We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks. Codes are available at https://github.com/JUGGHM/OREPA_CVPR2022.
-
Class Incremental Learning (CIL) aims at learning a classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Previous works mainly focus on mitigating forgetting in phases after the initial one. However, we find that improving CIL at its initial phase is also a promising direction. Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance. Motivated by this, we study the difference between a naively-trained initial-phase model and the oracle model. Specifically, since one major difference between these two models is the number of training classes, we investigate how such difference affects the model representations. We find that, with fewer training classes, the data representations of each class lie in a long and narrow region; with more training classes, the representations of each class scatter more uniformly. Inspired by this observation, we propose Class-wise Decorrelation (CwD) that effectively regularizes representations of each class to scatter more uniformly, thus mimicking the model jointly trained with all classes (i.e., the oracle model). Our CwD is simple to implement and easy to plug into existing methods. Extensive experiments on various benchmark datasets show that CwD consistently and significantly improves the performance of existing state-of-the-art methods by around 1% to 3%. Code: https://github.com/Yujun-Shi/CwD.
-
Lidars are depth measuring sensors widely used in autonomous driving and augmented reality. However, the large volume of data produced by lidars can lead to high costs in data storage and transmission. While lidar data can be represented as two interchangeable representations: 3D point clouds and range images, most previous work focus on compressing the generic 3D point clouds. In this work, we show that directly compressing the range images can leverage the lidar scanning pattern, compared to compressing the unprojected point clouds. We propose a novel data-driven range image compression algorithm, named RIDDLE (Range Image Deep DeLta Encoding). At its core is a deep model that predicts the next pixel value in a raster scanning order, based on contextual laser shots from both the current and past scans (represented as a 4D point cloud of spherical coordinates and time). The deltas between predictions and original values can then be compressed by entropy encoding. Evaluated on the Waymo Open Dataset and KITTI, our method demonstrates significant improvement in the compression rate (under the same distortion) compared to widely used point cloud and range image compression algorithms as well as recent deep methods.
-
The visual relationship recognition (VRR) task aims at understanding the pairwise visual relationships between interacting objects in an image. These relationships typically have a long-tail distribution due to their compositional nature. This problem gets more severe when the vocabulary becomes large, rendering this task very challenging. This paper shows that modeling an effective message-passing flow through an attention mechanism can be critical to tackling the compositionality and long-tail challenges in VRR. The method, called RelTransformer, represents each im- age as a fully-connected scene graph and restructures the whole scene into the relation-triplet and global-scene contexts. It directly passes the message from each element in the relation-triplet and global-scene contexts to the target relation via self-attention. We also design a learnable memory to augment the long-tail relation representation learning. Through extensive experiments, we find that our model generalizes well on many VRR benchmarks. Our model outperforms the best-performing models on two large-scale long-tail VRR benchmarks, VG8K-LT (+2.0% overall acc) and GQA-LT (+26.0% overall acc), both having a highly skewed distribution towards the tail. It also achieves strong results on the VG200 relation detection task. Our code is available at https://github.com/Vision-CAIR/ RelTransformer.
-
High-order decomposition is a widely used model compression approach towards compact convolutional neural networks (CNNs). However, many of the existing solutions, though can efficiently reduce CNN model sizes, are very difficult to bring considerable saving for computational costs, especially when the compression ratio is not huge, thereby causing the severe computation inefficiency problem. To overcome this challenge, in this paper we propose efficient High-Order DEcomposed Convolution (HODEC). By performing systematic explorations on the underlying reason and mitigation strategy for the computation inefficiency, we develop a new decomposition and computation-efficient execution scheme, enabling simultaneous reductions in computational and storage costs. To demonstrate the effectiveness of HODEC, we perform empirical evaluations for various CNN models on different datasets. HODEC shows consistently outstanding compression and acceleration performance. For ResNet-56 on CIFAR-10 dataset, HODEC brings 67% fewer model parameters and 62% fewer FLOPs with 1.17% accuracy increase than the baseline. For ResNet-50 on ImageNet dataset, HODEC achieves 63% FLOPs reduction with 0.31% accuracy increase than the uncompressed model.
-
In this work, we focus on scene flow learning on point clouds in a self-supervised manner. A real-world scene can be well modeled as a collection of rigidly moving parts, therefore its scene flow can be represented as a combination of rigid motion of each part. Inspired by this observation, we propose to generate pseudo scene flow for self-supervised learning based on piecewise rigid motion estimation, in which the source point cloud is decomposed into a set of local regions and each region is treated as rigid. By rigidly aligning each region with its potential counterpart in the target point cloud, we obtain a region-specific rigid transformation to represent the flow, which together constitutes the pseudo scene flow labels of the entire scene to enable network training. Compared with most existing approaches relying on point-wise similarities for point matching, our method explicitly enforces region-wise rigid alignments, yielding locally rigid pseudo scene flow labels. We demonstrate the effectiveness of our self-supervised learning method on FlyingThings3D and KITTI datasets. Comprehensive experiments show that our method achieves new state-of-the-art performance in self-supervised scene flow learning, without any ground truth scene flow for supervision, even outperforming some supervised counterparts.
-
Deep learning researchers have a keen interest in proposing new novel activation functions that can boost neural network performance. A good choice of activation function can have a significant effect on improving network performance and training dynamics. Rectified Linear Unit (ReLU) is a popular hand-designed activation function and is the most common choice in the deep learning community due to its simplicity though ReLU has some drawbacks. In this paper, we have proposed two new novel activation functions based on approximation of the maximum function, and we call these functions Smooth Maximum Unit (SMU and SMU-1). We show that SMU and SMU-1 can smoothly approximate ReLU, Leaky ReLU, or more general Maxout family, and GELU is a particular case of SMU. Replacing ReLU by SMU, Top-1 classification accuracy improves by 6.22%, 3.39%, 3.51%, and 3.08% on the CIFAR100 dataset with ShuffleNet V2, PreActResNet-50, ResNet-50, and SeNet-50 models respectively. Also, our experimental evaluation shows that SMU and SMU-1 improve network performance in a variety of deep learning tasks like image classification, object detection, semantic segmentation, and machine translation compared to widely used activation functions.
-
QR (quick response) codes are widely used as an offline-to-online channel to convey information (e.g., links) from publicity materials (e.g., display and print) to mobile devices. However, QR Codes are not favorable for taking up valuable space of publicity materials. Recent works propose invisible codes/hyperlinks that can convey hidden information from offline to online. However, they require markers to locate invisible codes, which fails the purpose of invisible codes to be visible because of the markers. This paper proposes a novel invisible information hiding architecture for display/print-camera scenarios, consisting of hiding, locating, correcting, and recovery, where invisible markers are learned to make hidden codes truly invisible. We hide information in a sub-image rather than the entire image and include a localization module in the end-to-end framework. To achieve both high visual quality and high recovering robustness, an effective multi-stage training strategy is proposed. The experimental results show that the proposed method outperforms the state-of-the-art information hiding methods in both visual quality and robustness. In addition, the automatic localization of hidden codes significantly reduces the time of manually correcting geometric distortions for photos, which is a revolutionary innovation for information hiding in mobile applications.
-
Personalized image aesthetics assessment (PIAA) is challenging due to its highly subjective nature. People's aesthetic tastes depend on diversified factors, including image characteristics and subject characters. The existing PIAA databases are limited in terms of annotation diversity, especially the subject aspect, which can no longer meet the increasing demands of PIAA research. To solve the dilemma, we conduct so far, the most comprehensive subjective study of personalized image aesthetics and introduce a new Personalized image Aesthetics database with Rich Attributes (PARA), which consists of 31,220 images with annotations by 438 subjects. PARA features wealthy annotations, including 9 image-oriented objective attributes and 4 human-oriented subjective attributes. In addition, desensitized subject information, such as personality traits, is also provided to support study of PIAA and user portraits. A comprehensive analysis of the annotation data is provided and statistic study indicates that the aesthetic preferences can be mirrored by proposed subjective attributes. We also propose a conditional PIAA model by utilizing subject information as conditional prior. Experimental results indicate that the conditional PIAA model can outperform the control group, which is also the first attempt to demonstrate how image aesthetics and subject characters interact to produce the intricate personalized tastes on image aesthetics. We believe the database and the associated analysis would be useful for conducting next-generation PIAA study. The project page of PARA can be found at https://cv-datasets.institutecv.com/#/data-sets.
-
Pre-training models on Imagenet or other massive datasets of real images has led to major advances in computer vision, albeit accompanied with shortcomings related to curation cost, privacy, usage rights, and ethical issues. In this paper, for the first time, we study the transferability of pre-trained models based on synthetic data generated by graphics simulators to downstream tasks from very different domains. In using such synthetic data for pre-training, we find that downstream performance on different tasks are favored by different configurations of simulation parameters (e.g. lighting, object pose, backgrounds, etc.), and that there is no one-size-fits-all solution. It is thus better to tailor synthetic pre-training data to a specific downstream task, for best performance. We introduce Task2Sim, a unified model mapping downstream task representations to optimal simulation parameters to generate synthetic pre-training data for them. Task2Sim learns this mapping by training to find the set of best parameters on a set of "seen" tasks. Once trained, it can then be used to predict best simulation parameters for novel "unseen" tasks in one shot, without requiring additional training. Given a budget in number of images per class, our extensive experiments with 20 diverse downstream tasks show Task2Sim's task-adaptive pre-training data results in significantly better downstream performance than non-adaptively choosing simulation parameters on both seen and unseen tasks. It is even competitive with pre-training on real images from Imagenet.
-
Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques accomplish this task by using pseudo-labels, but these labels are inherently noisy and deteriorate the accuracy. To overcome this problem, several pseudo-label refinement methods have been proposed, but they neglect the fine-grained local context essential for person re-ID. In this paper, we propose a novel Part-based Pseudo Label Refinement (PPLR) framework that reduces the label noise by employing the complementary relationship between global and part features. Specifically, we design a cross agreement score as the similarity of k-nearest neighbors between feature spaces to exploit the reliable complementary relationship. Based on the cross agreement, we refine pseudo-labels of global features by ensembling the predictions of part features, which collectively alleviate the noise in global feature clustering. We further refine pseudo-labels of part features by applying label smoothing according to the suitability of given labels for each part. Thanks to the reliable complementary information provided by the cross agreement score, our PPLR effectively reduces the influence of noisy labels and learns discriminative representations with rich local contexts. Extensive experimental results on Market-1501 and MSMT17 demonstrate the effectiveness of the proposed method over the state-of-the-art performance. The code is available at https://github.com/yoonkicho/PPLR.
-
Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments, training agents that cannot generalize across the two. Although learning to navigate in continuous spaces is closer to the real-world, training such an agent is significantly more difficult than training an agent in discrete spaces. However, recent advances in discrete VLN are challenging to translate to continuous VLN due to the domain gap. The fundamental difference between the two setups is that discrete navigation assumes prior knowledge of the connectivity graph of the environment, so that the agent can effectively transfer the problem of navigation with low-level controls to jumping from node to node with high-level actions by grounding to an image of a navigable direction. To bridge the discrete-to-continuous gap, we propose a predictor to generate a set of candidate waypoints during navigation, so that agents designed with high-level actions can be transferred to and trained in continuous environments. We refine the connectivity graph of Matterport3D to fit the continuous Habitat-Matterport3D, and train the waypoints predictor with the refined graphs to produce accessible waypoints at each time step. Moreover, we demonstrate that the predicted waypoints can be augmented during training to diversify the views and paths, and therefore enhance agent's generalization ability. Through extensive experiments we show that agents navigating in continuous environments with predicted waypoints perform significantly better than agents using low-level actions, which reduces the absolute discrete-to-continuous gap by 11.76% Success Weighted by Path Length (SPL) for the Cross-Modal Matching Agent and 18.24% SPL for the Recurrent VLN-BERT. Our agents, trained with a simple imitation learning objective, outperform previous methods by a large margin, achieving new state-of-the-art results on the testing environments of the R2R-CE and the RxR-CE datasets.
-
The rapid development of deep learning provides a better solution for the end-to-end reconstruction of hyperspectral image (HSI). However, existing learning-based methods have two major defects. Firstly, networks with self-attention usually sacrifice internal resolution to balance model performance against complexity, losing fine-grained high-resolution (HR) features. Secondly, even if the optimization focusing on spatial-spectral domain learning (SDL) converges to the ideal solution, there is still a significant visual difference between the reconstructed HSI and the truth. So we propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy. Dynamic FDL supervision forces the model to reconstruct fine-grained frequencies and compensate for excessive smoothing and distortion caused by pixel-level losses. The HR pixel-level attention and frequency-level refinement in our HDNet mutually promote HSI perceptual quality. Extensive quantitative and qualitative experiments show that our method achieves SOTA performance on simulated and real HSI datasets. https://github.com/Huxiaowan/HDNet
-
Open-world object detection (OWOD) is a challenging computer vision problem, where the task is to detect a known set of object categories while simultaneously identifying unknown objects. Additionally, the model must incrementally learn new classes that become known in the next training episodes. Distinct from standard object detection, the OWOD setting poses significant challenges for generating quality candidate proposals on potentially unknown objects, separating the unknown objects from the background and detecting diverse unknown objects. Here, we introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection. The proposed OW-DETR comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification and objectness scoring to explicitly address the aforementioned OWOD challenges. Our OW-DETR explicitly encodes multi-scale contextual information, possesses less inductive bias, enables knowledge transfer from known classes to the unknown class and can better discriminate between unknown objects and background. Comprehensive experiments are performed on two benchmarks: MS-COCO and PASCAL VOC. The extensive ablations reveal the merits of our proposed contributions. Further, our model outperforms the recently introduced OWOD approach, ORE, with absolute gains ranging from 1.8% to 3.3% in terms of unknown recall on MS-COCO. In the case of incremental object detection, OW-DETR outperforms the state-of-the-art for all settings on PASCAL VOC. Our code is available at https://github.com/akshitac8/OW-DETR.
-
Deep Implicit Function (DIF) has gained popularity as an efficient 3D shape representation. To capture geometry details, current methods usually learn DIF using local latent codes, which discretize the space into a regular 3D grid (or octree) and store local codes in grid points (or octree nodes). Given a query point, the local feature is computed by interpolating its neighboring local codes with their positions. However, the local codes are constrained at discrete and regular positions like grid points, which makes the code positions difficult to be optimized and limits their representation ability. To solve this problem, we propose to learn DIF with Dynamic Code Cloud, named DCC-DIF. Our method explicitly associates local codes with learnable position vectors, and the position vectors are continuous and can be dynamically optimized, which improves the representation ability. In addition, we propose a novel code position loss to optimize the code positions, which heuristically guides more local codes to be distributed around complex geometric details. In contrast to previous methods, our DCC-DIF represents 3D shapes more efficiently with a small amount of local codes, and improves the reconstruction quality. Experiments demonstrate that DCC-DIF achieves better performance over previous methods. Code and data are available at https://github.com/lity20/DCCDIF.
-
We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory footprint from the depth of the model, Reversible Vision Transformers enable memory efficient scaling of transformer architectures. We adapt two popular models, namely Vision Transformer and Multi-scale Vision Transformers, to reversible variants and benchmark extensively across both model sizes and tasks of image classification, object detection and video classification. Reversible Vision Transformers achieve a reduced memory footprint of up to 15.5x at identical model complexity, parameters and accuracy, demonstrating the promise of reversible vision transformers as an efficient backbone for resource limited training regimes. Finally, we find that the additional computational burden of recomputing activations is more than overcome for deeper models, where throughput can increase up to 3.9x over their non-reversible counterparts. Code and models are available at https://github.com/facebookresearch/mvit.
-
Humans have the remarkable ability to perceive objects as a whole, even when parts of them are occluded. This ability of amodal perception forms the basis of our perceptual and cognitive understanding of our world. To enable robots to reason with this capability, we formulate and propose a novel task that we name amodal panoptic segmentation. The goal of this task is to simultaneously predict the pixel-wise semantic segmentation labels of the visible regions of stuff classes and the instance segmentation labels of both the visible and occluded regions of thing classes. To facilitate research on this new task, we extend two established benchmark datasets with pixel-level amodal panoptic segmentation labels that we make publicly available as KITTI-360-APS and BDD100K-APS. We present several strong baselines, along with the amodal panoptic quality (APQ) and amodal parsing coverage (APC) metrics to quantify the performance in an interpretable manner. Furthermore, we propose the novel amodal panoptic segmentation network (APSNet), as a first step towards addressing this task by explicitly modeling the complex relationships between the occluders and occludes. Extensive experimental evaluations demonstrate that APSNet achieves state-of-the-art performance on both benchmarks and more importantly exemplifies the utility of amodal recognition. The datasets are available at http://amodal-panoptic.cs.uni-freiburg.de
-
Measurements from the Event Horizon Telescope enabled the visualization of light emission around a black hole for the first time. So far, these measurements have been used to recover a 2D image under the assumption that the emission field is static over the period of acquisition. In this work, we propose BH-NeRF, a novel tomography approach that leverages gravitational lensing to recover the continuous 3D emission field near a black hole. Compared to other 3D reconstruction or tomography settings, this task poses two significant challenges: first, rays near black holes follow curved paths dictated by general relativity, and second, we only observe measurements from a single viewpoint. Our method captures the unknown emission field using a continuous volumetric function parameterized by a coordinate-based neural network, and uses knowledge of Keplerian orbital dynamics to establish correspondence between 3D points over time. Together, these enable BH-NeRF to recover accurate 3D emission fields, even in challenging situations with sparse measurements and uncertain orbital dynamics. This work takes the first steps in showing how future measurements from the Event Horizon Telescope could be used to recover evolving 3D emission around the supermassive black hole in our Galactic center.
-
Making generative models 3D-aware bridges the 2D image space and the 3D physical world yet remains challenging. Recent attempts equip a Generative Adversarial Network (GAN) with a Neural Radiance Field (NeRF), which maps 3D coordinates to pixel values, as a 3D prior. However, the implicit function in NeRF has a very local receptive field, making the generator hard to become aware of the global structure. Meanwhile, NeRF is built on volume rendering which can be too costly to produce high-resolution results, increasing the optimization difficulty. To alleviate these two problems, we propose a novel framework, termed as VolumeGAN, for high-fidelity 3D-aware image synthesis, through explicitly learning a structural representation and a textural representation. We first learn a feature volume to represent the underlying structure, which is then converted to a feature field using a NeRF-like model. The feature field is further accumulated into a 2D feature map as the textural representation, followed by a neural renderer for appearance synthesis. Such a design enables independent control of the shape and the appearance. Extensive experiments on a wide range of datasets confirm that, our approach achieves sufficiently higher image quality and better 3D control than the previous methods..
-
Object-guided text-to-image synthesis aims to generate images from natural language descriptions built by two-step frameworks, i.e., the model generates the layout and then synthesizes images from the layout and captions. However, such frameworks have two issues: 1) complex structure, since generating language-related layout is not a trivial task; 2) error propagation, because the inappropriate layout will mislead the image synthesis and is hard to be revised. In this paper, we propose an object-guided joint-decoding module to simultaneously generate the image and the corresponding layout. Specially, we present the joint-decoding transformer to model the joint probability on images tokens and the corresponding layouts tokens, where layout tokens provide additional observed data to model the complex scene better. Then, we describe a novel Layout-VQGAN for layout encoding and decoding to provide more information about the complex scene. After that, we present the detail-enhanced module to enrich the language-related details based on two facts: 1) visual details could be omitted in the compression of VQGANs; 2) the joint-decoding transformer would not have sufficient generating capacity. The experiments show that our approach is competitive with previous object-centered models and can generate diverse and high-quality objects under the given layouts.
-
Geometric verification is considered a de facto solution for the re-ranking task in image retrieval. In this study, we propose a novel image retrieval re-ranking network named Correlation Verification Networks (CVNet). Our proposed network, comprising deeply stacked 4D convolutional layers, gradually compresses dense feature correlation into image similarity while learning diverse geometric matching patterns from various image pairs. To enable cross-scale matching, it builds feature pyramids and constructs cross-scale feature correlations within a single inference, replacing costly multi-scale inferences. In addition, we use curriculum learning with the hard negative mining and Hide-and-Seek strategy to handle hard samples without losing generality. Our proposed re-ranking network shows state-of-the-art performance on several retrieval benchmarks with a significant margin (+12.6% in mAP on ROxford-Hard+1M set) over state-of-the-art methods. The source code and models are available online: https://github.com/sungonce/CVNet.
-
Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data, which is costly to collect, compared to image-only or text-only data. In this paper, we propose unsupervised Vision-and-Language pre-training (UVLP) to learn the cross-modal representation from non-parallel image and text datasets. We found two key factors that lead to good unsupervised V+L pre-training without parallel data: (i) joint image-and-text input (ii) overall image-text alignment (even for non-parallel data). Accordingly, we propose a novel unsupervised V+L pre-training curriculum for non-parallel texts and images. We first construct a weakly aligned image-text corpus via a retrieval-based approach, then apply a set of multi-granular alignment pre-training tasks, including region-to-tag, region-to-phrase, and image-to-sentence alignment, to bridge the gap between the two modalities. A comprehensive ablation study shows each granularity is helpful to learn a stronger pre-trained model. We adapt our pre-trained model to a set of V+L downstream tasks, including VQA, NLVR2, Visual Entailment, and RefCOCO+. Our model achieves the state-of-art performance in all these tasks under the unsupervised setting.
-
While deep face recognition (FR) systems have shown amazing performance in identification and verification, they also arouse privacy concerns for their excessive surveillance on users, especially for public face images widely spread on social networks. Recently, some studies adopt adversarial examples to protect photos from being identified by unauthorized face recognition systems. However, existing methods of generating adversarial face images suffer from many limitations, such as awkward visual, white-box setting, weak transferability, making them difficult to be applied to protect face privacy in reality. In this paper, we propose adversarial makeup transfer GAN (AMT-GAN), a novel face protection method aiming at constructing adversarial face images that preserve stronger black-box transferability and better visual quality simultaneously. AMT-GAN leverages generative adversarial networks (GAN) to synthesize adversarial face images with makeup transferred from reference images. In particular, we introduce a new regularization module along with a joint training strategy to reconcile the conflicts between the adversarial noises and the cycle consistence loss in makeup transfer, achieving a desirable balance between the attack strength and visual changes. Extensive experiments verify that compared with state of the arts, AMT-GAN can not only preserve a comfortable visual quality, but also achieve a higher attack success rate over commercial FR APIs, including Face++, Aliyun, and Microsoft.
-
State-of-the-art approaches to ObjectGoal navigation (ObjectNav) rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Potential functions for ObjectGoal Navigation with Interaction-free learning (PONI), a modular approach that disentangles the skills of 'where to look?' for an object and 'how to navigate to (x, y)?'. Our key insight is that 'where to look?' can be treated purely as a perception problem, and learned without environment interactions. To address this, we propose a network that predicts two complementary potential functions conditioned on a semantic map and uses them to decide where to look for an unseen object. We train the potential function network using supervised learning on a passive dataset of top-down semantic maps, and integrate it into a modular framework to perform ObjectNav. Experiments on Gibson and Matterport3D demonstrate that our method achieves the state-of-the-art for ObjectNav while incurring up to 1,600x less computational cost for training. Code and pre-trained models are available.
-
How to effectively handle label noise has been one of the most practical but challenging tasks in Deep Neural Networks (DNNs). Recent popular methods for training DNNs with noisy labels mainly focus on directly filtering out samples with low confidence or repeatedly mining valuable information from low-confident samples. %to further modify DNNs. However, they cannot guarantee the robust generalization of models due to the ignorance of useful information hidden in noisy data. To address this issue, we propose a new effective method named as LaCoL (Latent Contrastive Learning) to leverage the negative correlations from the noisy data. Specifically, in label space, we exploit the weakly-augmented data to filter samples and adopt classification loss on strong augmentations of the selected sample set, which can preserve the training diversity. While in metric space, we utilize weakly-supervised contrastive learning to excavate these negative correlations hidden in noisy data. Moreover, a cross-space similarity consistency regularization is provided to constrain the gap between label space and metric space. Extensive experiments have validated the superiority of our approach over existing state-of-the-art methods.
-
Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation
Multi-frame human pose estimation has long been a compelling and fundamental problem in computer vision. This task is challenging due to fast motion and pose occlusion that frequently occur in videos. State-of-the-art methods strive to incorporate additional visual evidences from neighboring frames (supporting frames) to facilitate the pose estimation of the current frame (key frame). One aspect that has been obviated so far, is the fact that current methods directly aggregate unaligned contexts across frames. The spatial-misalignment between pose features of the current frame and neighboring frames might lead to unsatisfactory results. More importantly, existing approaches build upon the straightforward pose estimation loss, which unfortunately cannot constrain the network to fully leverage useful information from neighboring frames. To tackle these problems, we present a novel hierarchical alignment framework, which leverages coarse-to-fine deformations to progressively update a neighboring frame to align with the current frame at the feature level. We further propose to explicitly supervise the knowledge extraction from neighboring frames, guaranteeing that useful complementary cues are extracted. To achieve this goal, we theoretically analyzed the mutual information between the frames and arrived at a loss that maximizes the taskrelevant mutual information. These allow us to rank No.1 in the Multi-frame Person Pose Estimation Challenge on benchmark dataset PoseTrack2017, and obtain state-of-the-art performance on benchmarks Sub-JHMDB and PoseTrack2018. Our code is released at https://github.com/Pose-Group/FAMI-Pose, hoping that it will be useful to the community.
-
Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the "invertibility" of different image segments and project each segment into a latent layer. Easier regions can be inverted into an earlier layer in the generator's latent space, while more challenging regions can be inverted into a later feature space. Experiments show that our method obtains better inversion results compared to the recent approaches on complex categories, while maintaining downstream editability. Please refer to our project page at gauravparmar.com/sam_ inversion.
-
Transformers trained with self-supervision using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we show a graph-based method that uses the self-supervised transformer features to discover an object from an image. Visual tokens are viewed as nodes in a weighted graph with edges representing a connectivity score based on the similarity of tokens. Foreground objects can then be segmented using a normalized graph-cut to group self-similar regions. We solve the graph-cut problem using spectral clustering with generalized eigen-decomposition and show that the second smallest eigenvector provides a cutting solution since its absolute value indicates the likelihood that a token belongs to a foreground object. Despite its simplicity, this approach significantly boosts the performance of unsupervised object discovery: we improve over the recent state-of-the-art LOST by a margin of 6.9%, 8.1%, and 8.1% respectively on the VOC07, VOC12, and COCO20K. The performance can be further improved by adding a second stage class-agnostic detector (CAD). Our proposed method can be easily extended to unsupervised saliency detection and weakly supervised object detection. For unsupervised saliency detection, we improve IoU for 4.9%, 5.2%, 12.9% on ECSSD, DUTS, DUTOMRON respectively compared to state-of-the-art. For weakly supervised object detection, we achieve competitive performance on CUB and ImageNet. Our code is available at: https://www.m-psi.fr/Papers/TokenCut2022/
-
Recent high-performing Human-Object Interaction (HOI) detection techniques have been highly influenced by Transformer-based object detector (i.e., DETR). Nevertheless, most of them directly map parametric interaction queries into a set of HOI predictions through vanilla Transformer in a one-stage manner. This leaves rich inter- or intra-interaction structure under-exploited. In this work, we design a novel Transformer-style HOI detector, i.e., Structure-aware Transformer over Interaction Proposals (STIP), for HOI detection. Such design decomposes the process of HOI set prediction into two subsequent phases, i.e., an interaction proposal generation is first performed, and then followed by transforming the non-parametric interaction proposals into HOI predictions via a structure-aware Transformer. The structure-aware Transformer upgrades vanilla Transformer by encoding additionally the holistically semantic structure among interaction proposals as well as the locally spatial structure of human/object within each interaction proposal, so as to strengthen HOI predictions. Extensive experiments conducted on V-COCO and HICO-DET benchmarks have demonstrated the effectiveness of STIP, and superior results are reported when comparing with the state-of-the-art HOI detectors. Source code is available at https://github.com/zyong812/STIP.
-
Domain Adaptive Object Detection (DAOD) models a joint distribution of images and labels from an annotated source domain and learns a domain-invariant transformation to estimate the target labels with the given target domain images. Existing methods assume that the source domain labels are completely clean, yet large-scale datasets often contain error-prone annotations due to instance ambiguity, which may lead to a biased source distribution and severely degrade the performance of the domain adaptive detector de facto. In this paper, we represent the first effort to formulate noisy DAOD and propose a Noise Latent Transferability Exploration (NLTE) framework to address this issue. It is featured with 1) Potential Instance Mining (PIM), which leverages eligible proposals to recapture the miss-annotated instances from the background; 2) Morphable Graph Relation Module (MGRM), which models the adaptation feasibility and transition probability of noisy samples with relation matrices; 3) Entropy-Aware Gradient Reconcilement (EAGR), which incorporates the semantic information into the discrimination process and enforces the gradients provided by noisy and clean samples to be consistent towards learning domain-invariant representations. A thorough evaluation on benchmark DAOD datasets with noisy source annotations validates the effectiveness of NLTE. In particular, NLTE improves the mAP by 8.4% under 60% corrupted annotations and even approaches the ideal upper bound of training on a clean source dataset.
-
This paper probes intrinsic factors behind typical failure cases (e.g spatial inconsistency and boundary confusion) produced by the existing state-of-the-art method in face parsing. To tackle these problems, we propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation (DML-CSR) for face parsing. Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection. These tasks only share low-level encoder weights without high-level interactions between each other, enabling to decouple auxiliary modules from the whole network at the inference stage. To address spatial inconsistency, we develop a dynamic dual graph convolutional network to capture global contextual information without using any extra pooling operation. To handle boundary confusion in both single and multiple face scenarios, we exploit binary and category edge detection to jointly obtain generic geometric structure and fine-grained semantic clues of human faces. Besides, to prevent noisy labels from degrading model generalization during training, cyclical self-regulation is proposed to self-ensemble several model instances to get a new model and the resulting model then is used to self-distill subsequent models, through alternating iterations. Experiments show that our method achieves the new state-of-the-art performance on the Helen, CelebAMask-HQ, and Lapa datasets. The source code is available at https://github.com/deepinsight/insightface/tree/master/parsing/dml_csr.
-
Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data. In this paper, we explore more challenging exemplar-based high-resolution portrait style transfer by introducing a novel DualStyleGAN with flexible control of dual styles of the original face domain and the extended artistic portrait domain. Different from StyleGAN, DualStyleGAN provides a natural way of style transfer by characterizing the content and style of a portrait with an intrinsic style path and a new extrinsic style path, respectively. The delicately designed extrinsic style path enables our model to modulate both the color and complex structural styles hierarchically to precisely pastiche the style example. Furthermore, a novel progressive fine-tuning scheme is introduced to smoothly transform the generative space of the model to the target domain, even with the above modifications on the network architecture. Experiments demonstrate the superiority of DualStyleGAN over state-of-the-art methods in high-quality portrait style transfer and flexible style control.
-
This paper studies the task of One-Shot image Generation (OSG), where generation network learned on base dataset should be generalizable to synthesize images of novel categories with only one available sample per novel category. Most existing methods for feature transfer in one-shot image generation only learn reusable features implicitly on pre-training tasks. Such methods would be likely to overfit pre-training tasks. In this paper, we propose a novel model to explicitly learn and memorize reusable features that can help hallucinate novel category images. To be specific, our algorithm learns to decompose image features into the Category-Related (CR) and Category-Independent (CI) features. Our model learning to memorize class-independent CI features which are further utilized by our feature hallucination component to generate target novel category images. We validate our model on several benchmarks. Extensive experiments demonstrate that our model effectively boosts the OSG performance and can generate compelling and diverse samples.
-
In this paper, we address the problem of texture representation for 3D shapes for the challenging and underexplored tasks of texture transfer and synthesis. Previous works either apply spherical texture maps which may lead to large distortions, or use continuous texture fields that yield smooth outputs lacking details. We argue that the traditional way of representing textures with images and linking them to a 3D mesh via UV mapping is more desirable, since synthesizing 2D images is a well-studied problem. We propose AUV-Net which learns to embed 3D surfaces into a 2D aligned UV space, by mapping the corresponding semantic parts of different 3D shapes to the same location in the UV space. As a result, textures are aligned across objects, and can thus be easily synthesized by generative models of images. Texture alignment is learned in an unsupervised manner by a simple yet effective texture alignment module, taking inspiration from traditional works on linear subspace learning. The learned UV mapping and aligned texture representations enable a variety of applications including texture transfer, texture synthesis, and textured single view 3D reconstruction. We conduct experiments on multiple datasets to demonstrate the effectiveness of our method.
-
Open-vocabulary object detection aims to detect novel object categories beyond the training set. The advanced open-vocabulary two-stage detectors employ instance-level visual-to-visual knowledge distillation to align the visual space of the detector with the semantic space of the Pre-trained Visual-Language Model (PVLM). However, in the more efficient one-stage detector, the absence of class-agnostic object proposals hinders the knowledge distillation on unseen objects, leading to severe performance degradation. In this paper, we propose a hierarchical visual-language knowledge distillation method, i.e., HierKD, for open-vocabulary one-stage detection. Specifically, a global-level knowledge distillation is explored to transfer the knowledge of unseen categories from the PVLM to the detector. Moreover, we combine the proposed global-level knowledge distillation and the common instance-level knowledge distillation in a hierarchical structure to learn the knowledge of seen and unseen categories simultaneously. Extensive experiments on MS-COCO show that our method significantly surpasses the previous best one-stage detector with 11.9% and 6.7% AP50 gains under the zero-shot detection and generalized zero-shot detection settings, and reduces the AP50 performance gap from 14% to 7.3% compared to the best two-stage detector. Code will be publicly available.
-
We investigate the problem of training generative models on very sparse collections of 3D models. Particularly, instead of using difficult-to-obtain large sets of 3D models, we demonstrate that geometrically-motivated energy functions can be used to effectively augment and boost only a sparse collection of example (training) models. Technically, we analyze the Hessian of the as-rigid-as-possible (ARAP) energy to adaptively sample from and project to the underlying (local) shape space, and use the augmented dataset to train a variational autoencoder (VAE). We iterate the process, of building latent spaces of VAE and augmenting the associated dataset, to progressively reveal a richer and more expressive generative space for creating geometrically and semantically valid samples. We evaluate our method against a set of strong baselines, provide ablation studies, and demonstrate application towards establishing shape correspondences. GLASS produces multiple interesting and meaningful shape variations even when starting from as few as 3-10 training shapes. Our code is available at https: //sanjeevmk.github.io/glass_webpage/.
-
We present a novel neural implicit representation for articulated human bodies. Compared to explicit template meshes, neural implicit body representations provide an efficient mechanism for modeling interactions with the environment, which is essential for human motion reconstruction and synthesis in 3D scenes. However, existing neural implicit bodies suffer from either poor generalization on highly articulated poses or slow inference time. In this work, we observe that prior knowledge about the human body's shape and kinematic structure can be leveraged to improve generalization and efficiency. We decompose the full-body geometry into local body parts and employ a part-aware encoder-decoder architecture to learn neural articulated occupancy that models complex deformations locally. Our local shape encoder represents the body deformation of not only the corresponding body part but also the neighboring body parts. The decoder incorporates the geometric constraints of local body shape which significantly improves pose generalization. We demonstrate that our model is suitable for resolving self-intersections and collisions with 3D environments. Quantitative and qualitative experiments show that our method largely outperforms existing solutions in terms of both efficiency and accuracy.
-
Since the rise of vision-language navigation (VLN), great progress has been made in instruction following -- building a follower to navigate environments under the guidance of instructions. However, far less attention has been paid to the inverse task: instruction generation -- learning a speaker to generate grounded descriptions for navigation routes. Existing VLN methods train a speaker independently and typically treat it as a data augmentation tool for strengthening the follower, while ignoring rich cross-task relations. Here we describe an approach that learns the two tasks simultaneously and exploits their intrinsic correlations to boost the training of each: the follower judges whether the speaker-created instruction explains the original navigation route correctly, and vice versa. Without the need of aligned instruction-path pairs, such cycle-consistent learning scheme is complementary to task-specific training objectives defined on labeled data, and can also be applied over unlabeled paths (sampled without paired instructions). Another agent, called creator, is added to generate counterfactual environments. It greatly changes current scenes yet leaves novel items -- which are crucial for the execution of original instructions -- unchanged. Thus more informative training scenes are synthesized and the three agents compose a powerful VLN learning system. Experiments on a standard benchmark show that our approach improves the performance of various follower models and produces accurate navigation instructions. Our code will be released.
-
Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution (OOD). The more complex the task to learn, the more likely it is that statistical artifacts (i.e. selection biases, spurious correlations) are simpler than the mechanisms to learn. We demonstrate that the simplicity bias can be mitigated and OOD generalization improved. We train a set of similar models to fit the data in different ways using a penalty on the alignment of their input gradients. We show theoretically and empirically that this induces the learning of more complex predictive patterns. OOD generalization fundamentally requires information beyond i.i.d. examples, such as multiple training environments, counterfactual examples, or other side information. Our approach shows that we can defer this requirement to an independent model selection stage. We obtain SOTA results in visual recognition on biased data and generalization across visual domains. The method - the first to evade the simplicity bias - highlights the need for a better understanding and control of inductive biases in deep learning.
-
Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles. Participants work without fixed instructions, and the sequences feature rich and natural variations in action ordering, mistakes, and corrections. Assembly101 is the first multi-view action dataset, with simultaneous static (8) and egocentric (4) recordings. Sequences are annotated with more than 100K coarse and 1M fine-grained action segments, and 18M 3D hand poses. We benchmark on three action understanding tasks: recognition, anticipation and temporal segmentation. Additionally, we propose a novel task of detecting mistakes. The unique recording format and rich set of annotations allow us to investigate generalization to new toys, cross-view transfer, long-tailed distributions, and pose vs. appearance. We envision that Assembly101 will serve as a new challenge to investigate various activity understanding problems.
-
Given a set of putative 3D-3D point correspondences, we aim to remove outliers and estimate rigid transformation with 6 degrees of freedom (DOF). Simultaneously estimating these 6 DOF is time-consuming due to high-dimensional parameter space. To solve this problem, it is common to decompose 6 DOF, i.e. independently compute 3-DOF rotation and 3-DOF translation. However, high non-linearity of 3-DOF rotation still limits the algorithm efficiency, especially when the number of correspondences is large. In contrast, we propose to decompose 6 DOF into (2+1) and (1+2) DOF. Specifically, (2+1) DOF represent 2-DOF rotation axis and 1-DOF displacement along this rotation axis. (1+2) DOF indicate 1-DOF rotation angle and 2-DOF displacement orthogonal to the above rotation axis. To compute these DOF, we design a novel two-stage strategy based on inlier set maximization. By leveraging branch and bound, we first search for (2+1) DOF, and then the remaining (1+2) DOF. Thanks to the proposed transformation decomposition and two-stage search strategy, our method is deterministic and leads to low computational complexity. We extensively compare our method with state-of-the-art approaches. Our method is more accurate and robust than the approaches that provide similar efficiency to ours. Our method is more efficient than the approaches whose accuracy and robustness are comparable to ours.
-
Implicit neural representation (INR) has been successful in representing static images. Contemporary image-based INR, with the use of Fourier-based positional encoding, can be viewed as a mapping from sinusoidal patterns with different frequencies to image content. Inspired by that view, we hypothesize that it is possible to generate temporally varying content with a single image-based INR model by displacing its input sinusoidal patterns over time. By exploiting the relation between the phase information in sinusoidal functions and their displacements, we incorporate into the conventional image-based INR model a phase-varying positional encoding module, and couple it with a phase-shift generation module that determines the phase-shift values at each frame. The model is trained end-to-end on a video to jointly determine the phase-shift values at each time with the mapping from the phase-shifted sinusoidal functions to the corresponding frame, enabling an implicit video representation. Experiments on a wide range of videos suggest that such a model is capable of learning to interpret phase-varying positional embeddings into the corresponding time-varying content. More importantly, we found that the learned phase-shift vectors tend to capture meaningful temporal and motion information from the video. In particular, manipulating the phase-shift vectors induces meaningful changes in the temporal dynamics of the resulting video, enabling non-trivial temporal and motion editing effects such as temporal interpolation, motion magnification, motion smoothing, and video loop detection.
-
Neural priors are a promising direction to capture low-level vision statistics without relying on handcrafted regularizers. Recent works have successfully shown the use of neural architecture biases to implicitly regularize image denoising, super-resolution, inpainting, synthesis, scene flow, among others. They do not rely on large-scale datasets to capture prior statistics and thus generalize well to out-of-the-distribution data. Inspired by such advances, we investigate neural priors for trajectory representation. Traditionally, trajectories have been represented by a set of handcrafted bases that have limited expressibility. Here, we propose a neural trajectory prior to capture continuous spatio-temporal information without the need for offline data. We demonstrate how our proposed objective is optimized during runtime to estimate trajectories for two important tasks: Non-Rigid Structure from Motion (NRSfM) and lidar scene flow integration for self-driving scenes. Our results are competitive to many state-of-the-art methods for both tasks.
-
We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer trit-planes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.
-
Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent shortcomings, e.g., regression methods tend to overfit due to the indirect learning cost volume, and classification methods cannot directly infer the exact depth due to its discrete prediction. In this paper, we propose a novel representation, termed Unification, to unify the advantages of regression and classification. It can directly constrain the cost volume like classification methods, but also realize the sub-pixel depth prediction like regression methods. To excavate the potential of unification, we design a new loss function named Unified Focal Loss, which is more uniform and reasonable to combat the challenge of sample imbalance. Combining these two unburdened modules, we present a coarse-to-fine framework, that we call UniMVSNet. The results of ranking first on both DTU and Tanks and Temples benchmarks verify that our model not only performs the best but also has the best generalization ability.
-
In the real open world, data tends to follow long-tailed class distributions, motivating the well-studied long-tailed recognition (LTR) problem. Naive training produces models that are biased toward common classes in terms of higher accuracy. The key to addressing LTR is to balance various aspects including data distribution, training losses, and gradients in learning. We explore an orthogonal direction, weight balancing , motivated by the empirical observation that the naively trained classifier has "artificially" larger weights in norm for common classes (because there exists abundant data to train them, unlike the rare classes). We investigate three techniques to balance weights, L2-normalization, weight decay, and MaxNorm. We first point out that L2-normalization "perfectly" balances per-class weights to be unit norm, but such a hard constraint might prevent classes from learning better classifiers. In contrast, weight decay penalizes larger weights more heavily and so learns small balanced weights; the MaxNorm constraint encourages growing small weights within a norm ball but caps all the weights by the radius. Our extensive study shows that both help learn balanced weights and greatly improve the LTR accuracy. Surprisingly, weight decay, although underexplored in LTR, significantly improves over prior work. Therefore, we adopt a two-stage training paradigm and propose a simple approach to LTR: (1) learning features using the cross-entropy loss by tuning weight decay, and (2) learning classifiers using class-balanced loss by tuning weight decay and MaxNorm. Our approach achieves the state-of-the-art accuracy on five standard benchmarks, serving as a future baseline for long-tailed recognition.
-
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an image from noise with sentence embedding, and then refine the features with fine-grained word embedding iteratively. A close inspection of their generated images reveals a major limitation: even though the generated image holistically matches the description, individual image regions or parts of somethings are often not recognizable or consistent with words in the sentence, e.g. "a white crown". To address this problem, we propose a novel framework Semantic-Spatial Aware GAN for synthesizing images from input text. Concretely, we introduce a simple and effective Semantic-Spatial Aware block, which (1) learns semantic-adaptive transformation conditioned on text to effectively fuse text features and image features, and (2) learns a semantic mask in a weakly-supervised way that depends on the current text-image fusion process in order to guide the transformation spatially. Experiments on the challenging COCO and CUB bird datasets demonstrate the advantage of our method over the recent state-of-the-art approaches, regarding both visual fidelity and alignment with input text description. Code available at https://github.com/wtliao/text2image.
-
Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of labeled or unlabeled data from the shifted domain. This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e.g. autonomous driving in challenging weather conditions. To address this problem of continuous adaptation to distribution shifts, we propose Dynamic Unsupervised Adaptation (DUA). By continuously adapting the statistics of the batch normalization layers we modify the feature representations of the model. We show that by sequentially adapting a model with only a fraction of unlabeled data, a strong performance gain can be achieved. With even less than 1% of unlabeled data from the target domain, DUA already achieves competitive results to strong baselines. In addition, the computational overhead is minimal in contrast to previous approaches. Our approach is simple, yet effective and can be applied to any architecture which uses batch normalization as one of its components. We show the utility of DUA by evaluating it on a variety of domain adaptation datasets and tasks including object recognition, digit recognition and object detection.
-
We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds. The resultant distribution can then be sampled to generate likely completions, each of which exhibits plausible shape details, while being faithful to the input. To facilitate the use of transformers for 3D, we introduce a compact 3D representation, vector quantized deep implicit function (VQDIF), that utilizes spatial sparsity to represent a close approximation of a 3D shape by a short sequence of discrete variables. Experiments demonstrate that ShapeFormer outperforms prior art for shape completion from ambiguous partial inputs in terms of both completion quality and diversity. We also show that our approach effectively handles a variety of shape types, incomplete patterns, and real-world scans.
-
In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy. These other goals include out-of-distribution (OOD) robustness, prediction consistency, resilience to adversaries, calibrated uncertainty estimates, and the ability to detect anomalous inputs. However, improving performance towards these goals is often a balancing act that today's methods cannot achieve without sacrificing performance on other safety axes. For instance, adversarial training improves adversarial robustness but sharply degrades other classifier performance metrics. Similarly, strong data augmentation and regularization techniques often improve OOD robustness but harm anomaly detection, raising the question of whether a Pareto improvement on all existing safety measures is possible. To meet this challenge, we design a new data augmentation strategy utilizing the natural structural complexity of pictures such as fractals, which outperforms numerous baselines, is near Pareto-optimal, and roundly improves safety measures.
-
Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, we represent an object boundary by a linear combination of the M eigencontours. We also incorporate the eigencontours into an instance segmentation framework. Experimental results demonstrate that the proposed eigencontours can represent object boundaries more effectively and more efficiently than existing descriptors in a low-dimensional space. Furthermore, the proposed algorithm yields meaningful performances on instance segmentation datasets.
-
For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain? This setting, namely generalizable cross-modality segmentation, owning its clinical potential, is much more challenging than other related settings, e.g., domain adaptation. To achieve this goal, we in this paper propose a novel dual-normalization model by leveraging the augmented source-similar and source-dissimilar images during our generalizable segmentation. To be specific, given a single source domain, aiming to simulate the possible appearance change in unseen target domains, we first utilize a nonlinear transformation to augment source-similar and source-dissimilar images. Then, to sufficiently exploit these two types of augmentations, our proposed dual-normalization based model employs a shared backbone yet independent batch normalization layer for separate normalization. Afterward, we put forward a style-based selection scheme to automatically choose the appropriate path in the test stage. Extensive experiments on three publicly available datasets, i.e., BraTS, Cross-Modality Cardiac, and Abdominal Multi-Organ datasets, have demonstrated that our method outperforms other state-of-the-art domain generalization methods. Code is available at https://github.com/zzzqzhou/Dual-Normalization.
-
Optical flow is a fundamental method used for quantitative motion estimation on the image plane. In the deep learning era, most works treat it as a task of 'matching of features', learning to pull matched pixels as close as possible in feature space and vice versa. However, spatial affinity (smoothness constraint), another important component for motion understanding, has been largely overlooked. In this paper, we introduce a novel approach, called kernel patch attention (KPA), to better resolve the ambiguity in dense matching by explicitly taking the local context relations into consideration. Our KPA operates on each local patch, and learns to mine the context affinities for better inferring the flow fields. It can be plugged into contemporary optical flow architecture and empower the model to conduct comprehensive motion analysis with both feature similarities and spatial relations. On Sintel dataset, the proposed KPA-Flow achieves the best performance with EPE of 1.35 on clean pass and 2.36 on final pass, and it sets a new record of 4.60% in F1-all on KITTI-15 benchmark.
-
Recently, vision-language pre-training shows great potential in open-vocabulary object detection, where detectors trained on base classes are devised for detecting new classes. The class text embedding is firstly generated by feeding prompts to the text encoder of a pre-trained vision-language model. It is then used as the region classifier to supervise the training of a detector. The key element that leads to the success of this model is the proper prompt, which requires careful words tuning and ingenious design. To avoid laborious prompt engineering, there are some prompt representation learning methods being proposed for the image classification task, which however can only be sub-optimal solutions when applied to the detection task. In this paper, we introduce a novel method, detection prompt (DetPro), to learn continuous prompt representations for open-vocabulary object detection based on the pre-trained vision-language model. Different from the previous classification-oriented methods, DetPro has two highlights: 1) a background interpretation scheme to include the proposals in image background into the prompt training; 2) a context grading scheme to separate proposals in image foreground for tailored prompt training. We assemble DetPro with ViLD, a recent state-of-the-art openworld object detector, and conduct experiments on the LVIS as well as transfer learning on the Pascal VOC, COCO, Objects365 datasets. Experimental results show that our DetPro outperforms the baseline ViLD [5] in all settings, e.g., +3.4 APbox and +3.0 APmask improvements on the novel classes of LVIS. Code and models are available at https://github.com/dyabel/detpro.
-
Recording fast motion in a high FPS (frame-per-second) requires expensive high-speed cameras. As an alternative, interpolating low-FPS videos from commodity cameras has attracted significant attention. If only low-FPS videos are available, motion assumptions (linear or quadratic) are necessary to infer intermediate frames, which fail to model complex motions. Event camera, a new camera with pixels producing events of brightness change at the temporal resolution of \mu s (10^ -6 second ), is a game-changing device to enable video interpolation at the presence of arbitrarily complex motion. Since event camera is a novel sensor, its potential has not been fulfilled due to the lack of processing algorithms. The pioneering work Time Lens introduced event cameras to video interpolation by designing optical devices to collect a large amount of paired training data of high-speed frames and events, which is too costly to scale. To fully unlock the potential of event cameras, this paper proposes a novel TimeReplayer algorithm to interpolate videos captured by commodity cameras with events. It is trained in an unsupervised cycle-consistent style, canceling the necessity of high-speed training data and bringing the additional ability of video extrapolation. Its state-of-the-art results and demo videos in supplementary reveal the promising future of event-based vision.
-
Continual learning is an important problem for achieving human-level intelligence in real-world applications as an agent must continuously accumulate knowledge in response to streaming data/tasks. In this work, we consider a general and yet under-explored incremental learning problem in which both the class distribution and class-specific domain distribution change over time. In addition to the typical challenges in class incremental learning, this setting also faces the intra-class stability-plasticity dilemma and intra-class domain imbalance problems. To address above issues, we develop a novel domain-aware continual learning method based on the EM framework. Specifically, we introduce a flexible class representation based on the von Mises-Fisher mixture model to capture the intra-class structure, using an expansion-and-reduction strategy to dynamically increase the number of components according to the class complexity. Moreover, we design a bi-level balanced memory to cope with data imbalances within and across classes, which combines with a distillation loss to achieve better inter- and intra-class stability-plasticity trade-off. We conduct exhaustive experiments on three benchmarks: iDigits, iDomainNet and iCIFAR-20. The results show that our approach consistently outperforms previous methods by a significant margin, demonstrating its superiority.
-
We introduce an interactive image segmentation and visualization framework for identifying, inspecting, and editing tiny objects (just a few pixels wide) in large multi-megapixel high-dynamic-range (HDR) images. Detecting cosmic rays (CRs) in astronomical observations is a cumbersome workflow that requires multiple tools, so we developed an interactive toolkit that unifies model inference, HDR image visualization, segmentation mask inspection and editing into a single graphical user interface. The feature set, initially designed for astronomical data, makes this work a useful research-supporting tool for human-in-the-loop tiny-object segmentation in scientific areas like biomedicine, materials science, remote sensing, etc., as well as computer vision. Our interface features mouse-controlled, synchronized, dual-window visualization of the image and the segmentation mask, a critical feature for locating tiny objects in multi-megapixel images. The browser-based tool can be readily hosted on the web to provide multi-user access and GPU acceleration for any device. The toolkit can also be used as a high-precision annotation tool, or adapted as the frontend for an interactive machine learning framework. Our open-source dataset, CR detection model, and visualization toolkit are available at https://github.com/cy-xu/cosmic-conn.
-
Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a method that leverages the best of both worlds. In this paper we present a new framework, ActiveZero, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. First, we demonstrate the transferability of our method to out-of-distribution real data by using a mixed domain learning strategy. In the simulation domain, we use a combination of supervised disparity loss and self-supervised losses on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised losses on a dataset that is out-of-distribution from either training simulation data or test real data. Second, our method introduces a novel self-supervised loss called temporal IR reprojection to increase the robustness and accuracy of our reprojections in hard-to-perceive regions. Finally, we show how the method can be trained end-to-end and that each module is important for attaining the end result. Extensive qualitative and quantitative evaluations on real data demonstrate state of the art results that can even beat a commercial depth sensor.
-
Transformers have been successfully applied to computer vision due to its powerful modelling capacity with self-attention. However, the good performance of transformers heavily depends on enormous training images. Thus, a data-efficient transformer solution is urgently needed. In this work, we propose an early knowledge distillation framework, which is termed as DearKD, to improvethe data-efficiency required by transformers. Our DearKD is a two-stage framework that first distills the inductive biases from the early intermediate layers of a CNN and then gives the transformer full play by training without distillation. Further, our DearKD can also be applied to the extreme data-free case where no real images are available, where we propose a boundary-preserving intra-divergence loss based on DeepInversion to further close the performance gap against the full-data counterpart. Extensive experiments on ImageNet, partial ImageNet, data-free setting and other downstream tasks prove the superiority of DearKD over its baselines and state-of-the-art methods.
-
We propose a novel method of registering less-overlap RGB-D scans. Our method learns global information of a scene to construct a panorama, and aligns RGB-D scans to the panorama to perform registration. Different from existing methods that use local feature points to register less-overlap RGB-D scans and mismatch too much, we use global information to guide the registration, thereby alleviating the mismatching problem by preserving global consistency of alignments. To this end, we build a scene inference network to construct the panorama representing global information. We introduce a reinforcement learning strategy to iteratively align RGB-D scans with the panorama and refine the panorama representation, which reduces the noise of global information and preserves global consistency of both geometric and photometric alignments. Experimental results on benchmark datasets including SUNCG, Matterport, and ScanNet show the superiority of our method.
-
Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We also devise a multi-task learning for better optimization convergence and depth accuracy. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving overall reconstruction score of 0.33mm on DTU and f-score of 59.48% on Tanks & Temples.
-
Partially-supervised instance segmentation is a task which requests segmenting objects from novel categories via learning on limited base categories with annotated masks thus eliminating demands of heavy annotation burden. The key to addressing this task is to build an effective class-agnostic mask segmentation model. Unlike previous methods that learn such models only on base categories, in this paper, we propose a new method, named ContrastMask, which learns a mask segmentation model on both base and novel categories under a unified pixel-level contrastive learning framework. In this framework, annotated masks of base categories and pseudo masks of novel categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa. Through this framework, feature discrimination between foreground and background is largely improved, facilitating learning of the class-agnostic mask segmentation model. Exhaustive experiments on the COCO dataset demonstrate the superiority of our method, which outperforms previous state-of-the-arts.
-
Recently deep learning methods have shown significant progress in data clustering tasks. Deep clustering methods (including distance-based methods and subspace-based methods) integrate clustering and feature learning into a unified framework, where there is a mutual promotion between clustering and representation. However, deep subspace clustering methods are usually in the framework of self-expressive model and hence have quadratic time and space complexities, which prevents their applications in large-scale clustering and real-time clustering. In this paper, we propose a new mechanism for deep clustering. We aim to learn the subspace bases from deep representation in an iterative refining manner while the refined subspace bases help learning the representation of the deep neural networks in return. The proposed method is out of the self-expressive framework, scales to the sample size linearly, and is applicable to arbitrarily large datasets and online clustering scenarios. More importantly, the clustering accuracy of the proposed method is much higher than its competitors. Extensive comparison studies with state-of-the-art clustering approaches on benchmark datasets demonstrate the superiority of the proposed method.
-
Due to the visual ambiguity, purely kinematic formulations on monocular human motion capture are often physically incorrect, biomechanically implausible, and can not reconstruct accurate interactions. In this work, we focus on exploiting the high-precision and non-differentiable physics simulator to incorporate dynamical constraints in motion capture. Our key-idea is to use real physical supervisions to train a target pose distribution prior for sampling-based motion control to capture physically plausible human motion. To obtain accurate reference motion with terrain interactions for the sampling, we first introduce an interaction constraint based on SDF (Signed Distance Field) to enforce appropriate ground contact modeling. We then design a novel two-branch decoder to avoid stochastic error from pseudo ground-truth and train a distribution prior with the non-differentiable physics simulator. Finally, we regress the sampling distribution from the current state of the physical character with the trained prior and sample satisfied target poses to track the estimated reference motion. Qualitative and quantitative results show that we can obtain physically plausible human motion with complex terrain interactions, human shape variations, and diverse behaviors. More information can be found at https://www.yangangwang.com/papers/HBZ-NM-2022-03.html
-
Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is helpful in modeling distant correspondences, error accumulation is inevitable due to the propagation mechanism. In this work, we present a novel, generic iterative alignment module which employs a gradual refinement scheme for sub-alignments, yielding more accurate motion compensation. To further enhance the alignment accuracy and temporal consistency, we develop a non-parametric re-weighting method, where the importance of each neighboring frame is adaptively evaluated in a spatial-wise way for aggregation. By virtue of the proposed strategies, our model achieves state-of-the-art performance on multiple benchmarks across a range of video restoration tasks including video super-resolution, denoising and deblurring.
-
Vision Transformers (ViTs) and their multi-scale and hierarchical variations have been successful at capturing image representations but their use has been generally studied for low-resolution images (e.g. - 256x256, 384x384). For gigapixel whole-slide imaging (WSI) in computational pathology, WSIs can be as large as 150000x150000 pixels at 20x magnification and exhibit a hierarchical structure of visual tokens across varying resolutions: from 16x16 images capture spatial patterns among cells, to 4096x4096 images characterizing interactions within the tissue microenvironment. We introduce a new ViT architecture called the Hierarchical Image Pyramid Transformer (HIPT), which leverages the natural hierarchical structure inherent in WSIs using two levels of self-supervised learning to learn high-resolution image representations. HIPT is pretrained across 33 cancer types using 10,678 gigapixel WSIs, 408,218 4096x4096 images, and 104M 256x256 images. We benchmark HIPT representations on 9 slide-level tasks, and demonstrate that: 1) HIPT with hierarchical pretraining outperforms current state-of-the-art methods for cancer subtyping and survival prediction, 2) self-supervised ViTs are able to model important inductive biases about the hierarchical structure of phenotypes in the tumor microenvironment.
-
This paper aims at recovering the shape of a scene with unknown, non-Lambertian, and possibly spatially-varying surface materials. When the shape of the object is highly complex and that shadows cast on the surface, the task becomes very challenging. To overcome these challenges, we propose a coordinate-based deep MLP (multilayer perceptron) to parameterize both the unknown 3D shape and the unknown reflectance at every surface point. This network is able to leverage the observed photometric variance and shadows on the surface, and recover both surface shape and general non-Lambertian reflectance. We explicitly predict cast shadows, mitigating possible artifacts on these shadowing regions, leading to higher estimation accuracy. Our framework is entirely self-supervised, in the sense that it requires neither ground truth shape nor BRDF. Tests on real-world images demonstrate that our method outperform existing methods by a significant margin. Thanks to the small size of the MLP-net, our method is an order of magnitude faster than previous CNN-based methods.
-
Transfer learning, where the goal is to transfer the well-trained deep learning models from a primary source task to a new task, is a crucial learning scheme for on-device machine learning, due to the fact that IoT/edge devices collect and then process massive data in our daily life. However, due to the tiny memory constraint in IoT/edge devices, such on-device learning requires ultra-small training memory footprint, bringing new challenges for memory-efficient learning. Many existing works solve this problem by reducing the number of trainable parameters. However, this doesn't directly translate to memory-saving since the major bottleneck is the activations, not parameters. To develop memory-efficient on-device transfer learning, in this work, we are the first to approach the concept of transfer learning from a new perspective of intermediate feature reprogramming of a pre-trained model (i.e., backbone). To perform this lightweight and memory-efficient reprogramming, we propose to train a tiny Reprogramming Network (Rep-Net) directly from the new task input data, while freezing the backbone model. The proposed Rep-Net model interchanges the features with the backbone model using an activation connector at regular intervals to mutually benefit both the backbone model and Rep-Net model features. Through extensive experiments, we validate each design specs of the proposed Rep-Net model in achieving highly memory-efficient on-device reprogramming. Our experiments establish the superior performance (i.e., low training memory and high accuracy) of Rep-Net compared to SOTA on-device transfer learning schemes across multiple benchmarks.
-
Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present RepSurf (representative surfaces), a novel representation of point clouds to explicitly depict the very local structure. We explore two variants of RepSurf, Triangular RepSurf and Umbrella RepSurf inspired by triangle meshes and umbrella curvature in computer graphics. We compute the representations of RepSurf by predefined geometric priors after surface reconstruction. RepSurf can be a plug-and-play module for most point cloud models thanks to its free collaboration with irregular points. Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. With an increase of around 0.008M number of parameters, 0.04G FLOPs, and 1.12ms inference time, our method achieves 94.7% (+0.5%) on ModelNet40, and 84.6% (+1.8%) on ScanObjectNN for classification, while 74.3% (+0.8%) mIoU on S3DIS 6-fold, and 70.0% (+1.6%) mIoU on ScanNet for segmentation. For detection, previous state-of-the-art detector with our RepSurf obtains 71.2% (+2.1%) mAP_25, 54.8% (+2.0%) mAP_50 on ScanNetV2, and 64.9% (+1.9%) mAP_25, 47.1% (+2.5%) mAP_50 on SUN RGB-D. Our lightweight Triangular RepSurf performs its excellence on these benchmarks as well. The code is publicly available at https://github.com/hancyran/RepSurf.
-
We propose a new video camouflaged object detection (VCOD) framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames. An essential property of camouflaged objects is that they usually exhibit patterns similar to the background and thus make them hard to identify from still images. Therefore, effectively handling temporal dynamics in videos becomes the key for the VCOD task as the camouflaged objects will be noticeable when they move. However, current VCOD methods often leverage homography or optical flows to represent motions, where the detection error may accumulate from both the motion estimation error and the segmentation error. On the other hand, our method unifies motion estimation and object segmentation within a single optimization framework. Specifically, we build a dense correlation volume to implicitly capture motions between neighbouring frames and utilize the final segmentation supervision to optimize the implicit motion estimation and segmentation jointly. Furthermore, to enforce temporal consistency within a video sequence, we jointly utilize a spatio-temporal transformer to refine the short-term predictions. Extensive experiments on VCOD benchmarks demonstrate the architectural effectiveness of our approach. We also provide a large-scale VCOD dataset named MoCA-Mask with pixel-level handcrafted ground-truth masks and construct a comprehensive VCOD benchmark with previous methods to facilitate research in this direction. Dataset Link: https://xueliancheng.github.io/SLT-Net-project.
-
This paper proposes a universal framework, called OVE6D, for model-based 6D object pose estimation from a single depth image and a target object mask. Our model is trained using purely synthetic data rendered from ShapeNet, and, unlike most of the existing methods, it generalizes well on new real-world objects without any fine-tuning. We achieve this by decomposing the 6D pose into viewpoint, in-plane rotation around the camera optical axis and translation, and introducing novel lightweight modules for estimating each component in a cascaded manner. The resulting network contains less than 4M parameters while demonstrating excellent performance on the challenging T-LESS and Occluded LINEMOD datasets without any dataset-specific training. We show that OVE6D outperforms some contemporary deep learning-based pose estimation methods specifically trained for individual objects or datasets with real-world training data.
-
In the clinic, resected tissue samples are stained with Hematoxylin-and-Eosin (H&E) and/or Immunhistochemistry (IHC) stains and presented to the pathologists on glass slides or as digital scans for diagnosis and assessment of disease progression. Cell-level quantification, e.g. in IHC protein expression scoring, can be extremely inefficient and subjective. We present DeepLIIF (https://deepliif.org), a first free online platform for efficient and reproducible IHC scoring. DeepLIIF outperforms current state-of-the-art approaches (relying on manual error-prone annotations) by virtually restaining clinical IHC slides with more informative multiplex immunofluorescence staining. Our DeepLIIF cloud-native platform supports (1) more than 150 proprietary/non-proprietary input formats via the Bio-Formats standard, (2) interactive adjustment, visualization, and downloading of the IHC quantification results and the accompanying restained images, (3) consumption of an exposed workflow API programmatically or through interactive plugins for open source whole slide image viewers such as QuPath/ImageJ, and (4) auto scaling to efficiently scale GPU resources based on user demand.
-
Video summarization has recently engaged increasing attention in computer vision communities. However, the scarcity of annotated data has been a key obstacle in this task. To address it, this work explores a new solution for video summarization by transferring samples from a correlated task (i.e., video moment localization) equipped with abundant training data. Our main insight is that the annotated video moments also indicate the semantic highlights of a video, essentially similar to video summary. Approximately, the video summary can be treated as a sparse, redundancy-free version of the video moments. Inspired by this observation, we propose an importance Propagation based collaborative Teaching Network (iPTNet). It consists of two separate modules that conduct video summarization and moment localization, respectively. Each module estimates a frame-wise importance map for indicating keyframes or moments. To perform cross-task sample transfer, we devise an importance propagation module that realizes the conversion between summarization-guided and localization-guided importance maps. This way critically enables optimizing one of the tasks using the data from the other task. Additionally, in order to avoid error amplification caused by batch-wise joint training, we devise a collaborative teaching scheme, which adopts a cross-task mean teaching strategy to realize the joint optimization of the two tasks and provide robust frame-level teaching signals. Extensive experiments on video summarization benchmarks demonstrate that iPTNet significantly outperforms previous state-of-the-art video summarization methods, serving as an effective solution that overcomes the data scarcity issue in video summarization.
-
Current methods for object detection, segmentation, and tracking fail in the presence of severe occlusions in busy urban environments. Labeled real data of occlusions is scarce (even in large datasets) and synthetic data leaves a domain gap, making it hard to explicitly model and learn occlusions. In this work, we present the best of both the real and synthetic worlds for automatic occlusion supervision using a large readily available source of data: time-lapse imagery from stationary webcams observing street intersections over weeks, months, or even years. We introduce a new dataset, Watch and Learn Time-lapse (WALT), consisting of 12 (4K and 1080p) cameras capturing urban environments over a year. We exploit this real data in a novel way to automatically mine a large set of unoccluded objects and then composite them in the same views to generate occlusions. This longitudinal self-supervision is strong enough for an amodal network to learn object-occluder-occluded layer representations. We show how to speed up the discovery of unoccluded objects and relate the confidence in this discovery to the rate and accuracy of training occluded objects. After watching and automatically learning for several days, this approach shows significant performance improvement in detecting and segmenting occluded people and vehicles, over human-supervised amodal approaches.
-
In this paper, we study an untouched problem in visible-infrared person re-identification (VI-ReID), namely, Twin Noise Labels (TNL) which refers to as noisy annotation and correspondence. In brief, on the one hand, it is inevitable to annotate some persons with the wrong identity due to the complexity in data collection and annotation, e.g., the poor recognizability in the infrared modality. On the other hand, the wrongly annotated data in a single modality will eventually contaminate the cross-modal correspondence, thus leading to noisy correspondence. To solve the TNL problem, we propose a novel method for robust VI-ReID, termed DuAlly Robust Training (DART). In brief, DART first computes the clean confidence of annotations by resorting to the memorization effect of deep neural networks. Then, the proposed method rectifies the noisy correspondence with the estimated confidence and further divides the data into four groups for further utilizations. Finally, DART employs a novel dually robust loss consisting of a soft identification loss and an adaptive quadruplet loss to achieve robustness on the noisy annotation and noisy correspondence. Extensive experiments on SYSU-MM01 and RegDB datasets verify the effectiveness of our method against the twin noisy labels compared with five state-of-the-art methods. The code could be accessed from https://github.com/XLearning-SCU/2022-CVPR-DART.
-
As a bio-inspired sensor with high temporal resolution, the spiking camera has an enormous potential in real applications, especially for motion estimation in high-speed scenes. However, frame-based and event-based methods are not well suited to spike streams from the spiking camera due to the different data modalities. To this end, we present, SCFlow, a tailored deep learning pipeline to estimate optical flow in high-speed scenes from spike streams. Importantly, a novel input representation is introduced which can adaptively remove the motion blur in spike streams according to the prior motion. Further, for training SCFlow, we synthesize two sets of optical flow data for the spiking camera, SPIkingly Flying Things and Photo-realistic High-speed Motion, denoted as SPIFT and PHM respectively, corresponding to random high-speed and well-designed scenes. Experimental results show that the SCFlow can predict optical flow from spike streams in different high-speed scenes. Moreover, SCFlow shows promising generalization on real spike streams. Codes and datasets refer to https://github.com/Acnext/Optical-Flow-For-Spiking-Camera.
-
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1% top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 49%/61% fewer MACs. The effectiveness of PoolFormer verifies our hypothesis and urges us to initiate the concept of "MetaFormer", a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.
-
In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce a method, named GradViT, that optimizes random noise into naturally looking images via an iterative process. The optimization objective consists of (i) a loss on matching the gradients, (ii) image prior in the form of distance to batch normalization statistics of a pretrained CNN model, and (iii) a total variation regularization on patches to guide correct recovery locations. We propose a unique loss scheduling function to overcome local minima during optimization. We evaluate GadViT on ImageNet1K and MS-Celeb-1M datasets, and observe unprecedentedly high fidelity and closeness to the original (hidden) data. During the analysis we find that vision transformers are significantly more vulnerable than previously studied CNNs due to the presence of the attention mechanism. Our method demonstrates new state-of-the-art results for gradient inversion in both qualitative and quantitative metrics. Project page at https://gradvit.github.io.
-
Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate super-resolved videos with higher resolution (HR) and higher frame rate (HFR). Quite intuitively, pioneering two-stage based methods complete ST-VSR directly combining two sub-tasks: Spatial Video Super-Resolution (S-VSR) and Temporal Video Super-Resolution (T-VSR) but ignore the reciprocal relations among them. Specifically, 1) T-VSR to S-VSR: temporal correlations help accurate spatial detail representation with more clues; 2) S-VSR to T-VSR: abundant spatial information contributes to the refinement of temporal prediction. To this end, we propose a one-stage based Cycle-projected Mutual learning network (CycMu-Net) for ST-VSR, which makes full use of spatial-temporal correlations via the mutual learning between S-VSR and T-VSR. Specifically, we propose to exploit the mutual information among them via iterative up-and-down projections, where the spatial and temporal features are fully fused and distilled, helping the high-quality video reconstruction. Besides extensive experiments on benchmark datasets, we also compare our proposed CycMu-Net with S-VSR and T-VSR tasks, demonstrating that our method significantly outperforms state-of-the-art methods. Codes are publicly available at: https://github.com/hhhhhumengshun/CycMuNet.
-
We present a novel Transformer-based network architecture for instance-aware image-to-image translation, dubbed InstaFormer, to effectively integrate global- and instance-level information. By considering extracted content features from an image as tokens, our networks discover global consensus of content features by considering context information through a self-attention module in Transformers. By augmenting such tokens with an instance-level feature extracted from the content feature with respect to bounding box information, our framework is capable of learning an interaction between object instances and the global image, thus boosting the instance-awareness. We replace layer normalization (LayerNorm) in standard Transformers with adaptive instance normalization (AdaIN) to enable a multi-modal translation with style codes. In addition, to improve the instance-awareness and translation quality at object regions, we present an instance-level content contrastive loss defined between input and translated image. We conduct experiments to demonstrate the effectiveness of our InstaFormer over the latest methods and provide extensive ablation studies.
-
This work addresses the task of overhead image segmentation when auxiliary ground-level images are available. Recent work has shown that performing joint inference over these two modalities, often called near/remote sensing, can yield significant accuracy improvements. Extending this line of work, we introduce the concept of geospatial attention, a geometry-aware attention mechanism that explicitly considers the geospatial relationship between the pixels in a ground-level image and a geographic location. We propose an approach for computing geospatial attention that incorporates geometric features and the appearance of the overhead and ground-level imagery. We introduce a novel architecture for near/remote sensing that is based on geospatial attention and demonstrate its use for five segmentation tasks. The results demonstrate that our method significantly outperforms the previous state-of-the-art methods.
-
Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG. One of the keys to this success is learned entropy models that estimate the probability distribution of the quantized latent representation. Like other vision tasks, most recent learned entropy models are based on convolutional neural networks (CNNs). However, CNNs have a limitation in modeling long-range dependencies due to their nature of local connectivity, which can be a significant bottleneck in image compression where reducing spatial redundancy is a key point. To overcome this issue, we propose a novel entropy model called Information Transformer (Informer) that exploits both global and local information in a content-dependent manner using an attention mechanism. Our experiments show that Informer improves rate-distortion performance over the state-of-the-art methods on the Kodak and Tecnick datasets without the quadratic computational complexity problem. Our source code is available at https://github.com/naver-ai/informer.
-
Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial matching fashion. However, people tend to overlook the fact that, due to the architecture differences, the semantic information on the same spatial location usually vary. This greatly undermines the underlying assumption of the one-to-one distillation approach. To this end, we propose a novel one-to-all spatial matching knowledge distillation approach. Specifically, we allow each pixel of the teacher feature to be distilled to all spatial locations of the student features given its similarity, which is generated from a target-aware transformer. Our approach surpasses the state-of-the-art methods by a significant margin on various computer vision benchmarks, such as ImageNet, Pascal VOC and COCOStuff10k. Code is available at https://github.com/sihaoevery/TaT.
-
Existing video understanding approaches, such as 3D convolutional neural networks and Transformer-Based methods, usually process the videos in a clip-wise manner. Hence huge GPU memory is needed, and fixed-length video clips are usually required. We introduce a novel Recurrent Vision Transformer (RViT) framework for spatial-temporal representation learning to achieve the video action recognition task. Specifically, the proposed RViT is equipped with an attention gate which is utilized to build interaction between current frame input and previous hidden state, thus aggregating the global level inter-frame features through the hidden state. RViT is executed recurrently to process a video clip by giving the current frame and previous hidden state. The RViT can capture both spatial and temporal features because of the attention gate and recurrent execution. Besides, the proposed RViT can work on both fixed-length and variant-length video clips properly without requiring large GPU memory thanks to the frame by frame processing flow. Our experiment results verify that RViT can achieve state-of-the-art performance on various datasets for the video recognition task. Specifically, RViT can achieve a top-1 accuracy of 81.5% on Kinetics-400, 92.31% on Jester, 67.9% on Something-Something-V2, and an mAP accuracy of 66.1% on Charades.
-
Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust. However, a serious problem of catastrophic overfitting exists, i.e., the robust accuracy against projected gradient descent (PGD) attack suddenly drops to 0% during the training. In this paper, we approach this problem from a novel perspective of optimization and firstly reveal the close link between the fast-growing gradient of each sample and overfitting, which can also be applied to understand robust overfitting in multi-step AT. To control the growth of the gradient, we propose a new AT method, Subspace Adversarial Training (Sub-AT), which constrains AT in a carefully extracted subspace. It successfully resolves both kinds of overfitting and significantly boosts the robustness. In subspace, we also allow single-step AT with larger steps and larger radius, further improving the robustness performance. As a result, we achieve state-of-the-art single-step AT performance. Without any regularization term, our single-step AT can reach over 51% robust accuracy against strong PGD-50 attack of radius 8/255 on CIFAR-10, reaching a competitive performance against standard multi-step PGD-10 AT with huge computational advantages. The code is released at https://github.com/nblt/Sub-AT.
-
3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection
As 3D object detection on point clouds relies on the geometrical relationships between the points, non-standard object shapes can hinder a method's detection capability. However, in safety-critical settings, robustness to out-of-domain and long-tail samples is fundamental to circumvent dangerous issues, such as the misdetection of damaged or rare cars. In this work, we substantially improve the generalization of 3D object detectors to out-of-domain data by deforming point clouds during training. We achieve this with 3D-VField: a novel data augmentation method that plausibly deforms objects via vector fields learned in an adversarial fashion. Our approach constrains 3D points to slide along their sensor view rays while neither adding nor removing any of them. The obtained vectors are transferable, sample-independent and preserve shape and occlusions. Despite training only on a standard dataset, such as KITTI, augmenting with our vector fields significantly improves the generalization to differently shaped objects and scenes. Towards this end, we propose and share CrashD: a synthetic dataset of realistic damaged and rare cars, with a variety of crash scenarios. Extensive experiments on KITTI, Waymo, our CrashD and SUN RGB-D show the generalizability of our techniques to out-of-domain data, different models and sensors, namely LiDAR and ToF cameras, for both indoor and outdoor scenes. Our CrashD dataset is available at https://crashd-cars.github.io.
-
Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses these expressions. Here we propose a system that can generate image segmentations based on arbitrary prompts at test time. A prompt can be either a text or an image. This approach enables us to create a unified model (trained once) for three common segmentation tasks, which come with distinct challenges: referring expression segmentation, zero-shot segmentation and one-shot segmentation. We build upon the CLIP model as a backbone which we extend with a transformer-based decoder that enables dense prediction. After training on an extended version of the PhraseCut dataset, our system generates a binary segmentation map for an image based on a free-text prompt or on an additional image expressing the query. We analyze different variants of the latter image-based prompts in detail. This novel hybrid input allows for dynamic adaptation not only to the three segmentation tasks mentioned above, but to any binary segmentation task where a text or image query can be formulated. Finally, we find our system to adapt well to generalized queries involving affordances or properties. Code is available at https://eckerlab.org/code/clipseg
-
Autonomous driving datasets have played an important role in validating the advancement of intelligent vehicle algorithms including localization, perception and prediction in academic areas. However, current existing datasets pay more attention to the structured urban road, which hampers the exploration on unstructured special scenarios. Moreover, the open-pit mine is one of the typical representatives for them. Therefore, we introduce the Autonomous driving dataset on the Mining scene (AutoMine) for positioning and perception tasks in this paper. The AutoMine is collected by multiple acquisition platforms including an SUV, a wide-body mining truck and an ordinary mining truck, depending on the actual mine operation scenarios. The dataset consists of 18+ driving hours, 18K annotated lidar and image frames for 3D perception with various mines, time-of-the-day and weather conditions. The main contributions of the AutoMine dataset are as follows: 1.The first autonomous driving dataset for perception and localization in mine scenarios. 2.There are abundant dynamic obstacles of 9 degrees of freedom with large dimension difference (mining trucks and pedestrians) and extreme climatic conditions (the dust and snow) in the mining area. 3.Multi-platform acquisition strategies could capture mining data from multiple perspectives that fit the actual operation. More details can be found in our website(https://automine.cc).
-
Learned image compression has achieved great success due to its excellent modeling capacity, but seldom further considers the Rate-Distortion Optimization (RDO) of each input image. To explore this potential in the learned codec, we make the first attempt to build a neural data-dependent transform and introduce a continuous online mode decision mechanism to jointly optimize the coding efficiency for each individual image. Specifically, apart from the image content stream, we employ an additional model stream to generate the transform parameters at the decoder side. The presence of a model stream enables our model to learn more abstract neural-syntax, which helps cluster the latent representations of images more compactly. Beyond the transform stage, we also adopt neural-syntax based post-processing for the scenarios that require higher quality reconstructions regardless of extra decoding overhead. Moreover, the involvement of the model stream further makes it possible to optimize both the representation and the decoder in an online way, i.e. RDO at the testing time. It is equivalent to a continuous online mode decision, like coding modes in the traditional codecs, to improve the coding efficiency based on the individual input image. The experimental results show the effectiveness of the proposed neural-syntax design and the continuous online mode decision mechanism, demonstrating the superiority of our method in coding efficiency.
-
Weakly supervised object localization (WSOL) aims to localize objects using only image-level labels. Recently a new paradigm has emerged by generating a foreground prediction map (FPM) to achieve localization task. Existing FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator. We argue for using activation value to achieve more efficient learning. It is based on the experimental observation that, for a trained network, CE converges to zero when the foreground mask covers only part of the object region. While activation value increases until the mask expands to the object boundary, which indicates that more object areas can be learned by using activation value. In this paper, we propose a Background Activation Suppression (BAS) method. Specifically, an Activation Map Constraint module (AMC) is designed to facilitate the learning of generator by suppressing the background activation value. Meanwhile, by using the foreground region guidance and the area constraint, BAS can learn the whole region of the object. In the inference phase, we consider the prediction maps of different categories together to obtain the final localization results. Extensive experiments show that BAS achieves significant and consistent improvement over the baseline methods on the CUB-200-2011 and ILSVRC datasets. Code and models are available at https://github.com/wpy1999/BAS.
-
Accurate prediction of future human positions is an essential task for modern video-surveillance systems. Current state-of-the-art models usually rely on a "history" of past tracked locations (e.g., 3 to 5 seconds) to predict a plausible sequence of future locations (e.g., up to the next 5 seconds). We feel that this common schema neglects critical traits of realistic applications: as the collection of input trajectories involves machine perception (i.e., detection and tracking), incorrect detection and fragmentation errors may accumulate in crowded scenes, leading to tracking drifts. On this account, the model would be fed with corrupted and noisy input data, thus fatally affecting its prediction performance. In this regard, we focus on delivering accurate predictions when only a few input observations are used, thus potentially lowering the risks associated with automatic perception. To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones). We show that a properly defined teacher supervision allows a student network to perform comparably to state-of-the-art approaches that demand more observations. Besides, extensive experiments on common trajectory forecasting datasets highlight that our student network better generalizes to unseen scenarios.
-
Knowledge distillation (KD) is a widely-used technique that utilizes large networks to improve the performance of compact models. Previous KD approaches usually aim to guide the student to mimic the teacher's behavior completely in the representation space. However, such one-to-one corresponding constraints may lead to inflexible knowledge transfer from the teacher to the student, especially those with low model capacities. Inspired by the ultimate goal of KD methods, we propose a novel Evaluation oriented KD method (EKD) for deep face recognition to directly reduce the performance gap between the teacher and student models during training. Specifically, we adopt the commonly used evaluation metrics in face recognition, i.e., False Positive Rate (FPR) and True Positive Rate (TPR) as the performance indicator. According to the evaluation protocol, the critical pair relations that cause the TPR and FPR difference between the teacher and student models are selected. Then, the critical relations in the student are constrained to approximate the corresponding ones in the teacher by a novel rank-based loss function, giving more flexibility to the student with low capacity. Extensive experimental results on popular benchmarks demonstrate the superiority of our EKD over state-of-the-art competitors.
-
Subgraph recognition aims at discovering a compressed substructure of a graph that is most informative to the graph property. It can be formulated by optimizing Graph Information Bottleneck (GIB) with a mutual information estimator. However, GIB suffers from training instability and degenerated results due to its intrinsic optimization process. To tackle these issues, we reformulate the subgraph recognition problem into two steps: graph perturbation and subgraph selection, leading to a novel Variational Graph Information Bottleneck (VGIB) framework. VGIB first employs the noise injection to modulate the information flow from the input graph to the perturbed graph. Then, the perturbed graph is encouraged to be informative to the graph property. VGIB further obtains the desired subgraph by filtering out the noise in the perturbed graph. With the customized noise prior for each input, the VGIB objective is endowed with a tractable variational upper bound, leading to a superior empirical performance as well as theoretical properties. Extensive experiments on graph interpretation, explainability of Graph Neural Networks, and graph classification show that VGIB finds better subgraphs than existing methods Extensive experiments on the explainability of Graph Neural Networks, graph interpretation, and graph classification show that VGIB finds better subgraphs than existing methods.
-
Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic solutions usually decompose the VPS task into several sub-tasks and utilize multiple surrogates (e.g. boxes and masks, centers and offsets) to represent objects. However, this divide-and-conquer strategy requires complex post-processing in both spatial and temporal domains and is vulnerable to failures from surrogate tasks. In this paper, inspired by object-centric learning which learns compact and robust object representations, we present Slot-VPS, the first end-to-end framework for this task. We encode all panoptic entities in a video, including both foreground instances and background semantics, in a unified representation called panoptic slots. The coherent spatio-temporal object's information is retrieved and encoded into the panoptic slots by the proposed Video Panoptic Retriever, enabling to localize, segment, differentiate, and associate objects in a unified manner. Finally, the output panoptic slots can be directly converted into the class, mask, and object ID of panoptic objects in the video. We conduct extensive ablation studies and demonstrate the effectiveness of our approach on two benchmark datasets, Cityscapes-VPS (val and test sets) and VIPER (val set), achieving new state-of-the-art performance of 63.7, 63.3 and 56.2 VPQ, respectively.
-
We propose a method for jointly estimating the 3D motion, 3D shape, and appearance of highly motion-blurred objects from a video. To this end, we model the blurred appearance of a fast moving object in a generative fashion by parametrizing its 3D position, rotation, velocity, acceleration, bounces, shape, and texture over the duration of a predefined time window spanning multiple frames. Using differentiable rendering, we are able to estimate all parameters by minimizing the pixel-wise reprojection error to the input video via backpropagating through a rendering pipeline that accounts for motion blur by averaging the graphics output over short time intervals. For that purpose, we also estimate the camera exposure gap time within the same optimization. To account for abrupt motion changes like bounces, we model the motion trajectory as a piece-wise polynomial, and we are able to estimate the specific time of the bounce at sub-frame accuracy. Experiments on established benchmark datasets demonstrate that our method outperforms previous methods for fast moving object deblurring and 3D reconstruction.
-
Video Instance Segmentation (VIS) aims to simultaneously classify, segment, and track multiple object instances in videos. Recent clip-level VIS takes a short video clip as input each time showing stronger performance than frame-level VIS (tracking-by-segmentation), as more temporal context from multiple frames is utilized. Yet, most clip-level methods are neither end-to-end learnable nor real-time. These limitations are addressed by the recent VIS transformer (VisTR) which performs VIS end-to-end within a clip. However, VisTR suffers from long training time due to its frame-wise dense attention. In addition, VisTR is not fully end-to-end learnable in multiple video clips as it requires a hand-crafted data association to link instance tracklets between successive clips. This paper proposes EfficientVIS, a fully end-to-end framework with efficient training and inference. At the core are tracklet query and tracklet proposal that associate and segment regions-of-interest (RoIs) across space and time by an iterative query-video interaction. We further propose a correspondence learning that makes tracklets linking between clips end-to-end learnable. Compared to VisTR, EfficientVIS requires 15x fewer training epochs while achieving state-of-the-art accuracy on the YouTube-VIS benchmark. Meanwhile, our method enables whole video instance segmentation in a single end-to-end pass without data association at all.
-
Accelerated by telemedicine, advances in Remote Photoplethysmography (rPPG) are beginning to offer a viable path toward non-contact physiological measurement. Unfortunately, the datasets for rPPG are limited as they require videos of the human face paired with ground-truth, synchronized heart rate data from a medical-grade health monitor. Also troubling is that the datasets are not inclusive of diverse populations, i.e., current real rPPG facial video datasets are imbalanced in terms of races or skin tones, leading to accuracy disparities on different demographic groups. This paper proposes a scalable biophysical learning based method to generate physio-realistic synthetic rPPG videos given any reference image and target rPPG signal and shows that it could further improve the state-of-the-art physiological measurement and reduce the bias among different groups. We also collect the largest rPPG dataset of its kind (UCLA-rPPG) with a diverse presence of subject skin tones, in the hope that this could serve as a benchmark dataset for different skin tones in this area and ensure that advances of the technique can benefit all people for healthcare equity. The dataset is available at https://visual.ee.ucla.edu/rppg_avatars.htm/.
-
TransRAC: Encoding Multi-Scale Temporal Correlation With Transformers for Repetitive Action Counting
Counting repetitive actions are widely seen in human activities such as physical exercise. Existing methods focus on performing repetitive action counting in short videos, which is tough for dealing with longer videos in more realistic scenarios. In the data-driven era, the degradation of such generalization capability is mainly attributed to the lack of long video datasets. To complement this margin, we introduce a new large-scale repetitive action counting dataset covering a wide variety of video lengths, along with more realistic situations where action interruption or action inconsistencies occur in the video. Besides, we also provide a fine-grained annotation of the action cycles instead of just counting annotation along with a numerical value. Such a dataset contains 1,451 videos with about 20,000 annotations, which is more challenging. For repetitive action counting towards more realistic scenarios, we further propose encoding multi-scale temporal correlation with transformers that can take into account both performance and efficiency. Furthermore, with the help of fine-grained annotation of action cycles, we propose a density map regression-based method to predict the action period, which yields better performance with sufficient interpretability. Our proposed method outperforms state-of-the-art methods on all datasets and also achieves better performance on the unseen dataset without fine-tuning. The dataset and code are available.
-
Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e., recovering a realistic NeRF at a different time of day from a group of tourism images. Existing solutions adopt NeRF with a controllable appearance embedding to render novel views under various conditions, but they cannot render view-consistent images with an unseen appearance. To solve this problem, we present an end-to-end framework for constructing a hallucinated NeRF, dubbed as Ha-NeRF. Specifically, we propose an appearance hallucination module to handle time-varying appearances and transfer them to novel views. Considering the complex occlusions of tourism images, we introduce an anti-occlusion module to decompose the static subjects for visibility accurately. Experimental results on synthetic data and real tourism photo collections demonstrate that our method can hallucinate the desired appearances and render occlusion-free images from different views. The project and supplementary materials are available at https://rover-xingyu.github.io/Ha-NeRF/.
-
Undoubtedly, high-fidelity 3D hair plays an indispensable role in digital humans. However, existing monocular hair modeling methods are either tricky to deploy in digital systems (e.g., due to their dependence on complex user interactions or large databases) or can produce only a coarse geometry. In this paper, we introduce NeuralHDHair, a flexible, fully automatic system for modeling high-fidelity hair from a single image. The key enablers of our system are two carefully designed neural networks: an IRHairNet (Implicit representation for hair using neural network) for inferring high-fidelity 3D hair geometric features (3D orientation field and 3D occupancy field) hierarchically and a GrowingNet (Growing hair strands using neural network) to efficiently generate 3D hair strands in parallel. Specifically, we perform a coarse-to-fine manner and propose a novel voxel-aligned implicit function (VIFu) to represent the global hair feature, which is further enhanced by the local details extracted from a hair luminance map. To improve the efficiency of a traditional hair growth algorithm, we adopt a local neural implicit function to grow strands based on the estimated 3D hair geometric features. Extensive experiments show that our method is capable of constructing a high-fidelity 3D hair model from a single image, both efficiently and effectively, and achieves the-state-of-the-art performance.
-
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e.g., generalization across distributions) is valued. Existing literature discussing this "hard-to-learn" concept are mainly expanded either along the dimension of the samples or the dimension of the features. In this paper, we aim to introduce a simple view merging these two dimensions, leading to a new, simple yet effective, heuristic to train machine learning models by emphasizing the worst-cases on both the sample and the feature dimensions. We name our method W2D following the concept of "Worst-case along Two Dimensions". We validate the idea and demonstrate its empirical strength over standard benchmarks.
-
We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all objects. The core component is a global tracking transformer that operates on objects from all frames in the sequence. The transformer encodes object features from all frames, and uses trajectory queries to group them into trajectories. The trajectory queries are object features from a single frame and naturally produce unique trajectories. Our global tracking transformer does not require intermediate pairwise grouping or combinatorial association, and can be jointly trained with an object detector. It achieves competitive performance on the popular MOT17 benchmark, with 75.3 MOTA and 59.1 HOTA. More importantly, our framework seamlessly integrates into state-of-the-art large-vocabulary detectors to track any objects. Experiments on the challenging TAO dataset show that our framework consistently improves upon baselines that are based on pairwise association, outperforming published work by a significant 7.7 tracking mAP. Code is available at https://github.com/xingyizhou/GTR.
-
Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use an inductive bias that random augmentations (e.g., random crops) of an image should produce similar embeddings. We show that such methods are vulnerable to backdoor attacks -- where an attacker poisons a small part of the unlabeled data by adding a trigger (image patch chosen by the attacker) to the images. The model performance is good on clean test images, but the attacker can manipulate the decision of the model by showing the trigger at test time. Backdoor attacks have been studied extensively in supervised learning and to the best of our knowledge, we are the first to study them for self-supervised learning. Backdoor attacks are more practical in self-supervised learning, since the use of large unlabeled data makes data inspection to remove poisons prohibitive. We show that in our targeted attack, the attacker can produce many false positives for the target category by using the trigger at test time. We also propose a defense method based on knowledge distillation that succeeds in neutralizing the attack. Our code is available here: https://github.com/UMBCvision/SSL-Backdoor
-
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers could improve the performance, yet the inner-modal attentive weights may be diluted, which could thus greatly undermine the final performance. In this paper, we propose a multimodal token fusion method (TokenFusion), tailored for transformer-based vision tasks. To effectively fuse multiple modalities, TokenFusion dynamically detects uninformative tokens and substitute these tokens with projected and aggregated inter-modal features. Residual positional alignment is also adopted to enable explicit utilization of the inter-modal alignments after fusion. The design of TokenFusion allows the transformer to learn correlations among multimodal features, while the single-modal transformer architecture remains largely intact. Extensive experiments are conducted on a variety of homogeneous and heterogeneous modalities and demonstrate that TokenFusion surpasses state-of-the-art methods in three typical vision tasks: multimodal image-to-image translation, RGB-depth semantic segmentation, and 3D object detection with point cloud and images.
-
Various facial manipulation techniques have drawn serious public concerns in morality, security, and privacy. Although existing face forgery classifiers achieve promising performance on detecting fake images, these methods are vulnerable to adversarial examples with injected imperceptible perturbations on the pixels. Meanwhile, many face forgery detectors always utilize the frequency diversity between real and fake faces as a crucial clue. In this paper, instead of injecting adversarial perturbations into the spatial domain, we propose a frequency adversarial attack method against face forgery detectors. Concretely, we apply discrete cosine transform (DCT) on the input images and introduce a fusion module to capture the salient region of adversary in the frequency domain. Compared with existing adversarial attacks (e.g. FGSM, PGD) in the spatial domain, our method is more imperceptible to human observers and does not degrade the visual quality of the original images. Moreover, inspired by the idea of meta-learning, we also propose a hybrid adversarial attack that performs attacks in both the spatial and frequency domains. Extensive experiments indicate that the proposed method fools not only the spatial-based detectors but also the state-of-the-art frequency-based detectors effectively. In addition, the proposed frequency attack enhances the transferability across face forgery detectors as black-box attacks.
-
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements. To alleviate this, the state-of-the-art framework RAFT gradually improves its prediction quality by using a large number of iterative refinements, achieving remarkable performance but introducing linearly increasing inference time. To enable both high accuracy and efficiency, we completely revamp the dominant flow regression pipeline by reformulating optical flow as a global matching problem, which identifies the correspondences by directly comparing feature similarities. Specifically, we propose a GMFlow framework, which consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. We further introduce a refinement step that reuses GMFlow at higher feature resolution for residual flow prediction. Our new framework outperforms 31-refinements RAFT on the challenging Sintel benchmark, while using only one refinement and running faster, suggesting a new paradigm for accurate and efficient optical flow estimation. Code is available at https://github.com/haofeixu/gmflow.
-
Generating speech-consistent body and gesture movements is a long-standing problem in virtual avatar creation. Previous studies often synthesize pose movement in a holistic manner, where poses of all joints are generated simultaneously. Such a straightforward pipeline fails to generate fine-grained co-speech gestures. One observation is that the hierarchical semantics in speech and the hierarchical structures of human gestures can be naturally described into multiple granularities and associated together. To fully utilize the rich connections between speech audio and human gestures, we propose a novel framework named Hierarchical Audio-to-Gesture (HA2G) for co-speech gesture generation. In HA2G, a Hierarchical Audio Learner extracts audio representations across semantic granularities. A Hierarchical Pose Inferer subsequently renders the entire human pose gradually in a hierarchical manner. To enhance the quality of synthesized gestures, we develop a contrastive learning strategy based on audio-text alignment for better audio representations. Extensive experiments and human evaluation demonstrate that the proposed method renders realistic co-speech gestures and outperforms previous methods in a clear margin. Project page: https://alvinliu0.github.io/projects/HA2G.
-
State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a "foundation", that targets all modalities at once---a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision and language tasks. We introduce FLAVA as such a model and demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities.
-
Sign languages are visual languages, with vocabularies as rich as their spoken language counterparts. However, current deep-learning based Sign Language Production (SLP) models produce under-articulated skeleton pose sequences from constrained vocabularies and this limits applicability. To be understandable and accepted by the deaf, an automatic SLP system must be able to generate co-articulated photo-realistic signing sequences for large domains of discourse. In this work, we tackle large-scale SLP by learning to co-articulate between dictionary signs, a method capable of producing smooth signing while scaling to unconstrained domains of discourse. To learn sign co-articulation, we propose a novel Frame Selection Network (FS-Net) that improves the temporal alignment of interpolated dictionary signs to continuous signing sequences. Additionally, we propose SignGAN, a pose-conditioned human synthesis model that produces photo-realistic sign language videos direct from skeleton pose. We propose a novel keypoint-based loss function which improves the quality of synthesized hand images. We evaluate our SLP model on the large-scale meineDGS (mDGS) corpus, conducting extensive user evaluation showing our FS-Net approach improves co-articulation of interpolated dictionary signs. Additionally, we show that SignGAN significantly outperforms all baseline methods for quantitative metrics, human perceptual studies and native deaf signer comprehension.
-
We endeavor on a rarely explored task named Insubstan-tial Object Detection (IOD), which aims to localize the object with following characteristics: (1) amorphous shape with indistinct boundary; (2) similarity to surroundings; (3) absence in color. Accordingly, it is far more challenging to distinguish insubstantial objects in a single static frame and the collaborative representation of spatial and tempo-ral information is crucial. Thus, we construct an IOD-Video dataset comprised of 600 videos (141,017 frames) covering various distances, sizes, visibility, and scenes captured by different spectral ranges. In addition, we develop a spatio-temporal aggregation framework for IOD, in which differ-ent backbones are deployed and a spatio-temporal aggregation loss (STAloss) is elaborately designed to leverage the consistency along the time axis. Experiments conducted on IOD-Video dataset demonstrate that spatio-temporal aggregation can significantly improve the performance of IOD. We hope our work will attract further researches into this valuable yet challenging task. The code will be available at: https://github.com/CalayZhou/IOD-Video.
-
Videos incorporate rich semantics as well as redundant information. Seeking a compact yet effective video representation, e.g., sample informative frames from the entire video, is critical to efficient video recognition. There have been works that formulate frame sampling as a sequential decision task by selecting frames one by one according to their importance. In this paper, we present a more efficient framework named OCSampler, which explores such a representation with one short clip. OCSampler designs a new paradigm of learning instance-specific video condensation policies to select frames only in a single step. Rather than picking up frames sequentially like previous methods, we simply process a whole sequence at once. Accordingly, these policies are derived from a light-weighted skim network together with a simple yet effective policy network. Moreover, we extend the proposed method with a frame number budget, enabling the framework to produce correct predictions in high confidence with as few frames as possible. Experiments on various benchmarks demonstrate the effectiveness of OCSampler over previous methods in terms of accuracy and efficiency. Specifically, it achieves 76.9% mAP and 21.7 GFLOPs on ActivityNet with an impressive throughput: 123.9 Video/s on a single TITAN Xp GPU.
-
Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. Despite their performance, they still suffer from interference across tasks which leads to catastrophic forgetting. To ameliorate this problem, we propose to only activate and select sparse neurons for learning current and past tasks at any stage. More parameters space and model capacity can thus be reserved for the future tasks. This minimizes the interference between parameters for different tasks. To do so, we propose a Sparse neural Network for Continual Learning (SNCL), which employs variational Bayesian sparsity priors on the activations of the neurons in all layers. Full Experience Replay (FER) provides effective supervision in learning the sparse activations of the neurons in different layers. A loss-aware reservoir-sampling strategy is developed to maintain the memory buffer. The proposed method is agnostic as to the network structures and the task boundaries. Experiments on different datasets show that SNCL achieves state-of-the-art result for mitigating forgetting.
-
Graph-Based Spatial Transformer With Memory Replay for Multi-Future Pedestrian Trajectory Prediction
Pedestrian trajectory prediction is an essential and challenging task for a variety of real-life applications such as autonomous driving and robotic motion planning. Besides generating a single future path, predicting multiple plausible future paths is becoming popular in some recent work on trajectory prediction. However, existing methods typically emphasize spatial interactions between pedestrians and surrounding areas but ignore the smoothness and temporal consistency of predictions. Our model aims to forecast multiple paths based on a historical trajectory by modeling multi-scale graph-based spatial transformers combined with a trajectory smoothing algorithm named "Memory Replay" utilizing a memory graph. Our method can comprehensively exploit the spatial information as well as correct the temporally inconsistent trajectories (e.g., sharp turns). We also propose a new evaluation metric named "Percentage of Trajectory Usage" to evaluate the comprehensiveness of diverse multi-future predictions. Our extensive experiments show that the proposed model achieves state-of-the-art performance on multi-future prediction and competitive results for single-future prediction. Code released at https://github.com/Jacobieee/ST-MR.
-
Cameras on portable devices are manufactured with a rolling-shutter (RS) mechanism, where the image rows (aka. scanlines) are read out sequentially. The unknown camera motions during the imaging process cause the so-called RS effects which are solved by motion assumptions in the literature. In this work, we give a solution to the absolute pose problem free of motion assumptions. We categorically demonstrate that the only requirement is motion smoothness instead of stronger constraints on the camera motion. To this end, we propose a novel mathematical abstraction for RS cameras observing a planar scene, called the scanline-homography, a 3x2 matrix with 5 DOFs. We establish the relationship between a scanline-homography and the corresponding plane-homography, a 3x3 matrix with 6 DOFs assuming the camera is calibrated. We estimate the scanline-homographies of an RS frame using a smooth image warp powered by B-Splines, and recover the plane-homographies afterwards to obtain the scanline-poses based on motion smoothness. We back our claims with various experiments. Code and new datasets: https://bitbucket.org/clermontferrand/planarscanlinehomography/src/master/.
-
Tables organize valuable content in a concise and compact representation. This content is extremely valuable for systems such as search engines, Knowledge Graph's, etc, since they enhance their predictive capabilities. Unfortunately, tables come in a large variety of shapes and sizes. Furthermore, they can have complex column/row-header configurations, multiline rows, different variety of separation lines, missing entries, etc. As such, the correct identification of the table-structure from an image is a non-trivial task. In this paper, we present a new table-structure identification model. The latter improves the latest end-to-end deep learning model (i.e. encoder-dual-decoder from PubTabNet) in two significant ways. First, we introduce a new object detection decoder for table-cells. In this way, we can obtain the content of the table-cells from programmatic PDF's directly from the PDF source and avoid the training of the custom OCR decoders. This architectural change leads to more accurate table-content extraction and allows us to tackle non-english tables. Second, we replace the LSTM decoders with transformer based decoders. This upgrade improves significantly the previous state-of-the-art tree-editing-distance-score (TEDS) from 91% to 98.5% on simple tables and from 88.7% to 95% on complex tables.
-
Synthesis of ergodic, stationary visual patterns is widely applicable in texturing, shape modeling, and digital content creation. The wide applicability of this technique thus requires the pattern synthesis approaches to be scalable, diverse, and authentic. In this paper, we propose an exemplar-based visual pattern synthesis framework that aims to model the inner statistics of visual patterns and generate new, versatile patterns that meet the aforementioned requirements. To this end, we propose an implicit network based on generative adversarial network (GAN) and periodic encoding, thus calling our network the Implicit Periodic Field Network (IPFN). The design of IPFN ensures scalability: the implicit formulation directly maps the input coordinates to features, which enables synthesis of arbitrary size and is computationally efficient for 3D shape synthesis. Learning with a periodic encoding scheme encourages diversity: the network is constrained to model the inner statistics of the exemplar based on spatial latent codes in a periodic field. Coupled with continuously designed GAN training procedures, IPFN is shown to synthesize tileable patterns with smooth transitions and local variations. Last but not least, thanks to both the adversarial training technique and the encoded Fourier features, IPFN learns high-frequency functions that produce authentic, high-quality results. To validate our approach, we present novel experimental results on various applications in 2D texture synthesis and 3D shape synthesis.
-
This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representations semantic-rich. In our experiments, we pre-train GLIP on 27M grounding data, including 3M human-annotated and 24M web-crawled image-text pairs. The learned representations demonstrate strong zero-shot and few-shot transferability to various object-level recognition tasks. 1) When directly evaluated on COCO and LVIS (without seeing any images in COCO during pre-training), GLIP achieves 49.8 AP and 26.9 AP, respectively, surpassing many supervised baselines. 2) After fine-tuned on COCO, GLIP achieves 60.8 AP on val and 61.5 AP on test-dev, surpassing prior SoTA. 3) When transferred to 13 downstream object detection tasks, a 1-shot GLIP rivals with a fully-supervised Dynamic Head.
-
Though unsupervised domain adaptation (UDA) has achieved very impressive progress recently, it remains a great challenge due to missing target annotations and the rich discrepancy between source and target distributions. We propose Spectral UDA (SUDA), an effective and efficient UDA technique that works in the spectral space and can generalize across different visual recognition tasks. SUDA addresses the UDA challenges from two perspectives. First, it introduces a spectrum transformer (ST) that mitigates inter-domain discrepancies by enhancing domain-invariant spectra while suppressing domain-variant spectra of source and target samples simultaneously. Second, it introduces multi-view spectral learning that learns useful unsupervised representations by maximizing mutual information among multiple ST-generated spectral views of each target sample. Extensive experiments show that SUDA achieves superior accuracy consistently across different visual tasks in image classification, semantic segmentation, and object detection. Additionally, SUDA also works with the transformer-based network and achieves state-of-the-art performance on object detection.
-
The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time image enhancement tasks, which models a non-linear 3D color transform by sparsely sampling it into a discretized 3D lattice. Previous works have made efforts to learn image-adaptive output color values of LUTs for flexible enhancement but neglect the importance of sampling strategy. They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform. Focusing on this problem, we present AdaInt (Adaptive Intervals Learning), a novel mechanism to achieve a more flexible sampling point allocation by adaptively learning the non-uniform sampling intervals in the 3D color space. In this way, a 3D LUT can increase its capability by conducting dense sampling in color ranges requiring highly non-linear transforms and sparse sampling for near-linear transforms. The proposed AdaInt could be implemented as a compact and efficient plug-and-play module for a 3D LUT-based method. To enable the end-to-end learning of AdaInt, we design a novel differentiable operator called AiLUT-Transform (Adaptive Interval LUT Transform) to locate input colors in the non-uniform 3D LUT and provide gradients to the sampling intervals. Experiments demonstrate that methods equipped with AdaInt can achieve state-of-the-art performance on two public benchmark datasets with a negligible overhead increase. Our source code is available at https://github.com/ImCharlesY/AdaInt.
-
The point cloud learning community is witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are computationally expensive since they need to generate a large attention map, which has quadratic complexity (both in space and time) with respect to input size. To solve this shortcoming, we introduce patch-attention (PAT) to adaptively learn a much smaller set of bases upon which the attention maps are computed. By a weighted summation upon these bases, PAT not only captures the global shape context but also achieves linear complexity to input size. In addition, we propose a lightweight Multi-Scale Attention (MST) block to build attentions among features of different scales, providing the model with multi-scale features. Equipped with the PAT and MST, we construct our neural architecture called PatchFormer that integrates both modules into a joint framework for point cloud learning. Extensive experiments demonstrate that our network achieves comparable accuracy on general point cloud learning tasks with 9.2x speed-up than previous point Transformers.
-
Although detection with Transformer (DETR) is increasingly popular, its global attention modeling requires an extremely long training period to optimize and achieve promising detection performance. Alternative to existing studies that mainly develop advanced feature or embedding designs to tackle the training issue, we point out that the Region-of-Interest (RoI) based detection refinement can easily help mitigate the difficulty of training for DETR methods. Based on this, we introduce a novel REcurrent Glimpse-based decOder (REGO) in this paper. In particular, the REGO employs a multi-stage recurrent processing structure to help the attention of DETR gradually focus on foreground objects more accurately. In each processing stage, visual features are extracted as glimpse features from RoIs with enlarged bounding box areas of detection results from the previous stage. Then, a glimpse-based decoder is introduced to provide refined detection results based on both the glimpse features and the attention modeling outputs of the previous stage. In practice, REGO can be easily embedded in representative DETR variants while maintaining their fully end-to-end training and inference pipelines. In particular, REGO helps Deformable DETR achieve 44.8 AP on the MSCOCO dataset with only 36 training epochs, compared with the first DETR and the Deformable DETR that require 500 and 50 epochs to achieve comparable performance, respectively. Experiments also show that REGO consistently boosts the performance of different DETR detectors by up to 7% relative gain at the same setting of 50 training epochs. Code is available via https://github.com/zhechen/Deformable-DETR-REGO.
-
We introduce AiD Regen, a novel system that generates 3D wound models combining 2D semantic segmentation with 3D reconstruction so that they can be printed via 3D bio-printers during the surgery to treat diabetic foot ulcers (DFUs). AiD Regen seamlessly binds the full pipeline, which includes RGB-D image capturing, semantic segmentation, boundary-guided point-cloud processing, 3D model reconstruction, and 3D printable G-code generation, into a single system that can be used out of the box. We developed a multi-stage data preprocessing method to handle small and unbalanced DFU image datasets. AiD Regen's human-in-the-loop machine learning interface enables clinicians to not only create 3D regenerative patches with just a few touch interactions but also customize and confirm wound boundaries. As evidenced by our experiments, our model outperforms prior wound segmentation models and our reconstruction algorithm is capable of generating 3D wound models with compelling accuracy. We further conducted a case study on a real DFU patient and demonstrated the effectiveness of AiD Regen in treating DFU wounds.
-
This paper presents SimMIM, a simple framework for masked image modeling. We have simplified recently proposed relevant approaches, without the need for special designs, such as block-wise masking and tokenization via discrete VAE or clustering. To investigate what makes a masked image modeling task learn good representations, we systematically study the major components in our framework, and find that the simple designs of each component have revealed very strong representation learning performance: 1) random masking of the input image with a moderately large masked patch size (e.g., 32) makes a powerful pre-text task; 2) predicting RGB values of raw pixels by direct regression performs no worse than the patch classification approaches with complex designs; 3) the prediction head can be as light as a linear layer, with no worse performance than heavier ones. Using ViT-B, our approach achieves 83.8% top-1 fine-tuning accuracy on ImageNet-1K by pre-training also on this dataset, surpassing previous best approach by +0.6%. When applied to a larger model with about 650 million parameters, SwinV2-H, it achieves 87.1% top-1 accuracy on ImageNet-1K using only ImageNet-1K data. We also leverage this approach to address the data-hungry issue faced by large-scale model training, that a 3B model (SwinV2-G) is successfully trained to achieve state-of-the-art accuracy on four representative vision benchmarks using 40x less labeled data than that in previous practice (JFT-3B). The code is available at https://github.com/microsoft/SimMIM.
-
A well-known challenge in applying deep-learning methods to omnidirectional images is spherical distortion. In dense regression tasks such as depth estimation, where structural details are required, using a vanilla CNN layer on the distorted 360 image results in undesired information loss. In this paper, we propose a 360 monocular depth estimation pipeline, OmniFusion, to tackle the spherical distortion issue. Our pipeline transforms a 360 image into less-distorted perspective patches (i.e. tangent images) to obtain patch-wise predictions via CNN, and then merge the patch-wise results for final output. To handle the discrepancy between patch-wise predictions which is a major issue affecting the merging quality, we propose a new framework with the following key components. First, we propose a geometry-aware feature fusion mechanism that combines 3D geometric features with 2D image features to compensate for the patch-wise discrepancy. Second, we employ the self-attention-based transformer architecture to conduct a global aggregation of patch-wise information, which further improves the consistency. Last, we introduce an iterative depth refinement mechanism, to further refine the estimated depth based on the more accurate geometric features. Experiments show that our method greatly mitigates the distortion issue, and achieves state-of-the-art performances on several 360 monocular depth estimation benchmark datasets.
-
Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to severe confirmation bias during self-training. In this paper, we delve into this problem and propose a simple yet effective LabelMatch framework from two different yet complementary perspectives, i.e., distribution-level and instance-level. For the former one, it is reasonable to approximate the class distribution of the unlabeled data from that of the labeled data according to Monte Carlo Sampling. Guided by this weakly supervision cue, we introduce a re-distribution mean teacher, which leverages adaptive label-distribution-aware confidence thresholds to generate unbiased pseudo labels to drive student learning. For the latter one, there exists an overlooked label assignment ambiguity problem across teacher-student models. To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly. Experiments on both MS-COCO and PASCAL-VOC datasets demonstrate the considerable superiority of our proposed framework to other state-of-the-arts. Code will be available at https://github.com/HIK-LAB/SSOD.
-
Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to unsatisfactory performance due to a major domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans. To mitigate this issue, we propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visual representations, thus enabling fine-grained alignment between image regions and textual concepts. Our method leverages a CLIP model to match image regions with template captions, and then pretrains our model to align these region-text pairs in the feature space. When transferring our pretrained model to the open-vocabulary object detection task, our method outperforms the state of the art by 3.8 AP50 and 2.2 AP for novel categories on COCO and LVIS datasets, respectively. Further, the learned region representations support zero-shot inference for object detection, showing promising results on both COCO and LVIS datasets. Our code is available at https://github.com/microsoft/RegionCLIP.
-
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we propose a Transformer-based video interpolation framework that allows content-aware aggregation weights and considers long-range dependencies with the self-attention operations. To avoid the high computational cost of global self-attention, we introduce the concept of local attention into video interpolation and extend it to the spatial-temporal domain. Furthermore, we propose a space-time separation strategy to save memory usage, which also improves performance. In addition, we develop a multi-scale frame synthesis scheme to fully realize the potential of Transformers. Extensive experiments demonstrate the proposed model performs favorably against the state-of-the-art methods both quantitatively and qualitatively on a variety of benchmark datasets. The code and models are released at https://github.com/zhshi0816/ Video-Frame-Interpolation-Transformer.
-
We address weakly supervised point cloud segmentation by proposing a new model, MIL-derived transformer, to mine additional supervisory signals. First, the transformer model is derived based on multiple instance learning (MIL) to explore pair-wise cloud-level supervision, where two clouds of the same category yield a positive bag while two of different classes produce a negative bag. It leverages not only individual cloud annotations but also pair-wise cloud semantics for model optimization. Second, Adaptive global weighted pooling (AdaGWP) is integrated into our transformer model to replace max pooling and average pooling. It introduces learnable weights to re-scale logits in the class activation maps. It is more robust to noise while discovering more complete foreground points under weak supervision. Third, we perform point subsampling and enforce feature equivariance between the original and subsampled point clouds for regularization. The proposed method is end-to-end trainable and is general because it can work with different backbones with diverse types of weak supervision signals, including sparsely annotated points and cloud-level labels. The experiments show that it achieves state-of-the-art performance on the S3DIS and ScanNet benchmarks.
-
We introduce the first end-to-end learning-based solution to near-field Photometric Stereo (PS), where the light sources are close to the object of interest. This setup is especially useful for reconstructing large immobile objects. Our method is fast, producing a mesh from 52 512x384 resolution images in about 1 second on a commodity GPU, thus potentially unlocking several AR/VR applications. Existing approaches rely on optimization coupled with a far-field PS network operating on pixels or small patches. Using optimization makes these approaches slow and memory intensive (requiring 17GB GPU and 27GB of CPU memory) while using only pixels or patches makes them highly susceptible to noise and calibration errors. To address these issues, we develop a recursive multi-resolution scheme to estimate surface normal and depth maps of the whole image at each step. The predicted depth map at each scale is then used to estimate 'per-pixel lighting' for the next scale. This design makes our approach almost 45x faster and 2 degrees more accurate (11.3 vs. 13.3 degrees Mean Angular Error) than the state-of-the-art near-field PS reconstruction technique, which uses iterative optimization.
-
Template-based 3D object tracking still lacks a high-precision benchmark of real scenes due to the difficulty of annotating the accurate 3D poses of real moving video objects without using markers. In this paper, we present a multi-view approach to estimate the accurate 3D poses of real moving objects, and then use binocular data to construct a new benchmark for monocular textureless 3D object tracking. The proposed method requires no markers, and the cameras only need to be synchronous, relatively fixed as cross-view and calibrated. Based on our object-centered model, we jointly optimize the object pose by minimizing shape re-projection constraints in all views, which greatly improves the accuracy compared with the single-view approach, and is even more accurate than the depth-based method. Our new benchmark dataset contains 20 textureless objects, 22 scenes, 404 video sequences and 126K images captured in real scenes. The annotation error is guaranteed to be less than 2mm, according to both theoretical analysis and validation experiments. We re-evaluate the state-of-the-art 3D object tracking methods with our dataset, reporting their performance ranking in real scenes. Our BCOT benchmark and code can be found at https://ar3dv.github.io/BCOT-Benchmark/.
-
We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for object detection. This is enabled by a unified architecture, Omni-DETR, based on the recent progress on student-teacher framework and end-to-end transformer based object detection. Under this unified architecture, different types of weak labels can be leveraged to generate accurate pseudo labels, by a bipartite matching based filtering mechanism, for the model to learn. In the experiments, Omni-DETR has achieved state-of-the-art results on multiple datasets and settings. And we have found that weak annotations can help to improve detection performance and a mixture of them can achieve a better trade-off between annotation cost and accuracy than the standard complete annotation. These findings could encourage larger object detection datasets with mixture annotations. The code is available at https://github.com/amazon-research/omni-detr.
-
Omnidirectional cameras have been used widely to better understand surrounding environments. They are often configured as stereo to estimate depth. However, due to the optics of the fisheye lens, conventional epipolar geometry is inapplicable directly to omnidirectional camera images. Intermediate formats of omnidirectional images, such as equirectangular images, have been used. However, stereo matching performance on these image formats has been lower than the conventional stereo due to severe image distortion near pole regions. In this paper, to address the distortion problem of omnidirectional images, we devise a novel subdivision scheme of a spherical geodesic grid. This enables more isotropic patch sampling of spherical image information in the omnidirectional camera space. Our spherical geodesic grid is tessellated with an equal-arc subdivision, making the cell sizes and in-between distances as uniform as possible, i.e., the arc length of the spherical grid cell's edges is well regularized. Also, our uniformly tessellated coordinates in a 2D image can be transformed into spherical coordinates via one-to-one mapping, allowing for analytical forward/backward transformation. Our uniform tessellation scheme achieves a higher accuracy of stereo matching than the traditional cylindrical and cubemap-based approaches, reducing the memory footage required for stereo matching by 20 %.
-
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve new state of the art scores for image inpainting and class-conditional image synthesis and highly competitive performance on various tasks, including unconditional image generation, text-to-image synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.
-
Few-Shot Image Classification (FSIC) aims to recognize novel image classes with limited data, which is significant in practice. In this paper, we consider the FSIC problem in the case of adversarial examples. This is an extremely challenging issue because current deep learning methods are still vulnerable when handling adversarial examples, even with massive labeled training samples. For this problem, existing works focus on training a network in the meta-learning fashion that depends on numerous sampled few-shot tasks. In comparison, we propose a simple but effective baseline through directly learning generalizable representations without tedious task sampling, which is robust to unforeseen adversarial FSIC tasks. Specifically, we introduce an adversarial-aware mechanism to establish auxiliary supervision via feature-level differences between legitimate and adversarial examples. Furthermore, we design a novel adversarial-reweighted training manner to alleviate the imbalance among adversarial examples. The feature purifier is also employed as post-processing for adversarial features. Moreover, our method can obtain generalizable representations to remain superior transferability, even facing cross-domain adversarial examples. Extensive experiments show that our method can significantly outperform state-of-the-art adversarially robust FSIC methods on two standard benchmarks.
-
Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus on the most discriminative parts of an object (i.e., incomplete localization problem). In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background. To address it, we propose Class RE-Activation Mapping (CREAM), a novel clustering-based approach to boost the activation values of the integral object regions. To this end, we introduce class-specific foreground and background context embeddings as cluster centroids. A CAM-guided momentum preservation strategy is developed to learn the context embeddings during training. At the inference stage, the re-activation mapping is formulated as a parameter estimation problem under Gaussian Mixture Model, which can be solved by deriving an unsupervised Expectation-Maximization based soft-clustering algorithm. By simply integrating CREAM into various WSOL approaches, our method significantly improves their performance. CREAM achieves the state-of-the-art performance on CUB, ILSVRC and OpenImages benchmark datasets. Code is available at https://github.com/JLRepo/CREAM.
-
We address the problem of action segmentation in instructional task videos with a small number of weakly-labeled training videos and a large number of unlabeled videos, which we refer to as Semi-Weakly-Supervised Learning (SWSL) of actions. We propose a general SWSL framework that can efficiently learn from both types of videos and can leverage any of the existing weakly-supervised action segmentation methods. Our key observation is that the distance between the transcript of an unlabeled video and those of the weakly-labeled videos from the same task is small yet often nonzero. Therefore, we develop a Soft Restricted Edit (SRE) loss to encourage small variations between the predicted transcripts of unlabeled videos and ground-truth transcripts of the weakly-labeled videos of the same task. To compute the SRE loss, we develop a flexible transcript prediction (FTP) method that uses the output of the action classifier to find both the length of the transcript and the sequence of actions occurring in an unlabeled video. We propose an efficient learning scheme in which we alternate between minimizing our proposed loss and generating pseudo-transcripts for unlabeled videos. By experiments on two benchmark datasets, we demonstrate that our approach can significantly improve the performance by using unlabeled videos, especially when the number of weakly-labeled videos is small.
-
Federated learning frameworks typically require collaborators to share their local gradient updates of a common model instead of sharing training data to preserve privacy. However, prior works on Gradient Leakage Attacks showed that private training data can be revealed from gradients. So far almost all relevant works base their attacks on fully-connected or convolutional neural networks. Given the recent overwhelmingly rising trend of adapting Transformers to solve multifarious vision tasks, it is highly important to investigate the privacy risk of vision transformers. In this paper, we analyse the gradient leakage risk of self-attention based mechanism in both theoretical and practical manners. Particularly, we propose APRIL - Attention PRIvacy Leakage, which poses a strong threat to self-attention inspired models such as ViT. Showing how vision Transformers are at the risk of privacy leakage via gradients, we urge the significance of designing privacy-safer Transformer models and defending schemes.
-
In this paper, we present TExt Spotting TRansformers (TESTR), a generic end-to-end text spotting framework using Transformers for text detection and recognition in the wild. TESTR builds upon a single encoder and dual decoders for the joint text-box control point regression and character recognition. Other than most existing literature, our method is free from Region-of-Interest operations and heuristics-driven post-processing procedures; TESTR is particularly effective when dealing with curved text-boxes where special cares are needed for the adaptation of the traditional bounding-box representations. We show our canonical representation of control points suitable for text instances in both Bezier curve and polygon annotations. In addition, we design a bounding-box guided polygon detection (box-to-polygon) process. Experiments on curved and arbitrarily shaped datasets demonstrate state-of-the-art performances of the proposed TESTR algorithm.
-
Though neural radiance fields ("NeRF") have demonstrated impressive view synthesis results on objects and small bounded regions of space, they struggle on "unbounded" scenes, where the camera may point in any direction and content may exist at any distance. In this setting, existing NeRF-like models often produce blurry or low-resolution renderings (due to the unbalanced detail and scale of nearby and distant objects), are slow to train, and may exhibit artifacts due to the inherent ambiguity of the task of reconstructing a large scene from a small set of images. We present an extension of mip-NeRF (a NeRF variant that addresses sampling and aliasing) that uses a non-linear scene parameterization, online distillation, and a novel distortion-based regularizer to overcome the challenges presented by unbounded scenes. Our model, which we dub "mip-NeRF 360" as we target scenes in which the camera rotates 360 degrees around a point, reduces mean-squared error by 57% compared to mip-NeRF, and is able to produce realistic synthesized views and detailed depth maps for highly intricate, unbounded real-world scenes.
-
Designing better machine translation systems by considering auxiliary inputs such as images has attracted much attention in recent years. While existing methods show promising performance over the conventional text-only translation systems, they typically require paired text and image as input during inference, which limits their applicability to real-world scenarios. In this paper, we introduce a visual hallucination framework, called VALHALLA, which requires only source sentences at inference time and instead uses hallucinated visual representations for multimodal machine translation. In particular, given a source sentence an autoregressive hallucination transformer is used to predict a discrete visual representation from the input text, and the combined text and hallucinated representations are utilized to obtain the target translation. We train the hallucination transformer jointly with the translation transformer using standard backpropagation with cross-entropy losses while being guided by an additional loss that encourages consistency between predictions using either ground-truth or hallucinated visual representations. Extensive experiments on three standard translation datasets with a diverse set of language pairs demonstrate the effectiveness of our approach over both text-only baselines and state-of-the-art methods. Our codes and models will be publicly available. Project page: http://www.svcl.ucsd.edu/projects/valhalla.
-
We introduce a high resolution, 3D-consistent image and shape generation technique which we call StyleSDF. Our method is trained on single view RGB data only, and stands on the shoulders of StyleGAN2 for image generation, while solving two main challenges in 3D-aware GANs: 1) high-resolution, view-consistent generation of the RGB images, and 2) detailed 3D shape. We achieve this by merging an SDF-based 3D representation with a style-based 2D generator. Our 3D implicit network renders low-resolution feature maps, from which the style-based network generates view-consistent, 1024x1024 images. Notably, our SDF-based 3D modeling defines detailed 3D surfaces, leading to consistent volume rendering. Our method shows higher quality results compared to state of the art in terms of visual and geometric quality.
-
Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency between labeled and unlabeled data, outliers may occur in unlabeled data, further increasing the training difficulty. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers. Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i.e., outliers) from unlabeled data. Semi-supervised learning (SSL) is further deployed to exploit positive unlabeled data by dynamically generating pseudo-MOS. We adopt a dual-branch network including reference and distortion branches. Furthermore, spatial attention is introduced in the reference branch to concentrate more on the informative regions, and sliced Wasserstein distance is used for robust difference map computation to address the misalignment issues caused by images recovered by GAN models. Extensive experiments show that our method performs favorably against state-of-the-arts on the benchmark datasets PIPAL, KADID-10k, TID2013, LIVE and CSIQ.
-
We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions and tracks human bodies even when they go outside the camera's field of view. To achieve this, we first propose a deep generative motion infiller, which autoregressively infills the body motions of occluded humans based on visible motions. Additionally, in contrast to prior work, our approach reconstructs human meshes in consistent global coordinates even with dynamic cameras. Since the joint reconstruction of human motions and camera poses is underconstrained, we propose a global trajectory predictor that generates global human trajectories based on local body movements. Using the predicted trajectories as anchors, we present a global optimization framework that refines the predicted trajectories and optimizes the camera poses to match the video evidence such as 2D keypoints. Experiments on challenging indoor and in-the-wild datasets with dynamic cameras demonstrate that the proposed approach outperforms prior methods significantly in terms of motion infilling and global mesh recovery.
-
To interpret deep networks, one main approach is to associate neurons with human-understandable concepts. However, existing methods often ignore the inherent connections of different concepts (e.g., dog and cat both belong to animals), and thus lose the chance to explain neurons responsible for higher-level concepts (e.g., animal). In this paper, we study hierarchical concepts inspired by the hierarchical cognition process of human beings. To this end, we propose HIerarchical Neuron concepT explainer (HINT) to effectively build bidirectional associations between neurons and hierarchical concepts in a low-cost and scalable manner. HINT enables us to systematically and quantitatively study whether and how the implicit hierarchical relationships of concepts are embedded into neurons. Specifically, HINT identifies collaborative neurons responsible for one concept and multimodal neurons pertinent to different concepts, at different semantic levels from concrete concepts (e.g., dog) to more abstract ones (e.g., animal). Finally, we verify the faithfulness of the associations using Weakly Supervised Object Localization, and demonstrate its applicability in various tasks, such as discovering saliency regions and explaining adversarial attacks. Code is available on https://github.com/AntonotnaWang/HINT.
-
Inferring human-scene contact (HSC) is the first step toward understanding how humans interact with their surroundings. While detecting 2D human-object interaction (HOI) and reconstructing 3D human pose and shape (HPS) have enjoyed significant progress, reasoning about 3D human-scene contact from a single image is still challenging. Existing HSC detection methods consider only a few types of predefined contact, often reduce body and scene to a small number of primitives, and even overlook image evidence. To predict human-scene contact from a single image, we address the limitations above from both data and algorithmic perspectives. We capture a new dataset called RICH for "Real scenes, Interaction, Contact and Humans." RICH contains multiview outdoor/indoor video sequences at 4K resolution, ground-truth 3D human bodies captured using markerless motion capture, 3D body scans, and high resolution 3D scene scans. A key feature of RICH is that it also contains accurate vertex-level contact labels on the body. Using RICH, we train a network that predicts dense body-scene contacts from a single RGB image. Our key insight is that regions in contact are always occluded so the network needs the ability to explore the whole image for evidence. We use a transformer to learn such non-local relationships and propose a new Body-Scene contact TRansfOrmer (BSTRO). Very few methods explore 3D contact; those that do focus on the feet only, detect foot contact as a post-processing step, or infer contact from body pose without looking at the scene. To our knowledge, BSTRO is the first method to directly estimate 3D body-scene contact from a single image. We demonstrate that BSTRO significantly outperforms the prior art. The code and dataset will be available for research purposes.
-
We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that high-resolution videos and diversified semantics can significantly improve cross-modality learning. In this paper, we propose a novel High-resolution and Diversified VIdeo-LAnguage pre-training model (HD-VILA) for many visual tasks. In particular, we collect a large dataset with two distinct properties: 1) the first high-resolution dataset including 371.5k hours of 720p videos, and 2) the most diversified dataset covering 15 popular YouTube categories. To enable VL pre-training, we jointly optimize the HD-VILA model by a hybrid Transformer that learns rich spatiotemporal features, and a multimodal Transformer that enforces interactions of the learned video features with diversified texts. Our pre-training model achieves new state-of-the-art results in 10 VL understanding tasks and 2 more novel text-to-visual generation tasks. For example, we outperform SOTA models with relative increases of 40.4% R@1 in zero-shot MSR-VTT text-to-video retrieval task, and 55.4% in high-resolution dataset LSMDC. The learned VL embedding is also effective in generating visually pleasing and semantically relevant results in text-to-visual editing and super-resolution tasks.
-
This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Aiming at generating an image of high visual quality, previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. These approaches neglect that modality differences implying the complementary information are extremely important for both fusion and subsequent detection task. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to a target-aware Dual Adversarial Learning (TarDAL) network for fusion and a commonly used detection network. The fusion network with one generator and dual discriminators seeks commons while learning from differences, which preserves structural information of targets from the infrared and textural details from the visible. Furthermore, we build a synchronized imaging system with calibrated infrared and optical sensors, and collect currently the most comprehensive benchmark covering a wide range of scenarios. Extensive experiments on several public datasets and our benchmark demonstrate that our method outputs not only visually appealing fusion but also higher detection mAP than the state-of-the-art approaches.
-
Generalized zero-shot learning (GZSL) requires a classifier trained on seen classes that can recognize objects from both seen and unseen classes. Due to the absence of unseen training samples, the classifier tends to bias towards seen classes. To mitigate this problem, feature generation based models are proposed to synthesize visual features for unseen classes. However, these features are generated in the visual feature space which lacks of discriminative ability. Therefore, some methods turn to find a better embedding space for the classifier training. They emphasize the inter-class relationships of seen classes, leading the embedding space overfitted to seen classes and unfriendly to unseen classes. Instead, in this paper, we propose an Intra-Class Compactness Enhancement method (ICCE) for GZSL. Our ICCE promotes intra-class compactness with inter-class separability on both seen and unseen classes in the embedding space and visual feature space. By promoting the intra-class relationships but the inter-class structures, we can distinguish different classes with better generalization. Specifically, we propose a Self-Distillation Embedding (SDE) module and a Semantic-Visual Contrastive Generation (SVCG) module. The former promotes intra-class compactness in the embedding space, while the latter accomplishes it in the visual feature space. The experiments demonstrate that our ICCE outperforms the state-of-the-art methods on four datasets and achieves competitive results on the remaining dataset.
-
In computer-aided design (CAD) systems, 2D line drawings are commonly used to illustrate 3D object designs. To reconstruct the 3D models depicted by a single 2D line drawing, an important key is finding the edge loops in the line drawing which correspond to the actual faces of the 3D object. In this paper, we approach the classical problem of face identification from a novel data-driven point of view. We cast it as a sequence generation problem: starting from an arbitrary edge, we adopt a variant of the popular Transformer model to predict the edges associated with the same face in a natural order. This allows us to avoid searching the space of all possible edge loops with various hand-crafted rules and heuristics as most existing methods do, deal with challenging cases such as curved surfaces and nested edge loops, and leverage additional cues such as face types. We further discuss how possibly imperfect predictions can be used for 3D object reconstruction. The project page is at https://manycore-research.github.io/faceformer.
-
Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in the high-frequency region, giving equal consideration to the low and high-frequency areas. In this paper, we propose a new lossless image compression method that proceeds the encoding in a coarse-to-fine manner to separate and process low and high-frequency regions differently. We initially compress the low-frequency components and then use them as additional input for encoding the remaining high-frequency region. The low-frequency components act as a strong prior in this case, which leads to improved estimation in the high-frequency area. In addition, we design the frequency decomposition process to be adaptive to color channel, spatial location, and image characteristics. As a result, our method derives an image-specific optimal ratio of low/high-frequency components. Experiments show that the proposed method achieves state-of-the-art performance for benchmark high-resolution datasets.
-
The nonuniform quantization strategy for compressing neural networks usually achieves better performance than its counterpart, i.e., uniform strategy, due to its superior representational capacity. However, many nonuniform quantization methods overlook the complicated projection process in implementing the nonuniformly quantized weights/activations, which incurs non-negligible time and space overhead in hardware deployment. In this study, we propose Nonuniform-to-Uniform Quantization (N2UQ), a method that can maintain the strong representation ability of nonuniform methods while being hardware-friendly and efficient as the uniform quantization for model inference. We achieve this through learning the flexible in-equidistant input thresholds to better fit the underlying distribution while quantizing these real-valued inputs into equidistant output levels. To train the quantized network with learnable input thresholds, we introduce a generalized straight-through estimator (G-STE) for intractable backward derivative calculation w.r.t. threshold parameters. Additionally, we consider entropy preserving regularization to further reduce information loss in weight quantization. Even under this adverse constraint of imposing uniformly quantized weights and activations, our N2UQ outperforms state-of-the-art nonuniform quantization methods by 0.5 1.7% on ImageNet, demonstrating the contribution of N2UQ design. Code and models are available at: https://github.com/liuzechun/Nonuniform-to-Uniform-Quantization.
-
Stitched images provide a wide field-of-view (FoV) but suffer from unpleasant irregular boundaries. To deal with this problem, existing image rectangling methods devote to searching an initial mesh and optimizing a target mesh to form the mesh deformation in two stages. Then rectangular images can be generated by warping stitched images. However, these solutions only work for images with rich linear structures, leading to noticeable distortions for portraits and landscapes with non-linear objects. In this paper, we address these issues by proposing the first deep learning solution to image rectangling. Concretely, we predefine a rigid target mesh and only estimate an initial mesh to form the mesh deformation, contributing to a compact one-stage solution. The initial mesh is predicted using a fully convolutional network with a residual progressive regression strategy. To obtain results with high content fidelity, a comprehensive objective function is proposed to simultaneously encourage the boundary rectangular, mesh shape-preserving, and content perceptually natural. Besides, we build the first image stitching rectangling dataset with a large diversity in irregular boundaries and scenes. Extensive experiments demonstrate our superiority over traditional methods both quantitatively and qualitatively. The codes and dataset will be available.
-
Domain generalization refers to the problem of training a model from a collection of different source domains that can directly generalize to the unseen target domains. A promising solution is contrastive learning, which attempts to learn domain-invariant representations by exploiting rich semantic relations among sample-to-sample pairs from different domains. A simple approach is to pull positive sample pairs from different domains closer while pushing other negative pairs further apart. In this paper, we find that directly applying contrastive-based methods (e.g., supervised contrastive learning) are not effective in domain generalization. We argue that aligning positive sample-to-sample pairs tends to hinder the model generalization due to the significant distribution gaps between different domains. To address this issue, we propose a novel proxy-based contrastive learning method, which replaces the original sample-to-sample relations with proxy-to-sample relations, significantly alleviating the positive alignment issue. Experiments on the four standard benchmarks demonstrate the effectiveness of the proposed method. Furthermore, we also consider a more complex scenario where no ImageNet pre-trained models are provided. Our method consistently shows better performance.
-
We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry. We also present a new method for 6D pose estimation of rigid objects using the learnt distributions to sample, score and refine pose hypotheses. The correspondence distributions are learnt with a contrastive loss, represented in object-specific latent spaces by an encoder-decoder query model and a small fully connected key model. Our method is unsupervised with respect to visual ambiguities, yet we show that the query- and key models learn to represent accurate multi-modal surface distributions. Our pose estimation method improves the state-of-the-art significantly on the comprehensive BOP Challenge, trained purely on synthetic data, even compared with methods trained on real data. The project site is at surfemb.github.io.
-
We address the problem of generating a 360-degree image from a single image with a narrow field of view by estimating its surroundings. Previous methods suffered from overfitting to the training resolution and deterministic generation. This paper proposes a completion method using a transformer for scene modeling and novel methods to improve the properties of a 360-degree image on the output image. Specifically, we use CompletionNets with a transformer to perform diverse completions and AdjustmentNet to match color, stitching, and resolution with an input image, enabling inference at any resolution. To improve the properties of a 360-degree image on an output image, we also propose WS-perceptual loss and circular inference. Thorough experiments show that our method outperforms state-of-the-art (SOTA) methods both qualitatively and quantitatively. For example, compared to SOTA methods, our method completes images 16 times larger in resolution and achieves 1.7 times lower Frechet inception distance (FID). Furthermore, we propose a pipeline that uses the completion results for lighting and background of 3DCG scenes. Our plausible background completion enables perceptually natural results in the application of inserting virtual objects with specular surfaces.
-
A 3D scene consists of a set of objects, each with a shape and a layout giving their position in space. Understanding 3D scenes from 2D images is an important goal, with applications in robotics and graphics. While there have been recent advances in predicting 3D shape and layout from a single image, most approaches rely on 3D ground truth for training which is expensive to collect at scale. We overcome these limitations and propose a method that learns to predict 3D shape and layout for objects without any ground truth shape or layout information: instead we rely on multi-view images with 2D supervision which can more easily be collected at scale. Through extensive experiments on ShapeNet, Hypersim, and ScanNet we demonstrate that our approach scales to large datasets of realistic images, and compares favorably to methods relying on 3D ground truth. On Hypersim and ScanNet where reliable 3D ground truth is not available, our approach outperforms supervised approaches trained on smaller and less diverse datasets.
-
Temporal action detection (TAD) is an important yet challenging task in video understanding. It aims to simultaneously predict the semantic label and the temporal interval of every action instance in an untrimmed video. Rather than end-to-end learning, most existing methods adopt a head-only learning paradigm, where the video encoder is pre-trained for action classification, and only the detection head upon the encoder is optimized for TAD. The effect of end-to-end learning is not systematically evaluated. Besides, there lacks an in-depth study on the efficiency-accuracy trade-off in end-to-end TAD. In this paper, we present an empirical study of end-to-end temporal action detection. We validate the advantage of end-to-end learning over head-only learning and observe up to 11% performance improvement. Besides, we study the effects of multiple design choices that affect the TAD performance and speed, including detection head, video encoder, and resolution of input videos. Based on the findings, we build a mid-resolution baseline detector, which achieves the state-of-the-art performance of end-to-end methods while running more than 4x faster. We hope that this paper can serve as a guide for end-to-end learning and inspire future research in this field. Code and models are available at https://github.com/xlliu7/E2E-TAD.
-
From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies. We admire these progresses but are confused about the necessity: is there a simple method that can perform comparably well? This paper proposes SimVP, a simple video prediction model that is completely built upon CNN and trained by MSE loss in an end-to-end fashion. Without introducing any additional tricks and complicated strategies, we can achieve state-of-the-art performance on five benchmark datasets. Through extended experiments, we demonstrate that SimVP has strong generalization and extensibility on real-world datasets. The significant reduction of training cost makes it easier to scale to complex scenarios. We believe SimVP can serve as a solid baseline to stimulate the further development of video prediction.
-
Point-based object localization (POL), which pursues high-performance object sensing under low-cost data annotation, has attracted increased attention. However, the point annotation mode inevitably introduces semantic variance for the inconsistency of annotated points. Existing POL methods heavily reply on accurate key-point annotations which are difficult to define. In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points. To this end, we propose a coarse point refinement (CPR) approach, which to our best knowledge is the first attempt to alleviate semantic variance from the perspective of algorithm. CPR constructs point bags, selects semantic-correlated points, and produces semantic center points through multiple instance learning (MIL). In this way, CPR defines a weakly supervised evolution procedure, which ensures training high-performance object localizer under coarse point supervision. Experimental results on COCO, DOTA and our proposed SeaPerson dataset validate the effectiveness of the CPR approach. The dataset and code will be available at https://github.com/ucas-vg/PointTinyBenchmark/
-
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable to track objects with strong variation over a long time span. As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward. We present a novel unsupervised tracking framework, in which we can learn temporal correspondence both on the classification branch and regression branch. Specifically, to propagate reliable template feature in the forward propagation process so that the tracker can be trained in the cycle, we first propose a consistency propagation transformation. We then identify an ill-posed penalty problem in conventional cycle training in backward propagation process. Thus, a differentiable region mask is proposed to select features as well as to implicitly penalize tracking errors on intermediate frames. Moreover, since noisy labels may degrade training, we propose a mask-guided loss reweighting strategy to assign dynamic weights based on the quality of pseudo labels. In extensive experiments, our tracker outperforms preceding unsupervised methods by a substantial margin, performing on par with supervised methods on large-scale datasets such as TrackingNet and LaSOT. Code is available at https://github.com/FlorinShum/ULAST.
-
Multiple-instance learning (MIL) provides an effective way to tackle the video anomaly detection problem by modeling it as a weakly supervised problem as the labels are usually only available at the video level while missing for frames due to expensive labeling cost. We propose to conduct novel Bayesian non-parametric submodular video partition (BN-SVP) to significantly improve MIL model training that can offer a highly reliable solution for robust anomaly detection in practical settings that include outlier segments or multiple types of abnormal events. BN-SVP essentially performs dynamic non-parametric hierarchical clustering with an enhanced self-transition that groups segments in a video into temporally consistent and semantically coherent hidden states that can be naturally interpreted as scenes. Each segment is assumed to be generated through a non-parametric mixture process that allows variations of segments within the same scenes to accommodate the dynamic and noisy nature of many real-world surveillance videos. The scene and mixture component assignment of BN-SVP also induces a pairwise similarity among segments, resulting in non-parametric construction of a submodular set function. Integrating this function with an MIL loss effectively exposes the model to a diverse set of potentially positive instances to improve its training. A greedy algorithm is developed to optimize the submodular function and support efficient model training. Our theoretical analysis ensures a strong performance guarantee of the proposed algorithm. The effectiveness of the proposed approach is demonstrated over multiple real-world anomaly video datasets with robust detection performance.
-
Despite recent advances in deep neural models for semantic image editing, present approaches are dependent on explicit human input. Previous work assumes the availability of manually curated datasets for supervised learning, while for unsupervised approaches the human inspection of discovered components is required to identify those which modify worthwhile semantic features. Here, we present a novel alternative: the utilization of brain responses as a supervision signal for learning semantic feature representations. Participants (N=30) in a neurophysiological experiment were shown artificially generated faces and instructed to look for a particular semantic feature, such as "old" or "smiling", while their brain responses were recorded via electroencephalography (EEG). Using supervision signals inferred from these responses, semantic features within the latent space of a generative adversarial network (GAN) were learned and then used to edit semantic features of new images. We show that implicit brain supervision achieves comparable semantic image editing performance to explicit manual labeling. This work demonstrates the feasibility of utilizing implicit human reactions recorded via brain-computer interfaces for semantic image editing and interpretation.
-
Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this paper, we propose an intuitive yet effective self-supervised approach to train a 3D shape variational autoencoder (VAE) which encourages a disentangled latent representation of identity features. Curating the mini-batch generation by swapping arbitrary features across different shapes allows to define a loss function leveraging known differences and similarities in the latent representations. Experimental results conducted on 3D meshes show that state-of-the-art methods for latent disentanglement are not able to disentangle identity features of faces and bodies. Our proposed method properly decouples the generation of such features while maintaining good representation and reconstruction capabilities. Our code and pre-trained models are available at github.com/simofoti/3DVAE-SwapDisentangled.
-
As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not easily adapted to the other due to the divergent training datasets and tracking objects of both tasks. Although UniTrack demonstrates that a shared appearance model with multiple heads can be used to tackle individual tracking tasks, it fails to exploit the large-scale tracking datasets for training and performs poorly on single object tracking. In this work, we present the Unified Transformer Tracker (UTT) to address tracking problems in different scenarios with one paradigm. A track transformer is developed in our UTT to track the target in both SOT and MOT where the correlation between the target feature and the tracking frame feature is exploited to localize the target. We demonstrate that both SOT and MOT tasks can be solved within this framework, and the model can be simultaneously end-to-end trained by alternatively optimizing the SOT and MOT objectives on the datasets of individual tasks. Extensive experiments are conducted on several benchmarks with a unified model trained on both SOT and MOT datasets.
-
Recent cost volume pyramid based deep neural networks have unlocked the potential of efficiently leveraging high-resolution images for depth inference from multi-view stereo. In general, those approaches assume that the depth of each pixel follows a unimodal distribution. Boundary pixels usually follow a multi-modal distribution as they represent different depths; Therefore, the assumption results in an erroneous depth prediction at the coarser level of the cost volume pyramid and can not be corrected in the refinement levels leading to wrong depth predictions. In contrast, we propose constructing the cost volume by non-parametric depth distribution modeling to handle pixels with unimodal and multi-modal distributions. Our approach outputs multiple depth hypotheses at the coarser level to avoid errors in the early stage. As we perform local search around these multiple hypotheses in subsequent levels, our approach does not maintain the rigid depth spatial ordering and, therefore, we introduce a sparse cost aggregation network to derive information within each volume. We evaluate our approach extensively on two benchmark datasets: DTU and Tanks & Temples. Our experimental results show that our model outperforms existing methods by a large margin and achieves superior performance on boundary regions. Code is available at https://github.com/NVlabs/NP-CVP-MVSNet
-
Despite the recent success of long-tailed object detection, almost all long-tailed object detectors are developed based on the two-stage paradigm. In practice, one-stage detectors are more prevalent in the industry because they have a simple and fast pipeline that is easy to deploy. However, in the long-tailed scenario, this line of work has not been explored so far. In this paper, we investigate whether one-stage detectors can perform well in this case. We discover the primary obstacle that prevents one-stage detectors from achieving excellent performance is: categories suffer from different degrees of positive-negative imbalance problems under the long-tailed data distribution. The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem. To address this issue, we propose the Equalized Focal Loss (EFL) that rebalances the loss contribution of positive and negative samples of different categories independently according to their imbalance degrees. Specifically, EFL adopts a category-relevant modulating factor which can be adjusted dynamically by the training status of different categories. Extensive experiments conducted on the challenging LVIS v1 benchmark demonstrate the effectiveness of our proposed method. With an end-to-end training pipeline, EFL achieves 29.2% in terms of overall AP and obtains significant performance improvements on rare categories, surpassing all existing state-of-the-art methods. The code is available at https://github.com/ModelTC/EOD.
-
Our work focuses on addressing sample deficiency from low-density regions of data manifold in common image datasets. We leverage diffusion process based generative models to synthesize novel images from low-density regions. We observe that uniform sampling from diffusion models predominantly samples from high-density regions of the data manifold. Therefore, we modify the sampling process to guide it towards low-density regions while simultaneously maintaining the fidelity of synthetic data. We rigorously demonstrate that our process successfully generates novel high fidelity samples from low-density regions. We further examine generated samples and show that the model does not memorize low-density data and indeed learns to generate novel samples from low-density regions.
-
Deep Learning (DL) has shown great promise in the unsupervised task of clustering. That said, while in classical (i.e., non-deep) clustering the benefits of the nonparametric approach are well known, most deep-clustering methods are parametric: namely, they require a predefined and fixed number of clusters, denoted by K. When K is unknown, however, using model-selection criteria to choose its optimal value might become computationally expensive, especially in DL as the training process would have to be repeated numerous times. In this work, we bridge this gap by introducing an effective deep-clustering method that does not require knowing the value of K as it infers it during the learning. Using a split/merge framework, a dynamic architecture that adapts to the changing K, and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones). While the very few existing deep nonparametric methods lack scalability, we demonstrate ours by being the first to report the performance of such a method on ImageNet. We also demonstrate the importance of inferring K by showing how methods that fix it deteriorate in performance when their assumed K value gets further from the ground-truth one, especially on imbalanced datasets. Our code is available at https://github.com/BGU-CS-VIL/DeepDPM.
-
Event-based cameras bring a unique capability to tracking, being able to function in challenging real-world conditions as a direct result of their high temporal resolution and high dynamic range. These imagers capture events asynchronously that encode rich temporal and spatial information. However, effectively extracting this information from events remains an open challenge. In this work, we propose a spiking transformer network, STNet, for single object tracking. STNet dynamically extracts and fuses information from both temporal and spatial domains. In particular, the proposed architecture features a transformer module to provide global spatial information and a spiking neural network (SNN) module for extracting temporal cues. The spiking threshold of the SNN module is dynamically adjusted based on the statistical cues of the spatial information, which we find essential in providing robust SNN features. We fuse both feature branches dynamically with a novel cross-domain attention fusion algorithm. Extensive experiments on three event-based datasets, FE240hz, EED and VisEvent validate that the proposed STNet outperforms existing state-of-the-art methods in both tracking accuracy and speed with a significant margin.
-
Interactive segmentation allows users to extract target masks by making positive/negative clicks. Although explored by many previous works, there is still a gap between academic approaches and industrial needs: first, existing models are not efficient enough to work on low power devices; second, they perform poorly when used to refine preexisting masks as they could not avoid destroying the correct part. FocalClick solves both issues at once by predicting and updating the mask in localized areas. For higher efficiency, we decompose the slow prediction on the entire image into two fast inferences on small crops: a coarse segmentation on the Target Crop, and a local refinement on the Focus Crop. To make the model work with preexisting masks, we formulate a sub-task termed Interactive Mask Correction, and propose Progressive Merge as the solution. Progressive Merge exploits morphological information to decide where to preserve and where to update, enabling users to refine any preexisting mask effectively. FocalClick achieves competitive results against SOTA methods with significantly smaller FLOPs. It also shows significant superiority when making corrections on preexisting masks. Code and data will be released at github.com/XavierCHEN34/ClickSEG
-
The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation. To tackle these issues, most of the previous works follow the global-local refinement pipeline, which pays more attention to the memory consumption but neglects the inference speed. In comparison to the pipeline that partitions the large image into small local regions, we focus on inferring the whole image directly. In this paper, we propose ISDNet, a novel ultra-high resolution segmentation framework that integrates the shallow and deep networks in a new manner, which significantly accelerates the inference speed while achieving accurate segmentation. To further exploit the relationship between the shallow and deep features, we propose a novel Relational-Aware feature Fusion module, which ensures high performance and robustness of our framework. Extensive experiments on Deepglobe, Inria Aerial, and Cityscapes datasets demonstrate our performance is consistently superior to state-of-the-arts. Specifically, it achieves 73.30 mIoU with a speed of 27.70 FPS on Deepglobe, which is more accurate and 172 x faster than the recent competitor. Code available at https://github.com/cedricgsh/ISDNet.
-
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications. This work instead develops a novel unsupervised domain adaptation framework for nighttime aerial tracking (named UDAT). Specifically, a unique object discovery approach is provided to generate training patches from raw nighttime tracking videos. To tackle the domain discrepancy, we employ a Transformer-based bridging layer post to the feature extractor to align image features from both domains. With a Transformer day/night feature discriminator, the daytime tracking model is adversarially trained to track at night. Moreover, we construct a pioneering benchmark namely NAT2021 for unsupervised domain adaptive nighttime tracking, which comprises a test set of 180 manually annotated tracking sequences and a train set of over 276k unlabelled nighttime tracking frames. Exhaustive experiments demonstrate the robustness and domain adaptability of the proposed framework in nighttime aerial tracking. The code and benchmark are available at https://github.com/vision4robotics/UDAT.
-
Audio-visual learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not fully exploited even when the multi-modal model outperforms its uni-modal counterpart. Specifically, in this paper we point out that existing audio-visual discriminative models, in which uniform objective is designed for all modalities, could remain under-optimized uni-modal representations, caused by another dominated modality in some scenarios, e.g., sound in blowing wind event, vision in drawing picture event, etc. To alleviate this optimization imbalance, we propose on-the-fly gradient modulation to adaptively control the optimization of each modality, via monitoring the discrepancy of their contribution towards the learning objective. Further, an extra Gaussian noise that changes dynamically is introduced to avoid possible generalization drop caused by gradient modulation. As a result, we achieve considerable improvement over common fusion methods on different audio-visual tasks, and this simple strategy can also boost existing multi-modal methods, which illustrates its efficacy and versatility.
-
Blind face restoration is to recover a high-quality face image from unknown degradations. As face image contains abundant contextual information, we propose a method, RestoreFormer, which explores fully-spatial attentions to model contextual information and surpasses existing works that use local convolutions. RestoreFormer has several benefits compared to prior arts. First, unlike the conventional multi-head self-attention in previous Vision Transformers (ViTs), RestoreFormer incorporates a multi-head cross-attention layer to learn fully-spatial interactions between corrupted queries and high-quality key-value pairs. Second, the key-value pairs in ResotreFormer are sampled from a reconstruction-oriented high-quality dictionary, whose elements are rich in high-quality facial features specifically aimed for face reconstruction, leading to superior restoration results. Third, RestoreFormer outperforms advanced state-of-the-art methods on one synthetic dataset and three real-world datasets, as well as produces images with better visual quality. Code is available at https://github.com/wzhouxiff/RestoreFormer.git.
-
Quantitative descriptions of confidence intervals and uncertainties of the predictions of a model are needed in many applications in vision and machine learning. Mechanisms that enable this for deep neural network (DNN) models are slowly becoming available, and occasionally, being integrated within production systems. But the literature is sparse in terms of how to perform statistical tests with the uncertainties produced by these overparameterized models. For two models with a similar accuracy profile, is the former model's uncertainty behavior better in a statistically significant sense compared to the second model? For high resolution images, performing hypothesis tests to generate meaningful actionable information (say, at a user specified significance level 0.05) is difficult but needed in both mission critical settings and elsewhere. In this paper, specifically for uncertainties defined on images, we show how revisiting results from Random Field theory (RFT) when paired with DNN tools (to get around computational hurdles) leads to efficient frameworks that can provide a hypothesis test capabilities, not otherwise available, for uncertainty maps from models used in many vision tasks. We show via many different experiments the viability of this framework.
-
Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients between the real and synthetic data batches. Despite the intuitive motivation and promising results, such gradient-based methods, by nature, easily overfit to a biased set of samples that produce dominant gradients, and thus lack a global supervision of data distribution. In this paper, we propose a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures. At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales, while accounting for the classification of real samples. Our scheme is further backed up by a novel dynamic bi-level optimization, which adaptively adjusts parameter updates to prevent over-/under-fitting. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art: on the SVHN dataset, for example, the performance gain is up to 11%. Extensive experiments and analysis verify the effectiveness and necessity of proposed designs.
-
Domain generalization (DG) is essentially an out-of-distribution problem, aiming to generalize the knowledge learned from multiple source domains to an unseen target domain. The mainstream is to leverage statistical models to model the dependence between data and labels, intending to learn representations independent of domain. Nevertheless, the statistical models are superficial descriptions of reality since they are only required to model dependence instead of the intrinsic causal mechanism. When the dependence changes with the target distribution, the statistic models may fail to generalize. In this regard, we introduce a general structural causal model to formalize the DG problem. Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments. Our goal is to extract the causal factors from inputs and then reconstruct the invariant causal mechanisms. However, the theoretical idea is far from practical of DG since the required causal/non-causal factors are unobserved. We highlight that ideal causal factors should meet three basic properties: separated from the non-causal ones, jointly independent, and causally sufficient for the classification. Based on that, we propose a Causality Inspired Representation Learning (CIRL) algorithm that enforces the representation to satisfy the above properties and then uses them to simulate the causal factors, which yields improved generalization ability. Extensive experimental results on several widely used datasets verify the effectiveness of our approach.
-
Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement in the coded aperture snapshot spectral imaging (CASSI) system. The HSI representations are highly similar and correlated across the spectral dimension. Modeling the inter-spectra interactions is beneficial for HSI reconstruction. However, existing CNN-based methods show limitations in capturing spectral-wise similarity and long-range dependencies. Besides, the HSI information is modulated by a coded aperture (physical mask) in CASSI. Nonetheless, current algorithms have not fully explored the guidance effect of the mask for HSI restoration. In this paper, we propose a novel framework, Mask-guided Spectral-wise Transformer (MST), for HSI reconstruction. Specifically, we present a Spectral-wise Multi-head Self-Attention (S-MSA) that treats each spectral feature as a token and calculates self-attention along the spectral dimension. In addition, we customize a Mask-guided Mechanism (MM) that directs S-MSA to pay attention to spatial regions with high-fidelity spectral representations. Extensive experiments show that our MST significantly outperforms state-of-the-art (SOTA) methods on simulation and real HSI datasets while requiring dramatically cheaper computational and memory costs. https://github.com/caiyuanhao1998/MST/
-
We propose a novel variational Bayesian formulation for diffeomorphic non-rigid registration of medical images, which learns in an unsupervised way a data-specific similarity metric. The proposed framework is general and may be used together with many existing image registration models. We evaluate it on brain MRI scans from the UK Biobank and show that use of the learnt similarity metric, which is parametrised as a neural network, leads to more accurate results than use of traditional functions, e.g. SSD and LCC, to which we initialise the model, without a negative impact on image registration speed or transformation smoothness. In addition, the method estimates the uncertainty associated with the transformation. The code and the trained models are available in a public repository: https://github.com/dgrzech/learnsim.
-
Online class-incremental continual learning aims to learn new classes continually from a never-ending and single-pass data stream, while not forgetting the learned knowledge of old classes. Existing replay-based methods have shown promising performance by storing a subset of old class data. Unfortunately, these methods only focus on selecting samples from the memory bank for replay and ignore the adequate exploration of semantic information in the single-pass data stream, leading to poor classification accuracy. In this paper, we propose a novel yet effective framework for online class-incremental continual learning, which considers not only the selection of stored samples, but also the full exploration of the data stream. Specifically, we propose a gradient-based sample selection strategy, which selects the stored samples whose gradients generated in the network are most interfered by the new incoming samples. We believe such samples are beneficial for updating the neural network based on back gradient propagation. More importantly, we seek to explore the semantic information between two different views of training images by maximizing their mutual information, which is conducive to the improvement of classification accuracy. Extensive experimental results demonstrate that our method achieves state-of-the-art performance on a variety of benchmark datasets. Our code is available on https://github.com/YananGu/DVC.
-
Scene Graph Generation (SGG) has attracted more and more attention from visual researchers in recent years, since Scene Graph (SG) is valuable in many downstream tasks due to its rich structural-semantic details. However, the application value of SG on downstream tasks is severely limited by the predicate classification bias, which is caused by long-tailed data and presented as semantic bias of predicted relation predicates. Existing methods mainly reduce the prediction bias by better aggregating contexts and integrating external priori knowledge, but rarely take the semantic similarities between predicates into account. In this paper, we propose a Predicate Probability Distribution based Loss (PPDL) to train the biased SGG models and obtain unbiased Scene Graphs ultimately. Firstly, we propose a predicate probability distribution as the semantic representation of a particular predicate class. Afterwards, we re-balance the biased training loss according to the similarity between the predicted probability distribution and the estimated one, and eventually eliminate the long-tailed bias on predicate classification. Notably, the PPDL training method is model-agnostic, and extensive experiments and qualitative analyses on the Visual Genome dataset reveal significant performance improvements of our method on tail classes compared to the state-of-the-art methods.
-
We present Block-NeRF, a variant of Neural Radiance Fields that can represent large-scale environments. Specifically, we demonstrate that when scaling NeRF to render city-scale scenes spanning multiple blocks, it is vital to decompose the scene into individually trained NeRFs. This decomposition decouples rendering time from scene size, enables rendering to scale to arbitrarily large environments, and allows per-block updates of the environment. We adopt several architectural changes to make NeRF robust to data captured over months under different environmental conditions. We add appearance embeddings, learned pose refinement, and controllable exposure to each individual NeRF, and introduce a procedure for aligning appearance between adjacent NeRFs so that they can be seamlessly combined. We build a grid of Block-NeRFs from 2.8 million images to create the largest neural scene representation to date, capable of rendering an entire neighborhood of San Francisco.
-
We exploit the complementary strengths of vision and proprioception to develop a point-goal navigation system for legged robots, called VP-Nav. Legged systems are capable of traversing more complex terrain than wheeled robots, but to fully utilize this capability, we need a high-level path planner in the navigation system to be aware of the walking capabilities of the low-level locomotion policy in varying environments. We achieve this by using proprioceptive feedback to ensure the safety of the planned path by sensing unexpected obstacles like glass walls, terrain properties like slipperiness or softness of the ground and robot properties like extra payload that are likely missed by vision. The navigation system uses onboard cameras to generate an occupancy map and a corresponding cost map to reach the goal. A fast marching planner then generates a target path. A velocity command generator takes this as input to generate the desired velocity for the walking policy. A safety advisor module adds sensed unexpected obstacles to the occupancy map and environment-determined speed limits to the velocity command generator. We show superior performance compared to wheeled robot baselines, and ablation studies which have disjoint high-level planning and low-level control. We also show the real-world deployment of VP-Nav on a quadruped robot with onboard sensors and computation. Videos at https://navigation-locomotion.github.io
-
The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e.g., "woman-on/standing on/walking on-beach" or "woman-near/looking at/in front of-child". While general SGG models are prone to predict head predicates and existing re-balancing strategies prefer tail categories, none of them can appropriately handle these hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating among hard-to-distinguish object classes, we propose a method named Fine-Grained Predicates Learning (FGPL) which aims at differentiating among hard-to-distinguish predicates for Scene Graph Generation task. Specifically, we first introduce a Predicate Lattice that helps SGG models to figure out fine-grained predicate pairs. Then, utilizing the Predicate Lattice, we propose a Category Discriminating Loss and an Entity Discriminating Loss, which both contribute to distinguishing fine-grained predicates while maintaining learned discriminatory power over recognizable ones. The proposed model-agnostic strategy significantly boosts the performances of three benchmark models (Transformer, VCTree, and Motif) by 22.8%, 24.1% and 21.7% of Mean Recall (mR@100) on the Predicate Classification sub-task, respectively. Our model also outperforms state-of-the-art methods by a large margin (i.e., 6.1%, 4.6%, and 3.2% of Mean Recall (mR@100)) on the Visual Genome dataset.
-
Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Segmentation (FS-Seg) tackles this problem with many constraints. In this paper, we introduce a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS-Seg), to analyze the generalization ability of simultaneously segmenting the novel categories with very few examples and the base categories with sufficient examples. It is the first study showing that previous representative state-of-the-art FS-Seg methods fall short in GFS-Seg and the performance discrepancy mainly comes from the constrained setting of FS-Seg. To make GFS-Seg tractable, we set up a GFS-Seg baseline that achieves decent performance without structural change on the original model. Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image. Both two contributions are experimentally shown to have substantial practical merit. Extensive experiments on Pascal-VOC and COCO manifest the effectiveness of CAPL, and CAPL generalizes well to FS-Seg by achieving competitive performance. Code will be made publicly available.
-
Previous LiDAR scene flow estimation methods, especially recurrent neural networks, usually suffer from structure distortion in challenging cases, such as sparse reflection and motion occlusions. In this paper, we propose a novel optimization method based on a recurrent neural network to predict LiDAR scene flow in a weakly supervised manner. Specifically, our neural recurrent network exploits direct rigidity constraints to preserve the geometric structure of the warped source scene during an iterative alignment procedure. An error awarded optimization strategy is proposed to update the LiDAR scene flow by minimizing the point measurement error instead of reconstructing the cost volume multiple times. Trained on two autonomous driving datasets, our network outperforms recent state-of-the-art networks on lidarKITTI by a large margin. The code and models will be available at https://github. com/gtdong-ustc/LiDARSceneFlow.
-
We present Neural Head Avatars, a novel neural representation that explicitly models the surface geometry and appearance of an animatable human avatar that can be used for teleconferencing in AR/VR or other applications in the movie or games industry that rely on a digital human. Our representation can be learned from a monocular RGB portrait video that features a range of different expressions and views. Specifically, we propose a hybrid representation consisting of a morphable model for the coarse shape and expressions of the face, and two feed-forward networks, predicting vertex offsets of the underlying mesh as well as a view- and expression-dependent texture. We demonstrate that this representation is able to accurately extrapolate to unseen poses and view points, and generates natural expressions while providing sharp texture details. Compared to previous works on head avatars, our method provides a disentangled shape and appearance model of the complete human head (including hair) that is compatible with the standard graphics pipeline. Moreover, it quantitatively and qualitatively outperforms current state of the art in terms of reconstruction quality and novel-view synthesis.
-
We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. For this, we propose to replace the linear transforms in DNNs by our B-cos transform. As we show, a sequence (network) of such transforms induces a single linear transform that faithfully summarises the full model computations. Moreover, the B-cos transform introduces alignment pressure on the weights during optimisation. As a result, those induced linear transforms become highly interpretable and align with task-relevant features. Importantly, the B-cos transform is designed to be compatible with existing architectures and we show that it can easily be integrated into common models such as VGGs, ResNets, InceptionNets, and DenseNets, whilst maintaining similar performance on ImageNet. The resulting explanations are of high visual quality and perform well under quantitative metrics for interpretability. Code available at github.com/moboehle/B-cos.
-
As 3D facial avatars become more widely used for communication, it is critical that they faithfully convey emotion. Unfortunately, the best recent methods that regress parametric 3D face models from monocular images are unable to capture the full spectrum of facial expression, such as subtle or extreme emotions. We find the standard reconstruction metrics used for training (landmark reprojection error, photometric error, and face recognition loss) are insufficient to capture high-fidelity expressions. The result is facial geometries that do not match the emotional content of the input image. We address this with EMOCA (EMOtion Capture and Animation), by introducing a novel deep perceptual emotion consistency loss during training, which helps ensure that the reconstructed 3D expression matches the expression depicted in the input image. While EMOCA achieves 3D reconstruction errors that are on par with the current best methods, it significantly outperforms them in terms of the quality of the reconstructed expression and the perceived emotional content. We also directly regress levels of valence and arousal and classify basic expressions from the estimated 3D face parameters. On the task of in-the-wild emotion recognition, our purely geometric approach is on par with the best image-based methods, highlighting the value of 3D geometry in analyzing human behavior. The model and code are publicly available at https://emoca.is.tue.mpg.de.
-
Modern handheld devices can acquire burst image sequence in a quick succession. However, the individual acquired frames suffer from multiple degradations and are misaligned due to camera shake and object motions. The goal of Burst Image Restoration is to effectively combine complimentary cues across multiple burst frames to generate high-quality outputs. Towards this goal, we develop a novel approach by solely focusing on the effective information exchange between burst frames, such that the degradations get filtered out while the actual scene details are preserved and enhanced. Our central idea is to create a set of pseudo-burst features that combine complimentary information from all the input burst frames to seamlessly exchange information. The pseudo-burst representations encode channel-wise features from the original burst images, thus making it easier for the model to learn distinctive information offered by multiple burst frames. However, the pseudo-burst cannot be successfully created unless the individual burst frames are properly aligned to discount inter-frame movements. Therefore, our approach initially extracts preprocessed features from each burst frame and matches them using an edge-boosting burst alignment module. The pseudo-burst features are then created and enriched using multi-scale contextual information. Our final step is to adaptively aggregate information from the pseudo-burst features to progressively increase resolution in multiple stages while merging the pseudo-burst features. In comparison to existing works that usually follow a late fusion scheme with single-stage upsampling, our approach performs favorably, delivering state-of-the-art performance on burst super-resolution, burst low-light image enhancement and burst denoising tasks. Our codes will be publicly released.
-
Transfer learning is a standard technique to transfer knowledge from one domain to another. For applications in medical imaging, transfer from ImageNet has become the de-facto approach, despite differences in the tasks and image characteristics between the domains. However, it is unclear what factors determine whether - and to what extent - transfer learning to the medical domain is useful. The long-standing assumption that features from the source domain get reused has recently been called into question. Through a series of experiments on several medical image benchmark datasets, we explore the relationship between transfer learning, data size, the capacity and inductive bias of the model, as well as the distance between the source and target domain. Our findings suggest that transfer learning is beneficial in most cases, and we characterize the important role feature reuse plays in its success.
-
The ability to synthesize long-term human motion sequences in real-world scenes can facilitate numerous applications. Previous approaches for scene-aware motion synthesis are constrained by pre-defined target objects or positions and thus limit the diversity of human-scene interactions for synthesized motions. In this paper, we focus on the problem of synthesizing diverse scene-aware human motions under the guidance of target action sequences. To achieve this, we first decompose the diversity of scene aware human motions into three aspects, namely interaction diversity (e.g. sitting on different objects with different poses in the given scenes), path diversity (e.g. moving to the target locations following different paths), and the motion diversity (e.g. having various body movements during moving). Based on this factorized scheme, a hierarchical framework is proposed with each sub-module responsible for modeling one aspect. We assess the effectiveness of our framework on two challenging datasets for scene-aware human motion synthesis. The experiment results show that the proposed framework remarkably outperforms the previous methods in terms of diversity and naturalness.
-
Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a particular trigger. Several works attempt to detect whether a given DNN has been injected with a specific trigger during the training. In a parallel line of research, the lottery ticket hypothesis reveals the existence of sparse subnetworks which are capable of reaching competitive performance as the dense network after independent training. Connecting these two dots, we investigate the problem of Trojan DNN detection from the brand new lens of sparsity, even when no clean training data is available. Our crucial observation is that the Trojan features are significantly more stable to network pruning than benign features. Leveraging that, we propose a novel Trojan network detection regime: first locating a "winning Trojan lottery ticket" which preserves nearly full Trojan information yet only chance-level performance on clean inputs; then recovering the trigger embedded in this already isolated subnetwork. Extensive experiments on various datasets, i.e., CIFAR-10, CIFAR-100, and ImageNet, with different network architectures, i.e., VGG-16, ResNet-18, ResNet-20s, and DenseNet-100 demonstrate the effectiveness of our proposal. Codes are available at https://github.com/VITA-Group/Backdoor-LTH.
-
Since facial actions such as lip movements contain significant information about speech content, it is not surprising that audio-visual speech enhancement methods are more accurate than their audio-only counterparts. Yet, state-of-the-art approaches still struggle to generate clean, realistic speech without noise artifacts and unnatural distortions in challenging acoustic environments. In this paper, we propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR. Our approach leverages audio-visual speech cues to generate the codes of a neural speech codec, enabling efficient synthesis of clean, realistic speech from noisy signals. Given the importance of speaker-specific cues in speech, we focus on developing personalized models that work well for individual speakers. We demonstrate the efficacy of our approach on a new audio-visual speech dataset collected in an unconstrained, large vocabulary setting, as well as existing audio-visual datasets, outperforming speech enhancement baselines on both quantitative metrics and human evaluation studies. Please see the supplemental video for qualitative results.
-
Deep learning methods can struggle to handle domain shifts not seen in training data, which can cause them to not generalize well to unseen domains. This has led to research attention on domain generalization (DG), which aims to the model's generalization ability to out-of-distribution. Adversarial domain generalization is a popular approach to DG, but conventional approaches (1) struggle to sufficiently align features so that local neighborhoods are mixed across domains; and (2) can suffer from feature space over collapse which can threaten generalization performance. To address these limitations, we propose localized adversarial domain generalization with space compactness maintenance (LADG) which constitutes two major contributions. First, we propose an adversarial localized classifier as the domain discriminator, along with a principled primary branch. This constructs a min-max game whereby the aim of the featurizer is to produce locally mixed domains. Second, we propose to use a coding-rate loss to alleviate feature space over collapse. We conduct comprehensive experiments on the Wilds DG benchmark to validate our approach, where LADG outperforms leading competitors on most datasets.
-
3D dense captioning aims to describe individual objects by natural language in 3D scenes, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only exploiting single modal information, e.g., point cloud, previous approaches fail to produce faithful descriptions. Though aggregating 2D features into point clouds may be beneficial, it introduces an extra computational burden, especially in inference phases. In this study, we investigate a cross-modal knowledge transfer using Transformer for 3D dense captioning, X-Trans2Cap, to effectively boost the performance of single-modal 3D caption through knowledge distillation using a teacher-student framework. In practice, during the training phase, the teacher network exploits auxiliary 2D modality and guides the student network that only takes point clouds as input through the feature consistency constraints. Owing to the well-designed cross-modal feature fusion module and the feature alignment in the training phase, X-Trans2Cap acquires rich appearance information embedded in 2D images with ease. Thus, a more faithful caption can be generated only using point clouds during the inference. Qualitative and quantitative results confirm that X-Trans2Cap outperforms previous state-of-the-art by a large margin, i.e., about +21 and about +16 absolute CIDEr score on ScanRefer and Nr3D datasets, respectively.
-
Face models are widely used in image processing and other domains. The input data to create a 3D face model ranges from accurate laser scans to simple 2D RGB photographs. These input data types are typically deficient either due to missing regions, or because they are under-constrained. As a result, reconstruction methods include embedded priors encoding the valid domain of faces. System designers must choose a source of input data and then choose a reconstruction method to obtain a usable 3D face. If a particular application domain requires accuracy X, which kinds of input data are suitable? Does the input data need to be 3D, or will 2D data suffice? This paper takes a step toward answering these questions using synthetic data. A ground truth dataset is used to analyze accuracy obtainable from 2D landmarks, 3D landmarks, low quality 3D, high quality 3D, texture color, normals, dense 2D image data, and when regions of the face are missing. Since the data is synthetic it can be analyzed both with and without measurement error. This idealized synthetic analysis is then compared to real results from several methods for constructing 3D faces from 2D photographs. The experimental results suggest that accuracy is severely limited when only 2D raw input data exists.
-
Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in autonomous driving to allow a vehicle to act safely in its 3D environment. The best performing methods in 3D semantic segmentation or object detection rely on a large amount of annotated data. Yet annotating 3D Lidar data for these tasks is tedious and costly. In this context, we propose a self-supervised pre-training method for 3D perception models that is tailored to autonomous driving data. Specifically, we leverage the availability of synchronized and calibrated image and LiDAR sensors in autonomous driving setups for distilling self-supervised pre-trained image representations into 3D models. Hence, our method does not require any point cloud nor image annotations. The key ingredient of our method is the use of superpixels which are used to pool 3D point features and 2D pixel features in visually similar regions. We then train a 3D network on the self-supervised task of matching these pooled point features with the corresponding pooled image pixel features. The advantages of contrasting regions obtained by superpixels are that: (1) grouping together pixels and points of visually coherent regions leads to a more meaningful contrastive task that produces features well adapted to 3D semantic segmentation and 3D object detection; (2) all the different regions have the same weight in the contrastive loss regardless of the number of 3D points sampled in these regions; (3) it mitigates the noise produced by incorrect matching of points and pixels due to occlusions between the different sensors. Extensive experiments on autonomous driving datasets demonstrate the ability of our image-to-Lidar distillation strategy to produce 3D representations that transfer well on semantic segmentation and object detection tasks.
-
We introduce a free-viewpoint rendering method -- HumanNeRF -- that works on a given monocular video of a human performing complex body motions, e.g. a video from YouTube. Our method enables pausing the video at any frame and rendering the subject from arbitrary new camera viewpoints or even a full 360-degree camera path for that particular frame and body pose. This task is particularly challenging, as it requires synthesizing photorealistic details of the body, as seen from various camera angles that may not exist in the input video, as well as synthesizing fine details such as cloth folds and facial appearance. Our method optimizes for a volumetric representation of the person in a canonical T-pose, in concert with a motion field that maps the estimated canonical representation to every frame of the video via backward warps. The motion field is decomposed into skeletal rigid and non-rigid motions, produced by deep networks. We show significant performance improvements over prior work, and compelling examples of free-viewpoint renderings from monocular video of moving humans in challenging uncontrolled capture scenarios.
-
Reconstructing the 3D pose of a person in metric scale from a single view image is a geometrically ill-posed problem. For example, we can not measure the exact distance of a person to the camera from a single view image without additional scene assumptions (e.g., known height). Existing learning based approaches circumvent this issue by reconstructing the 3D pose up to scale. However, there are many applications such as virtual telepresence, robotics, and augmented reality that require metric scale reconstruction. In this paper, we show that audio signals recorded along with an image, provide complementary information to reconstruct the metric 3D pose of the person. The key insight is that as the audio signals traverse across the 3D space, their interactions with the body provide metric information about the body's pose. Based on this insight, we introduce a time-invariant transfer function called pose kernel---the impulse response of audio signals induced by the body pose. The main properties of the pose kernel are that (1) its envelope highly correlates with 3D pose, (2) the time response corresponds to arrival time, indicating the metric distance to the microphone, and (3) it is invariant to changes in the scene geometry configurations. Therefore, it is readily generalizable to unseen scenes. We design a multi-stage 3D CNN that fuses audio and visual signals and learns to reconstruct 3D pose in a metric scale. We show that our multi-modal method produces accurate metric reconstruction in real world scenes, which is not possible with state-of-the-art lifting approaches including parametric mesh regression and depth regression.
-
The success of deep learning methods relies on the availability of well-labeled large-scale datasets. However, for medical images, annotating such abundant training data often requires experienced radiologists and consumes their limited time. Few-shot learning is developed to alleviate this burden, which achieves competitive performance with only several labeled data. However, a crucial yet previously overlooked problem in few-shot learning is about the selection of the template images for annotation before learning, which affects the final performance. We herein propose a novel Sample Choosing Policy (SCP) to select "the most worthy" images as the templates, in the context of medical landmark detection. SCP consists of three parts: 1) Self-supervised training for building a pre-trained deep model to extract features from radiological images, 2) Key Point Proposal for localizing informative patches, and 3) Representative Score Estimation for searching most representative samples or templates. The performance of SCP is demonstrated by various experiments on several widely-used public datasets. For one-shot medical landmark detection, the mean radial errors on Cephalometric and HandXray datasets are reduced from 3.595mm to 3.083mm and 4.114mm to 2.653mm, respectively.
-
In recent years, most 3D point cloud analysis models have focused on developing either new network architectures or more efficient modules for aggregating point features from a local neighborhood. Regardless of the network architecture or the methodology used for improved feature learning, these models share one thing, which is the use of max-pooling in the end to obtain permutation invariant features. We first show that this traditional approach causes only a fraction of 3D points contribute to the permutation invariant features, and discards the rest of the points. In order to address this issue and improve the performance of any baseline 3D point classification or segmentation model, we propose a new module, referred to as the Recycling MaxPooling (RMP) module, to recycle and utilize the features of some of the discarded points. We incorporate a refinement loss that uses the recycled features to refine the prediction loss obtained from the features kept by traditional max-pooling. To the best of our knowledge, this is the first work that explores recycling of still useful points that are traditionally discarded by max-pooling. We demonstrate the effectiveness of the proposed RMP module by incorporating it into several milestone baselines and state-of-the-art networks for point cloud classification and indoor semantic segmentation tasks. We show that RPM, without any bells and whistles, consistently improves the performance of all the tested networks by using the same base network implementation and hyper-parameters. The code is provided in the supplementary material.
-
Interpretability is an important property for visual models as it helps researchers and users understand the internal mechanism of a complex model. However, generating semantic explanations about the learned representation is challenging without direct supervision to produce such explanations. We propose a general framework, Latent Visual Semantic Explainer (LaViSE), to teach any existing convolutional neural network to generate text descriptions about its own latent representations at the filter level. Our method constructs a mapping between the visual and semantic spaces using generic image datasets, using images and category names. It then transfers the mapping to the target domain which does not have semantic labels. The proposed framework employs a modular structure and enables to analyze any trained network whether or not its original training data is available. We show that our method can generate novel descriptions for learned filters beyond the set of categories defined in the training dataset and perform an extensive evaluation on multiple datasets. We also demonstrate a novel application of our method for unsupervised dataset bias analysis which allows us to automatically discover hidden biases in datasets or compare different subsets without using additional labels. The dataset and code are made public to facilitate further research.
-
Quantization is an efficient network compression approach to reduce the inference time. However, existing approaches ignored the distribution difference between training and testing data, thereby inducing a large quantization error in inference. To address this issue, we propose a new quantization scheme, Alignment Quantization with ADMM-based Correlation Preservation (AlignQ), which exploits the cumulative distribution function (CDF) to align the data to be i.i.d. (independently and identically distributed) for quantization error minimization. Afterward, our theoretical analysis indicates that the significant changes in data correlations after the quantization induce a large quantization error. Accordingly, we aim to preserve the relationship of data from the original space to the aligned quantization space for retaining the prediction information. We design an optimization process by leveraging the Alternating Direction Method of Multipliers (ADMM) optimization to minimize the differences in data correlations before and after the alignment and quantization. In experiments, we visualize non-i.i.d. in training and testing data in the benchmark. We further adopt domain shift data to compare AlignQ with the state-of-the-art. Experimental results show that AlignQ achieves significant performance improvements, especially in low-bit models. Code is available at https://github.com/tinganchen/AlignQ.git.
-
Knowledge distillation (KD) shows a bright promise as a powerful regularization strategy to boost generalization ability by leveraging learned sample-level soft targets. Yet, employing a complex pre-trained teacher network or an ensemble of peer students in existing KD is both time-consuming and computationally costly. Various self KD methods have been proposed to achieve higher distillation efficiency. However, they either require extra network architecture modification, or are difficult to parallelize. To cope with these challenges, we propose an efficient and reliable self-distillation framework, named Self-Distillation from Last Mini-Batch (DLB). Specifically, we rearrange the sequential sampling by constraining half of each mini-batch coinciding with the previous iteration. Meanwhile, the rest half will coincide with the upcoming iteration. Afterwards, the former half mini-batch distills on-the-fly soft targets generated in the previous iteration. Our proposed mechanism guides the training stability and consistency, resulting in robustness to label noise. Moreover, our method is easy to implement, without taking up extra run-time memory or requiring model structure modification. Experimental results on three classification benchmarks illustrate that our approach can consistently outperform state-of-the-art self-distillation approaches with different network architectures. Additionally, our method shows strong compatibility with augmentation strategies by gaining additional performance improvement.
-
Annotating tens or hundreds of tiny objects in a given image is laborious yet crucial for a multitude of Computer Vision tasks. Such imagery typically contains objects from various categories, yet the multi-class interactive annotation setting for the detection task has thus far been unexplored. To address these needs, we propose a novel interactive annotation method for multiple instances of tiny objects from multiple classes, based on a few point-based user inputs. Our approach, C3Det, relates the full image context with annotator inputs in a local and global manner via late-fusion and feature-correlation, respectively. We perform experiments on the Tiny-DOTA and LCell datasets using both two-stage and one-stage object detection architectures to verify the efficacy of our approach. Our approach outperforms existing approaches in interactive annotation, achieving higher mAP with fewer clicks. Furthermore, we validate the annotation efficiency of our approach in a user study where it is shown to be 2.85x faster and yield only 0.36x task load (NASA-TLX, lower is better) compared to manual annotation. The code is available at https://github.com/ChungYi347/Interactive-Multi-Class-Tiny-Object-Detection.
-
Saliency detection with light field images is becoming attractive given the abundant cues available, however, this comes at the expense of large-scale pixel level annotated data which is expensive to generate. In this paper, we propose to learn light field saliency from pixel-level noisy labels obtained from unsupervised hand crafted featured-based saliency methods. Given this goal, a natural question is: can we efficiently incorporate the relationships among light field cues while identifying clean labels in a unified framework? We address this question by formulating the learning as a joint optimization of intra light field features fusion stream and inter scenes correlation stream to generate the predictions. Specially, we first introduce a pixel forgetting guided fusion module to mutually enhance the light field features and exploit pixel consistency across iterations to identify noisy pixels. Next, we introduce a cross scene noise penalty loss for better reflecting latent structures of training data and enabling the learning to be invariant to noise. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our framework showing that it learns saliency prediction comparable to state-of-the-art fully supervised light field saliency methods. Our code is available at https://github.com/OLobbCode/NoiseLF.
-
Generic Event Boundary Detection (GEBD) is a newly suggested video understanding task that aims to find one level deeper semantic boundaries of events. Bridging the gap between natural human perception and video understanding, it has various potential applications, including interpretable and semantically valid video parsing. Still at an early development stage, existing GEBD solvers are simple extensions of relevant video understanding tasks, disregarding GEBD's distinctive characteristics. In this paper, we propose a novel framework for unsupervised/supervised GEBD, by using the Temporal Self-similarity Matrix (TSM) as the video representation. The new Recursive TSM Parsing (RTP) algorithm exploits local diagonal patterns in TSM to detect boundaries, and it is combined with the Boundary Contrastive (BoCo) loss to train our encoder to generate more informative TSMs. Our framework can be applied to both unsupervised and supervised settings, with both achieving state-of-the-art performance by a huge margin in GEBD benchmark. Especially, our unsupervised method outperforms previous state-of-the-art "supervised" model, implying its exceptional efficacy.
-
Multi-view depth estimation methods typically require the computation of a multi-view cost-volume, which leads to huge memory consumption and slow inference. Furthermore, multi-view matching can fail for texture-less surfaces, reflective surfaces and moving objects. For such failure modes, single-view depth estimation methods are often more reliable. To this end, we propose MaGNet, a novel framework for fusing single-view depth probability with multi-view geometry, to improve the accuracy, robustness and efficiency of multi-view depth estimation. For each frame, MaGNet estimates a single-view depth probability distribution, parameterized as a pixel-wise Gaussian. The distribution estimated for the reference frame is then used to sample per-pixel depth candidates. Such probabilistic sampling enables the network to achieve higher accuracy while evaluating fewer depth candidates. We also propose depth consistency weighting for the multi-view matching score, to ensure that the multi-view depth is consistent with the single-view predictions. The proposed method achieves state-of-the-art performance on ScanNet, 7-Scenes and KITTI. Qualitative evaluation demonstrates that our method is more robust against challenging artifacts such as texture-less/reflective surfaces and moving objects. Our code and model weights are available at https://github.com/baegwangbin/MaGNet.
-
Learning personalized models for user-customized computer-vision tasks is challenging due to the limited private-data and computation available on each edge device. Decentralized learning (DL) can exploit the images distributed over devices on a network topology to train a global model but is not designed to train personalized models for different tasks or optimize the topology. Moreover, the mixing weights used to aggregate neighbors' gradient messages in DL can be sub-optimal for personalization since they are not adaptive to different nodes/tasks and learning stages. In this paper, we dynamically update the mixing-weights to improve the personalized model for each node's task and meanwhile learn a sparse topology to reduce communication costs. Our first approach, "learning to collaborate (L2C)", directly optimizes the mixing weights to minimize the local validation loss per node for a pre-defined set of nodes/tasks. In order to produce mixing weights for new nodes or tasks, we further develop "meta-L2C", which learns an attention mechanism to automatically assign mixing weights by comparing two nodes' model updates. We evaluate both methods on diverse benchmarks and experimental settings for image classification. Thorough comparisons to both classical and recent methods for IID/non-IID decentralized and federated learning demonstrate our method's advantages in identifying collaborators among nodes, learning sparse topology, and producing better personalized models with low communication and computational cost.
-
We present CLIP-NeRF, a multi-modal 3D object manipulation method for neural radiance fields (NeRF). By leveraging the joint language-image embedding space of the recent Contrastive Language-Image Pre-Training (CLIP) model, we propose a unified framework that allows manipulating NeRF in a user-friendly way, using either a short text prompt or an exemplar image. Specifically, to combine the novel view synthesis capability of NeRF and the controllable manipulation ability of latent representations from generative models, we introduce a disentangled conditional NeRF architecture that allows individual control over both shape and appearance. This is achieved by performing the shape conditioning via applying a learned deformation field to the positional encoding and deferring color conditioning to the volumetric rendering stage. To bridge this disentangled latent representation to the CLIP embedding, we design two code mappers that take a CLIP embedding as input and update the latent codes to reflect the targeted editing. The mappers are trained with a CLIP-based matching loss to ensure the manipulation accuracy. Furthermore, we propose an inverse optimization method that accurately projects an input image to the latent codes for manipulation to enable editing on real images. We evaluate our approach by extensive experiments on a variety of text prompts and exemplar images and also provide an intuitive editing interface for real-time user interaction.
-
Point cloud classifiers with rotation robustness have been widely discussed in the 3D deep learning community. Most proposed methods either use rotation invariant descriptors as inputs or try to design rotation equivariant networks. However, robust models generated by these methods have limited performance under clean aligned datasets due to modifications on the original classifiers or input space. In this study, for the first time, we show that the rotation robustness of point cloud classifiers can also be acquired via adversarial training with better performance on both rotated and clean datasets. Specifically, our proposed framework named ART-Point regards the rotation of the point cloud as an attack and improves rotation robustness by training the classifier on inputs with Adversarial RoTations. We contribute an axis-wise rotation attack that uses back-propagated gradients of the pre-trained model to effectively find the adversarial rotations. To avoid model over-fitting on adversarial inputs, we construct rotation pools that leverage the transferability of adversarial rotations among samples to increase the diversity of training data. Moreover, we propose a fast one-step optimization to efficiently reach the final robust model. Experiments show that our proposed rotation attack achieves a high success rate and ART-Point can be used on most existing classifiers to improve the rotation robustness while showing better performance on clean datasets than state-of-the-art methods.
-
Neural Radiance Fields (NeRF) is a popular view synthesis technique that represents a scene as a continuous volumetric function, parameterized by multilayer perceptrons that provide the volume density and view-dependent emitted radiance at each location. While NeRF-based techniques excel at representing fine geometric structures with smoothly varying view-dependent appearance, they often fail to accurately capture and reproduce the appearance of glossy surfaces. We address this limitation by introducing Ref-NeRF, which replaces NeRF's parameterization of view-dependent outgoing radiance with a representation of reflected radiance and structures this function using a collection of spatially-varying scene properties. We show that together with a regularizer on normal vectors, our model significantly improves the realism and accuracy of specular reflections. Furthermore, we show that our model's internal representation of outgoing radiance is interpretable and useful for scene editing.
-
The application of deep neural networks (DNNs) on 360-degree images has achieved remarkable progress in the recent years. However, DNNs have been demonstrated to be vulnerable to well-crafted adversarial examples, which may trigger severe safety problems in the real-world applications based on 360-degree images. In this paper, we propose an adversarial attack targeting spherical images, called 360-attactk, that transfers adversarial perturbations from perspective-view (PV) images to a final adversarial spherical image. Given a target spherical image, we first represent it with a set of planar PV images, and then perform 2D attacks on them to obtain adversarial PV images. Considering the issue of the projective distortion between spherical and PV images, we propose a distortion-aware attack to reduce the negative impact of distortion on attack. Moreover, to reconstruct the final adversarial spherical image with high aggressiveness, we calculate the spherical saliency map with a novel spherical spectrum method and next propose a saliency-aware fusion strategy that merges multiple inverse perspective projections for the same position on the spherical image. Extensive experimental results show that 360-attack is effective for disturbing spherical images in the black-box setting. Our attack also proves the presence of adversarial transferability from Z2 to SO3 groups.
-
Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researchers have investigated the potential of supervised contrastive learning for long-tailed recognition, and demonstrated that it provides a strong performance gain. In this paper, we show that while supervised contrastive learning can help improve performance, past baselines suffer from poor uniformity brought in by imbalanced data distribution. This poor uniformity manifests in samples from the minority class having poor separability in the feature space. To address this problem, we propose targeted supervised contrastive learning (TSC), which improves the uniformity of the feature distribution on the hypersphere. TSC first generates a set of targets uniformly distributed on a hypersphere. It then makes the features of different classes converge to these distinct and uniformly distributed targets during training. This forces all classes, including minority classes, to maintain a uniform distribution in the feature space, improves class boundaries, and provides better generalization even in the presence of long-tail data. Experiments on multiple datasets show that TSC achieves state-of-the-art performance on long-tailed recognition tasks.
-
Although considerable progress has been made in semantic scene understanding under clear weather, it is still a tough problem under adverse weather conditions, such as dense fog, due to the uncertainty caused by imperfect observations. Besides, difficulties in collecting and labeling foggy images hinder the progress of this field. Considering the success in semantic scene understanding under clear weather, we think it is reasonable to transfer knowledge learned from clear images to the foggy domain. As such, the problem becomes to bridge the domain gap between clear images and foggy images. Unlike previous methods that mainly focus on closing the domain gap caused by fog --- defogging the foggy images or fogging the clear images, we propose to alleviate the domain gap by considering fog influence and style variation simultaneously. The motivation is based on our finding that the style-related gap and the fog-related gap can be divided and closed respectively, by adding an intermediate domain. Thus, we propose a new pipeline to cumulatively adapt style, fog and the dual-factor (style and fog). Specifically, we devise a unified framework to disentangle the style factor and the fog factor separately, and then the dual-factor from images in different domains. Furthermore, we collaborate the disentanglement of three factors with a novel cumulative loss to thoroughly disentangle these three factors. Our method achieves the state-of-the-art performance on three benchmarks and shows generalization ability in rainy and snowy scenes.
-
We introduce Ev-TTA, a simple, effective test-time adaptation algorithm for event-based object recognition. While event cameras are proposed to provide measurements of scenes with fast motions or drastic illumination changes, many existing event-based recognition algorithms suffer from performance deterioration under extreme conditions due to significant domain shifts. Ev-TTA mitigates the severe domain gaps by fine-tuning the pre-trained classifiers during the test phase using loss functions inspired by the spatio-temporal characteristics of events. Since the event data is a temporal stream of measurements, our loss function enforces similar predictions for adjacent events to quickly adapt to the changed environment online. Also, we utilize the spatial correlations between two polarities of events to handle noise under extreme illumination, where different polarities of events exhibit distinctive noise distributions. Ev-TTA demonstrates a large amount of performance gain on a wide range of event-based object recognition tasks without extensive additional training. Our formulation can be successfully applied regardless of input representations and further extended into regression tasks. We expect Ev-TTA to provide the key technique to deploy event-based vision algorithms in challenging real-world applications where significant domain shift is inevitable.
-
Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle to represent and classify the tail classes. Although the problem of learning unbiased classifiers has been well studied, methods for representing imbalanced data are under-explored. In this paper, we focus on representation learning for imbalanced data. Recently, supervised contrastive learning has shown promising performance on balanced data recently. However, through our theoretical analysis, we find that for long-tailed data, it fails to form a regular simplex which is an ideal geometric configuration for representation learning. To correct the optimization behavior of SCL and further improve the performance of long-tailed visual recognition, we propose a novel loss for balanced contrastive learning (BCL). Compared with SCL, we have two improvements in BCL: class-averaging, which balances the gradient contribution of negative classes; class-complement, which allows all classes to appear in every mini-batch. The proposed balanced contrastive learning (BCL) method satisfies the condition of forming a regular simplex and assists the optimization of cross-entropy. Equipped with BCL, the proposed two-branch framework can obtain a stronger feature representation and achieve competitive performance on long-tailed benchmark datasets such as CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018.
-
Vanilla unsupervised domain adaptation methods tend to optimize the model with fixed neural architecture, which is not very practical in real-world scenarios since the target data is usually processed by different resource-limited devices. It is therefore of great necessity to facilitate architecture adaptation across various devices. In this paper, we introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs. The main challenge in this framework lies in simultaneously boosting the adaptation performance of numerous models in the model bank. To tackle this problem, we develop a Stochastic EnsEmble Distillation method to fully exploit the complementary knowledge in the model bank for inter-model interaction. Nevertheless, considering the optimization conflict between inter-model interaction and intra-model adaptation, we augment the existing bi-classifier domain confusion architecture into an Optimization-Separated Tri-Classifier counterpart. After optimizing the model bank, architecture adaptation is leveraged via our proposed Unsupervised Performance Evaluation Metric. Under various resource constraints, our framework surpasses other competing approaches by a very large margin on multiple benchmarks. It is also worth emphasizing that our framework can preserve the performance improvement against the source-only model even when the computing complexity is reduced to 1/64. Code will be available at https://github.com/HIK-LAB/SlimDA.
-
Graph neural networks (GNNs) have achieved state-ofthe-art performance in many graph-based tasks such as node classification and graph classification. However, many recent works have demonstrated that an attacker can mislead GNN models by slightly perturbing the graph structure. Existing attacks to GNNs are either under the less practical threat model where the attacker is assumed to access the GNN model parameters, or under the practical black-box threat model but consider perturbing node features that are shown to be not enough effective. In this paper, we aim to bridge this gap and consider black-box attacks to GNNs with structure perturbation as well as with theoretical guarantees. We propose to address this challenge through bandit techniques. Specifically, we formulate our attack as an online optimization with bandit feedback. This original problem is essentially NP-hard due to the fact that perturbing the graph structure is a binary optimization problem. We then propose an online attack based on bandit optimization which is proven to be sublinear to the query number T, i.e., O(N^ 1/2 T^ 3/4 ) where N is the number of nodes in the graph. Finally, we evaluate our proposed attack by conducting experiments over multiple datasets and GNN models. The experimental results on various citation graphs and image graphs show that our attack is both effective and efficient.
-
Deformable image registration (DIR), aiming to find spatial correspondence between images, is one of the most critical problems in the domain of medical image analysis. In this paper, we present a novel, generic, and accurate diffeomorphic image registration framework that utilizes neural ordinary differential equations (NODEs). We model each voxel as a moving particle and consider the set of all voxels in a 3D image as a high-dimensional dynamical system whose trajectory determines the targeted deformation field. Our method leverages deep neural networks for their expressive power in modeling dynamical systems, and simultaneously optimizes for a dynamical system between the image pairs and the corresponding transformation. Our formulation allows various constraints to be imposed along the transformation to maintain desired regularities. Our experiment results show that our method outperforms the benchmarks under various metrics. Additionally, we demonstrate the feasibility to expand our framework to register multiple image sets using a unified form of transformation, which could possibly serve a wider range of applications.
-
Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow. However, the correlation volume computation requires a lot of memory, which makes prediction difficult on high-resolution images. In this paper, we propose a novel Patchmatch-based framework to work on high-resolution optical flow estimation. Specifically, we introduce the first end-to-end Patchmatch based deep learning optical flow. It can get high-precision results with lower memory benefiting from propagation and local search of Patchmatch. Furthermore, a new inverse propagation is proposed to decouple the complex operations of propagation, which can significantly reduce calculations in multiple iterations. At the time of submission, our method ranks first on all the metrics on the popular KITTI2015 benchmark, and ranks second on EPE on the Sintel clean benchmark among published optical flow methods. Experiment shows our method has a strong cross-dataset generalization ability that the F1-all achieves 13.73%, reducing 21% from the best published result 17.4% on KITTI2015. What's more, our method shows a good details preserving result on the high-resolution dataset DAVIS and consumes 2x less memory than RAFT.
-
Few-shot object detection (FSOD), with the aim to detect novel objects using very few training examples, has recently attracted great research interest in the community. Metric-learning based methods have been demonstrated to be effective for this task using a two-branch based siamese network, and calculate the similarity between image regions and few-shot examples for detection. However, in previous works, the interaction between the two branches is only restricted in the detection head, while leaving the remaining hundreds of layers for separate feature extraction. Inspired by the recent work on vision transformers and vision-language transformers, we propose a novel Fully Cross-Transformer based model (FCT) for FSOD by incorporating cross-transformer into both the feature backbone and detection head. The asymmetric-batched cross-attention is proposed to aggregate the key information from the two branches with different batch sizes. Our model can improve the few-shot similarity learning between the two branches by introducing the multi-level interactions. Comprehensive experiments on both PASCAL VOC and MSCOCO FSOD benchmarks demonstrate the effectiveness of our model.
-
Semantic segmentation of point cloud data is a critical task for autonomous driving and other applications. Recent advances of point cloud segmentation are mainly driven by new designs of local aggregation operators and point sampling methods. Unlike image segmentation, few efforts have been made to understand the fundamental issue of scale and how scales should interact and be fused. In this work, we investigate how to efficiently and effectively integrate features at varying scales and varying stages in a point cloud segmentation network. In particular, we open up the commonly used encoder-decoder architecture, and design scale pyramid architectures that allow information to flow more freely and systematically, both laterally and upward/downward in scale. Moreover, a cross-scale attention feature learning block has been designed to enhance the multi-scale feature fusion which occurs everywhere in the network. Such a design of multi-scale processing and fusion gains large improvements in accuracy without adding much additional computation. When built on top of the popular KPConv network, we see consistent improvements on a wide range of datasets, including achieving state-of-the-art performance on NPM3D and S3DIS. Moreover, the pyramid architecture is generic and can be applied to other network designs: we show an example of similar improvements over RandLANet.
-
Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences. However, since weak supervision cannot distinguish the losses caused by the detection and description steps, directly conducting weakly supervised learning within a joint training describe-then-detect pipeline suffers limited performance. In this paper, we propose a decoupled training describe-then-detect pipeline tailored for weakly supervised local feature learning. Within our pipeline, the detection step is decoupled from the description step and postponed until discriminative and robust descriptors are learned. In addition, we introduce a line-to-window search strategy to explicitly use the camera pose information for better descriptor learning. Extensive experiments show that our method, namely PoSFeat (Camera Pose Supervised Feature), outperforms previous fully and weakly supervised methods and achieves state-ofthe-art performance on a wide range of downstream tasks.
-
In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning. CACL consists of a 3D CNN and a video transformer which are used in parallel to generate diverse positive pairs for contrastive learning. This allows the model to learn strong representations from such diverse yet meaningful pairs. Furthermore, we introduce a temporal self-supervised learning module able to predict an Edit distance explicitly between two video sequences in the temporal order. This enables the model to learn a rich temporal representation that compensates strongly to the video-level representation learned by the CACL. We evaluate our method on the tasks of video retrieval and action recognition on UCF101 and HMDB51 datasets, where our method achieves excellent performance, surpassing the state-of-the-art methods such as VideoMoCo and MoCo+BE by a large margin.
-
Given a composite image, image harmonization aims to adjust the foreground to make it compatible with the background. High-resolution image harmonization is in high demand, but still remains unexplored. Conventional image harmonization methods learn global RGB-to-RGB transformation which could effortlessly scale to high resolution, but ignore diverse local context. Recent deep learning methods learn the dense pixel-to-pixel transformation which could generate harmonious outputs, but are highly constrained in low resolution. In this work, we propose a high-resolution image harmonization network with Collaborative Dual Transformation (CDTNet) to combine pixel-to-pixel transformation and RGB-to-RGB transformation coherently in an end-to-end network. Our CDTNet consists of a low-resolution generator for pixel-to-pixel transformation, a color mapping module for RGB-to-RGB transformation, and a refinement module to take advantage of both. Extensive experiments on high-resolution benchmark dataset and our created high-resolution real composite images demonstrate that our CDTNet strikes a good balance between efficiency and effectiveness. Our used datasets can be found in https://github.com/bcmi/CDTNet-High-Resolution-Image-Harmonization.
-
Monocular 3D object detection is an essential task in autonomous driving. However, most current methods consider each 3D object in the scene as an independent training sample, while ignoring their inherent geometric relations, thus inevitably resulting in a lack of leveraging spatial constraints. In this paper, we propose a novel method that takes all the objects into consideration and explores their mutual relationships to help better estimate the 3D boxes. Moreover, since 2D detection is more reliable currently, we also investigate how to use the detected 2D boxes as guidance to globally constrain the optimization of the corresponding predicted 3D boxes. To this end, a differentiable loss function, termed as Homography Loss, is proposed to achieve the goal, which exploits both 2D and 3D information, aiming at balancing the positional relationships between different objects by global constraints, so as to obtain more accurately predicted 3D boxes. Thanks to the concise design, our loss function is universal and can be plugged into any mature monocular 3D detector, while significantly boosting the performance over their baseline. Experiments demonstrate that our method yields the best performance (Nov. 2021) compared with the other state-of-the-arts by a large margin on KITTI 3D datasets.
-
Lines are among the most used computer vision features, in applications such as camera calibration to object detection. Catadioptric cameras with rotationally symmetric mirrors are omnidirectional imaging devices, capturing up to a 360 degrees field of view. These are used in many applications ranging from robotics to panoramic vision. Although known for some specific configurations, the modeling of line projection was never fully solved for general central and non-central catadioptric cameras. We start by taking some general point reflection assumptions and derive a line reflection constraint. This constraint is then used to define a line projection into the image. Next, we compare our model with previous methods, showing that our general approach outputs the same polynomial degrees as previous configuration-specific systems. We run several experiments using synthetic and real-world data, validating our line projection model. Lastly, we show an application of our methods to an absolute camera pose problem.
-
Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a one-to-one label assignment scheme, where the Hungarian algorithm is applied to match only one positive sample for each ground truth. Such one-to-one assignment may not be optimal for the matching between the learned proposal boxes and ground truths. To address this problem, we propose dynamic label assignment (DLA) based on the optimal transport algorithm to assign increasing positive samples in the iterative training stages of Sparse R-CNN. We constrain the matching to be gradually looser in the sequential stages as the later stage produces the refined proposals with improved precision. Second, the learned proposal boxes and features remain fixed for different images in the inference process of Sparse R-CNN. Motivated by dynamic convolution, we propose dynamic proposal generation (DPG) to assemble multiple proposal experts dynamically for providing better initial proposal boxes and features for the consecutive training stages. DPG thereby can derive sample-dependent proposal boxes and features for inference. Experiments demonstrate that our method, named Dynamic Sparse R-CNN, can boost the strong Sparse R-CNN baseline with different backbones for object detection. Particularly, Dynamic Sparse R-CNN reaches the state-of-the-art 47.2% AP on the COCO 2017 validation set, surpassing Sparse R-CNN by 2.2% AP with the same ResNet-50 backbone.
-
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for 3D semantic segmentation. We find that, directly applying existing methods usually results in performance instability at test time, because multi-modal input is not considered jointly. To design a framework that can take full advantage of multi-modality, where each modality provides regularized self-supervisory signals to other modalities, we propose two complementary modules within and across the modalities. First, Intra-modal Pseudo-label Generation (Intra-PG) is introduced to obtain reliable pseudo labels within each modality by aggregating information from two models that are both pre-trained on source data but updated with target data at different paces. Second, Intermodal Pseudo-label Refinement (Inter-PR) adaptively selects more reliable pseudo labels from different modalities based on a proposed consistency scheme. Experiments demonstrate that our regularized pseudo labels produce stable self-learning signals in numerous multi-modal test-time adaptation scenarios for 3D semantic segmentation. Visit our project website at https://www.nec-labs.com/ mas/MM-TTA.
-
Recurrent models have gained popularity in deep learning (DL) based video super-resolution (VSR), due to their increased computational efficiency, temporal receptive field and temporal consistency compared to sliding-window based models. However, when inferring on long video sequences presenting low motion (i.e. in which some parts of the scene barely move), recurrent models diverge through recurrent processing, generating high frequency artifacts. To the best of our knowledge, no study about VSR pointed out this instability problem, which can be critical for some real-world applications. Video surveillance is a typical example where such artifacts would occur, as both the camera and the scene stay static for a long time. In this work, we expose instabilities of existing recurrent VSR networks on long sequences with low motion. We demonstrate it on a new long sequence dataset Quasi-Static Video Set, that we have created. Finally, we introduce a new framework of recurrent VSR networks that is both stable and competitive, based on Lipschitz stability theory. We propose a new recurrent VSR network, coined Middle Recurrent Video Super-Resolution (MRVSR), based on this framework. We empirically show its competitive performance on long sequences with low motion.
-
We propose the Dual-Generator (DG) network for large-pose face reenactment. Given a source face and a reference face as inputs, the DG network can generate an output face that has the same pose and expression as of the reference face, and has the same identity as of the source face. As most approaches do not particularly consider large-pose reenactment, the proposed approach addresses this issue by incorporating a 3D landmark detector into the framework and considering a loss function to capture visible local shape variation across large pose. The DG network consists of two modules, the ID-preserving Shape Generator (IDSG) and the Reenacted Face Generator (RFG). The IDSG encodes the 3D landmarks of the reference face into a reference landmark code, and encodes the source face into a source face code. The reference landmark code and the source face code are concatenated and decoded to a set of target landmarks that exhibits the pose and expression of the reference face and preserves the identity of the source face.
-
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel. To improve real world applicability of such models, there are growing interests to develop models optimized for arbitrary upscaling factors. Our proposed method is the first to treat arbitrary rescaling, both upscaling and downscaling, as one unified process. Using joint optimization of both directions, the proposed model is able to learn upscaling and downscaling simultaneously and achieve bidirectional arbitrary image rescaling. It improves the performance of current arbitrary upscaling models by a large margin while at the same time learns to maintain visual perception quality in downscaled images. The proposed model is further shown to be robust in cycle idempotence test, free of severe degradations in reconstruction accuracy when the downscaling-to-upscaling cycle is applied repetitively. This robustness is beneficial for image rescaling in the wild when this cycle could be applied to one image for multiple times. It also performs well on tests with arbitrary large scales and asymmetric scales, even when the model is not trained with such tasks. Extensive experiments are conducted to demonstrate the superior performance of our model.
-
Learning geometry, motion, and appearance priors of object classes is important for the solution of a large variety of computer vision problems. While the majority of approaches has focused on static objects, dynamic objects, especially with controllable articulation, are less explored. We propose a novel approach for learning a representation of the geometry, appearance, and motion of a class of articulated objects given only a set of color images as input. In a self-supervised manner, our novel representation learns shape, appearance, and articulation codes that enable independent control of these semantic dimensions. Our model is trained end-to-end without requiring any articulation annotations. Experiments show that our approach performs well for different joint types, such as revolute and prismatic joints, as well as different combinations of these joints. Compared to state of the art that uses direct 3D supervision and does not output appearance, we recover more faithful geometry and appearance from 2D observations only. In addition, our representation enables a large variety of applications, such as few-shot reconstruction, the generation of novel articulations, and novel view-synthesis. Project page: https://weify627.github.io/nasam/.
-
Fitting geometric models onto outlier contaminated data is provably intractable. Many computer vision systems rely on random sampling heuristics to solve robust fitting, which do not provide optimality guarantees and error bounds. It is therefore critical to develop novel approaches that can bridge the gap between exact solutions that are costly, and fast heuristics that offer no quality assurances. In this paper, we propose a hybrid quantum-classical algorithm for robust fitting. Our core contribution is a novel robust fitting formulation that solves a sequence of integer programs and terminates with a global solution or an error bound. The combinatorial subproblems are amenable to a quantum annealer, which helps to tighten the bound efficiently. While our usage of quantum computing does not surmount the fundamental intractability of robust fitting, by providing error bounds our algorithm is a practical improvement over randomised heuristics. Moreover, our work represents a concrete application of quantum computing in computer vision. We present results obtained using an actual quantum computer (D-Wave Advantage) and via simulation.
-
Knowledge of the road network topology is crucial for autonomous planning and navigation. Yet, recovering such topology from a single image has only been explored in part. Furthermore, it needs to refer to the ground plane, where also the driving actions are taken. This paper aims at extracting the local road network topology, directly in the bird's-eye-view (BEV), all in a complex urban setting. The only input consists of a single onboard, forward looking camera image. We represent the road topology using a set of directed lane curves and their interactions, which are captured using their intersection points. To better capture topology, we introduce the concept of minimal cycles and their covers. A minimal cycle is the smallest cycle formed by the directed curve segments (between two intersections). The cover is a set of curves whose segments are involved in forming a minimal cycle. We first show that the covers suffice to uniquely represent the road topology. The covers are then used to supervise deep neural networks, along with the lane curve supervision. These learn to predict the road topology from a single input image. The results on the NuScenes and Argoverse benchmarks are significantly better than those obtained with baselines. Code: https://github.com/ybarancan/TopologicalLaneGraph.
-
A novel algorithm to detect road lanes in the eigenlane space is proposed in this paper. First, we introduce the notion of eigenlanes, which are data-driven descriptors for structurally diverse lanes, including curved, as well as straight, lanes. To obtain eigenlanes, we perform the best rank-M approximation of a lane matrix containing all lanes in a training set. Second, we generate a set of lane candidates by clustering the training lanes in the eigenlane space. Third, using the lane candidates, we determine an optimal set of lanes by developing an anchor-based detection network, called SIIC-Net. Experimental results demonstrate that the proposed algorithm provides excellent detection performance for structurally diverse lanes. Our codes are available at https://github.com/dongkwonjin/Eigenlanes.
-
This paper introduces a new matting task called human instance matting (HIM), which requires the pertinent model to automatically predict a precise alpha matte for each human instance. Straightforward combination of closely related techniques, namely, instance segmentation, soft segmentation and human/conventional matting, will easily fail in complex cases requiring disentangling mingled colors belonging to multiple instances along hairy and thin boundary structures. To tackle these technical challenges, we propose a human instance matting framework, called InstMatt, where a novel mutual guidance strategy working in tandem with a multi-instance refinement module is used, for delineating multi-instance relationship among humans with complex and overlapping boundaries if present. A new instance matting metric called instance matting quality (IMQ) is proposed, which addresses the absence of a unified and fair means of evaluation emphasizing both instance recognition and mat-ting quality. Finally, we construct a HIM benchmark for evaluation, which comprises of both synthetic and natural benchmark images. In addition to thorough experimental results on HIM, preliminary results are presented on general instance matting beyond multiple and overlapping human instances.
-
Temporal contexts among consecutive frames are far from being fully utilized in existing visual trackers. In this work, we present TCTrack, a comprehensive framework to fully exploit temporal contexts for aerial tracking. The temporal contexts are incorporated at two levels: the extraction of features and the refinement of similarity maps. Specifically, for feature extraction, an online temporally adaptive convolution is proposed to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights according to the previous frames. For similarity map refinement, we propose an adaptive temporal transformer, which first effectively encodes temporal knowledge in a memory-efficient way, before the temporal knowledge is decoded for accurate adjustment of the similarity map. TCTrack is effective and efficient: evaluation on four aerial tracking benchmarks shows its impressive performance; real-world UAV tests show its high speed of over 27 FPS on NVIDIA Jetson AGX Xavier.
-
Recently, large pretrained models (e.g., BERT, StyleGAN, CLIP) show great knowledge transfer and generalization capability on various downstream tasks within their domains. Inspired by these efforts, in this paper we propose a unified model for open-domain image editing focusing on color and tone adjustment of open-domain images while keeping their original content and structure. Our model learns a unified editing space that is more semantic, intuitive, and easy to manipulate than the operation space (e.g., contrast, brightness, color curve) used in many existing photo editing softwares. Our model belongs to the image-to-image translation framework which consists of an image encoder and decoder, and is trained on pairs of before-and-after edited images to produce multimodal outputs. We show that by inverting image pairs into latent codes of the learned editing space, our model can be leveraged for various downstream editing tasks such as language-guided image editing, personalized editing, editing-style clustering, retrieval, etc. We extensively study the unique properties of the editing space in experiments and demonstrate superior performance on the aforementioned tasks.
-
We propose GAN-Supervised Learning, a framework for learning discriminative models and their GAN-generated training data jointly end-to-end. We apply our framework to the dense visual alignment problem. Inspired by the classic Congealing method, our GANgealing algorithm trains a Spatial Transformer to map random samples from a GAN trained on unaligned data to a common, jointly-learned target mode. We show results on eight datasets, all of which demonstrate our method successfully aligns complex data and discovers dense correspondences. GANgealing significantly outperforms past self-supervised correspondence algorithms and performs on-par with (and sometimes exceeds) state-of-the-art supervised correspondence algorithms on several datasets---without making use of any correspondence supervision or data augmentation and despite being trained exclusively on GAN-generated data. For precise correspondence, we improve upon state-of-the-art supervised methods by as much as 3x. We show applications of our method for augmented reality, image editing and automated pre-processing of image datasets for downstream GAN training.
-
End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition. However, recent state-of-the-art methods usually incorporate detection and recognition simply by sharing the backbone, which does not directly take advantage of the feature interaction between the two tasks. In this paper, we propose a new end-to-end scene text spotting framework termed SwinTextSpotter. Using a transformer encoder with dynamic head as the detector, we unify the two tasks with a novel Recognition Conversion mechanism to explicitly guide text localization through recognition loss. The straightforward design results in a concise framework that requires neither additional rectification module nor character-level annotation for the arbitrarily-shaped text. Qualitative and quantitative experiments on multi-oriented datasets RoIC13 and ICDAR 2015, arbitrarily-shaped datasets Total-Text and CTW1500, and multi-lingual datasets ReCTS (Chinese) and VinText (Vietnamese) demonstrate SwinTextSpotter significantly outperforms existing methods. Code is available at https://github.com/mxin262/SwinTextSpotter.
-
Multi-view clustering can explore common semantics from multiple views and has attracted increasing attention. However, existing works punish multiple objectives in the same feature space, where they ignore the conflict between learning consistent common semantics and reconstructing inconsistent view-private information. In this paper, we propose a new framework of multi-level feature learning for contrastive multi-view clustering to address the aforementioned issue. Our method learns different levels of features from the raw features, including low-level features, high-level features, and semantic labels/features in a fusion-free manner, so that it can effectively achieve the reconstruction objective and the consistency objectives in different feature spaces. Specifically, the reconstruction objective is conducted on the low-level features. Two consistency objectives based on contrastive learning are conducted on the high-level features and the semantic labels, respectively. They make the high-level features effectively explore the common semantics and the semantic labels achieve the multi-view clustering. As a result, the proposed framework can reduce the adverse influence of view-private information. Extensive experiments on public datasets demonstrate that our method achieves state-of-the-art clustering effectiveness.
-
Vector graphics (VG) have been ubiquitous in our daily life with vast applications in engineering, architecture, designs, etc. The VG recognition process of most existing methods is to first render the VG into raster graphics (RG) and then conduct recognition based on RG formats. However, this procedure discards the structure of geometries and loses the high resolution of VG. Recently, another category of algorithms is proposed to recognize directly from the original VG format. But it is affected by the topological errors that can be filtered out by RG rendering. Instead of looking at one format, it is a good solution to utilize the formats of VG and RG together to avoid these shortcomings. Besides, we argue that the VG-to-RG rendering process is essential to effectively combine VG and RG information. By specifying the rules on how to transfer VG primitives to RG pixels, the rendering process depicts the interaction and correlation between VG and RG. As a result, we propose RenderNet, a unified architecture for recognition on both 2D and 3D scenarios, which considers both VG/RG representations and exploits their interaction by incorporating the VG-to-RG rasterization process. Experiments show that RenderNet can achieve state-of-the-art performance on 2D and 3D object recognition tasks on various VG datasets.
-
Layout design is ubiquitous in many applications, e.g. architecture/urban planning, etc, which involves a lengthy iterative design process. Recently, deep learning has been leveraged to automatically generate layouts via image generation, showing a huge potential to free designers from laborious routines. While automatic generation can greatly boost productivity, designer input is undoubtedly crucial. An ideal AI-aided design tool should automate repetitive routines, and meanwhile accept human guidance and provide smart/proactive suggestions. However, the capability of involving humans into the loop has been largely ignored in existing methods which are mostly end-to-end approaches. To this end, we propose a new human-in-the-loop generative model, iPLAN, which is capable of automatically generating layouts, but also interacting with designers throughout the whole procedure, enabling humans and AI to co-evolve a sketchy idea gradually into the final design. iPLAN is evaluated on diverse datasets and compared with existing methods. The results show that iPLAN has high fidelity in producing similar layouts to those from human designers, great flexibility in accepting designer inputs and providing design suggestions accordingly, and strong generalizability when facing unseen design tasks and limited training data.
-
Video frame interpolation (VFI), which aims to synthesize intermediate frames of a video, has made remarkable progress with development of deep convolutional networks over past years. Existing methods built upon convolutional networks generally face challenges of handling large motion due to the locality of convolution operations. To overcome this limitation, we introduce a novel framework, which takes advantage of Transformer to model long-range pixel correlation among video frames. Further, our network is equipped with a novel cross-scale window-based attention mechanism, where cross-scale windows interact with each other. This design effectively enlarges the receptive field and aggregates multi-scale information. Extensive quantitative and qualitative experiments demonstrate that our method achieves new state-of-the-art results on various benchmarks.
-
Recent development of neural implicit function has shown tremendous success on high-quality 3D shape reconstruction. However, most works divide the space into inside and outside of the shape, which limits their representing power to single-layer and watertight shapes. This limitation leads to tedious data processing (converting non-watertight raw data to watertight) as well as the incapability of representing general object shapes in the real world. In this work, we propose a novel method to represent general shapes including non-watertight shapes and shapes with multi-layer surfaces. We introduce General Implicit Function for 3D Shape (GIFS), which models the relationships between every two points instead of the relationships between points and surfaces. Instead of dividing 3D space into predefined inside-outside regions, GIFS encodes whether two points are separated by any surface. Experiments on ShapeNet show that GIFS outperforms previous state-of-the-art methods in terms of reconstruction quality, rendering efficiency, and visual fidelity.
-
Neural Radiance Field (NeRF) has gained considerable attention recently for 3D scene reconstruction and novel view synthesis due to its remarkable synthesis quality. However, image blurriness caused by defocus or motion, which often occurs when capturing scenes in the wild, significantly degrades its reconstruction quality. To address this problem, We propose Deblur-NeRF, the first method that can recover a sharp NeRF from blurry input. We adopt an analysis-by-synthesis approach that reconstructs blurry views by simulating the blurring process, thus making NeRF robust to blurry inputs. The core of this simulation is a novel Deformable Sparse Kernel (DSK) module that models spatially-varying blur kernels by deforming a canonical sparse kernel at each spatial location. The ray origin of each kernel point is jointly optimized, inspired by the physical blurring process. This module is parameterized as an MLP that has the ability to be generalized to various blur types. Jointly optimizing the NeRF and the DSK module allows us to restore a sharp NeRF. We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes. Evaluation results on both synthetic and real-world data show that our method outperforms several baselines. The synthetic and real datasets along with the source code can be find in https://limacv.github.io/deblurnerf/
-
We are interested in anticipating as early as possible the target location of a person's object manipulation action in a 3D workspace from egocentric vision. It is important in fields like human-robot collaboration, but has not yet received enough attention from vision and learning communities. To stimulate more research on this challenging egocentric vision task, we propose a large multimodality dataset of more than 1 million frames of RGB-D and IMU streams, and provide evaluation metrics based on our high-quality 2D and 3D labels from semi-automatic annotation. Meanwhile, we design baseline methods using recurrent neural networks and conduct various ablation studies to validate their effectiveness. Our results demonstrate that this new task is worthy of further study by researchers in robotics, vision, and learning communities.
-
We propose a novel approach to generate temporally coherent UV coordinates for loose clothing. Our method is not constrained by human body outlines and can capture loose garments and hair. We implemented a differentiable pipeline to learn UV mapping between a sequence of RGB inputs and textures via UV coordinates. Instead of treating the UV coordinates of each frame separately, our data generation approach connects all UV coordinates via feature matching for temporal stability. Subsequently, a generative model is trained to balance the spatial quality and temporal stability. It is driven by supervised and unsupervised losses in both UV and image spaces. Our experiments show that the trained models output high-quality UV coordinates and generalize to new poses. Once a sequence of UV coordinates has been inferred by our model, it can be used to flexibly synthesize new looks and modified visual styles. Compared to existing methods, our approach reduces the computational workload to animate new outfits by several orders of magnitude.
-
Multi-agent trajectory prediction is critical for planning and decision-making in human-interactive autonomous systems, such as self-driving cars. However, most prediction models are developed separately from their upstream perception (detection and tracking) modules, assuming ground truth past trajectories as inputs. As a result, their performance degrades significantly when using real-world noisy tracking results as inputs. This is typically caused by the propagation of errors from tracking to prediction, such as noisy tracks, fragments, and identity switches. To alleviate this propagation of errors, we propose a new prediction paradigm that uses detections and their affinity matrices across frames as inputs, removing the need for error-prone data association during tracking. Since affinity matrices contain "soft" information about the similarity and identity of detections across frames, making predictions directly from affinity matrices retains strictly more information than making predictions from the tracklets generated by data association. Experiments on large-scale, real-world autonomous driving datasets show that our affinity-based prediction scheme reduces overall prediction errors by up to 57.9%, in comparison to standard prediction pipelines that use tracklets as inputs, with even more significant error reduction (up to 88.6%) if restricting the evaluation to challenging scenarios with tracking errors. Our project website is at https://www.xinshuoweng.com/projects/Affinipred
-
We introduce DoubleField, a novel framework combining the merits of both surface field and radiance field for high-fidelity human reconstruction and rendering. Within DoubleField, the surface field and radiance field are associated together by a shared feature embedding and a surface-guided sampling strategy. Moreover, a view-to-view transformer is introduced to fuse multi-view features and learn view-dependent features directly from high-resolution inputs. With the modeling power of DoubleField and the view-to-view transformer, our method significantly improves the reconstruction quality of both geometry and appearance, while supporting direct inference, scene-specific high-resolution finetuning, and fast rendering. The efficacy of DoubleField is validated by the quantitative evaluations on several datasets and the qualitative results in a real-world sparse multi-view system, showing its superior capability for high-quality human model reconstruction and photo-realistic free-viewpoint human rendering. Data and source code will be made public for the research purpose.
-
We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions and rewards. To avoid the potentially hazardous trial-and-error of reinforcement learning, we focus on differentiable planners such as Value Iteration Networks (VIN), which are trained offline from safe expert demonstrations. Although they work well in small simulations, we address two major limitations that hinder their deployment. First, we observed that current differentiable planners struggle to plan long-term in environments with a high branching complexity. While they should ideally learn to assign low rewards to obstacles to avoid collisions, these penalties are not strong enough to guarantee collision-free operation. We thus impose a structural constraint on the value iteration, which explicitly learns to model impossible actions and noisy motion. Secondly, we extend the model to plan exploration with a limited perspective camera under translation and fine rotations, which is crucial for real robot deployment. Our proposals significantly improve semantic navigation and exploration on several 2D and 3D environments, succeeding in settings that are otherwise challenging for differentiable planners. As far as we know, we are the first to successfully apply them to the difficult Active Vision Dataset, consisting of real images captured from a robot.
-
We propose an iterative method for estimating rigid transformations from point sets using adiabatic quantum computation. Compared to existing quantum approaches, our method relies on an adaptive scheme to solve the problem to high precision, and does not suffer from inconsistent rotation matrices. Experimentally, our method performs robustly on several 2D and 3D datasets even with high outlier ratio.
-
This paper presents Video K-Net, a simple, strong, and unified framework for fully end-to-end video panoptic segmentation. The method is built upon K-Net, a method that unifies image segmentation via a group of learnable kernels. We observe that these learnable kernels from K-Net, which encode object appearances and contexts, can naturally associate identical instances across video frames. Motivated by this observation, Video K-Net learns to simultaneously segment and track "things" and "stuff" in a video with simple kernel-based appearance modeling and cross-temporal kernel interaction. Despite the simplicity, it achieves state-of-the-art video panoptic segmentation results on Citscapes-VPS and KITTI-STEP without bells and whistles. In particular on KITTI-STEP, the simple method can boost almost 12% relative improvements over previous methods. We also validate its generalization on video semantic segmentation, where we boost various baselines by 2% on the VSPW dataset. Moreover, we extend K-Net into clip-level video framework for video instance segmentation where we obtain 40.5% for ResNet50 backbone and 51.5% mAP for Swin-base on YouTube-2019 validation set. We hope this simple yet effective method can serve as a new flexible baseline in video segmentation. Both code and models are released at \href https://github.com/lxtGH/Video-K-Net.
-
Our lives can be seen as a complex weaving of activities; we switch from one activity to another, to maximise our achievements or in reaction to demands placed upon us. Observing a video of unscripted daily activities, we parse the video into its constituent activity threads through a process we call unweaving. To accomplish this, we introduce a video representation explicitly capturing activity threads called a thread bank, along with a neural controller capable of detecting goal changes and continuations of past activities, together forming UnweaveNet. We train and evaluate UnweaveNet on sequences from the unscripted egocentric dataset EPIC-KITCHENS. We propose and showcase the efficacy of pretraining UnweaveNet in a self-supervised manner.
-
Data imbalance exists ubiquitously in real-world visual regressions, e.g., age estimation and pose estimation, hurting the model's generalizability and fairness. Thus, imbalanced regression gains increasing research attention recently. Compared to imbalanced classification, imbalanced regression focuses on continuous labels, which can be boundless and high-dimensional and hence more challenging. In this work, we identify that the widely used Mean Square Error (MSE) loss function can be ineffective in imbalanced regression. We revisit MSE from a statistical view and propose a novel loss function, Balanced MSE, to accommodate the imbalanced training label distribution. We further design multiple implementations of Balanced MSE to tackle different real-world scenarios, particularly including the one that requires no prior knowledge about the training label distribution. Moreover, to the best of our knowledge, Balanced MSE is the first general solution to high-dimensional imbalanced regression. Extensive experiments on both synthetic and three real-world benchmarks demonstrate the effectiveness of Balanced MSE.
-
Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices). However, the data distribution among clients is often non-IID in nature, making efficient optimization difficult. To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model. Instead, we consider rethinking solutions to data heterogeneity in FL with a focus on local learning generality rather than proximal restriction. To this end, we first present a systematic study informed by second-order indicators to better understand algorithm effectiveness in FL. Interestingly, we find that standard regularization methods are surprisingly strong performers in mitigating data heterogeneity effects. Based on our findings, we further propose a simple and effective method, FedAlign, to overcome data heterogeneity and the pitfalls of previous methods. FedAlign achieves competitive accuracy with state-of-the-art FL methods across a variety of settings while minimizing computation and memory overhead. Code is available at https://github.com/mmendiet/FedAlign.
-
Remote photoplethysmography (rPPG), which aims at measuring heart activities and physiological signals from facial video without any contact, has great potential in many applications. Recent deep learning approaches focus on mining subtle rPPG clues using convolutional neural networks with limited spatio-temporal receptive fields, which neglect the long-range spatio-temporal perception and interaction for rPPG modeling. In this paper, we propose the PhysFormer, an end-to-end video transformer based architecture, to adaptively aggregate both local and global spatio-temporal features for rPPG representation enhancement. As key modules in PhysFormer, the temporal difference transformers first enhance the quasi-periodic rPPG features with temporal difference guided global attention, and then refine the local spatio-temporal representation against interference. Furthermore, we also propose the label distribution learning and a curriculum learning inspired dynamic constraint in frequency domain, which provide elaborate supervisions for PhysFormer and alleviate overfitting. Comprehensive experiments are performed on four benchmark datasets to show our superior performance on both intra- and cross-dataset testings. One highlight is that, unlike most transformer networks needed pretraining from large-scale datasets, the proposed PhysFormer can be easily trained from scratch on rPPG datasets, which makes it promising as a novel transformer baseline for the rPPG community. The codes will be released soon.
-
Most existing deep learning-based approaches for monocular 3D object detection directly regress the dimensions of objects and overlook their importance in solving the ill-posed problem. In this paper, we propose a general method to learn appropriate embeddings for dimension estimation in monocular 3D object detection. Specifically, we consider two intuitive clues in learning the dimension-aware embeddings with deep neural networks. First, we constrain the pair-wise distance on the embedding space to reflect the similarity of corresponding dimensions so that the model can take advantage of inter-object information to learn more discriminative embeddings for dimension estimation. Second, we propose to learn representative shape templates on the dimension-aware embedding space. Through the attention mechanism, each object can interact with the learnable templates and obtain the attentive dimensions as the initial estimation, which is further refined by the combined features from both the object and the attentive templates. Experimental results on the well-established KITTI dataset demonstrate the proposed method of dimension embeddings can bring consistent improvements with negligible computation cost overhead. We achieve new state-of-the-art performance on the KITTI 3D object detection benchmark.
-
Automatic font generation remains a challenging research issue due to the large amounts of characters with complicated structures. Typically, only a few samples can serve as the style/content reference (termed few-shot learning), which further increases the difficulty to preserve local style patterns or detailed glyph structures. We investigate the drawbacks of previous studies and find that a coarse-grained discriminator is insufficient for supervising a font generator. To this end, we propose a novel Component-Aware Module (CAM), which supervises the generator to decouple content and style at a more fine-grained level, i.e., the component level. Different from previous studies struggling to increase the complexity of generators, we aim to perform more effective supervision for a relatively simple generator to achieve its full potential, which is a brand new perspective for font generation. The whole framework achieves remarkable results by coupling component-level supervision with adversarial learning, hence we call it Component-Guided GAN, shortly CG-GAN. Extensive experiments show that our approach outperforms state-of-the-art one-shot font generation methods. Furthermore, it can be applied to handwritten word synthesis and scene text image editing, suggesting the generalization of our approach.
-
Neural Radiance Fields (NeRF) has achieved unprecedented view synthesis quality using coordinate-based neural scene representations. However, NeRF's view dependency can only handle simple reflections like highlights but cannot deal with complex reflections such as those from glass and mirrors. In these scenarios, NeRF models the virtual image as real geometries which leads to inaccurate depth estimation, and produces blurry renderings when the multi-view consistency is violated as the reflected objects may only be seen under some of the viewpoints. To overcome these issues, we introduce NeRFReN, which is built upon NeRF to model scenes with reflections. Specifically, we propose to split a scene into transmitted and reflected components, and model the two components with separate neural radiance fields. Considering that this decomposition is highly under-constrained, we exploit geometric priors and apply carefully-designed training strategies to achieve reasonable decomposition results. Experiments on various self-captured scenes show that our method achieves high-quality novel view synthesis and physically sound depth estimation results while enabling scene editing applications.
-
While researches on model-based blind single image super-resolution (SISR) have achieved tremendous successes recently, most of them do not consider the image degradation sufficiently. Firstly, they always assume image noise obeys an independent and identically distributed (i.i.d.) Gaussian or Laplacian distribution, which largely underestimates the complexity of real noise. Secondly, previous commonly-used kernel priors (e.g., normalization, sparsity) are not effective enough to guarantee a rational kernel solution, and thus degenerates the performance of subsequent SISR task. To address the above issues, this paper proposes a model-based blind SISR method under the probabilistic framework, which elaborately models image degradation from the perspectives of noise and blur kernel. Specifically, instead of the traditional i.i.d. noise assumption, a patch-based non-i.i.d. noise model is proposed to tackle the complicated real noise, expecting to increase the degrees of freedom of the model for noise representation. As for the blur kernel, we novelly con- struct a concise yet effective kernel generator, and plug it into the proposed blind SISR method as an explicit kernel prior (EKP). To solve the proposed model, a theoretically grounded Monte Carlo EM algorithm is specifically designed. Comprehensive experiments demonstrate the superiority of our method over current state-of-the-arts on synthetic and real datasets. The source code is available at https://github.com/zsyOAOA/BSRDM.
-
We present an algorithm for detecting planar primitives from unorganized 3D point clouds. Departing from an initial configuration, the algorithm refines both the continuous plane parameters and the discrete assignment of input points to them by seeking high fidelity, high simplicity and high completeness. Our key contribution relies upon the design of an exploration mechanism guided by a multi-objective energy function. The transitions within the large solution space are handled by five geometric operators that create, remove and modify primitives. We demonstrate the potential of our method on a variety of scenes, from organic shapes to man-made objects, and sensors, from multiview stereo to laser. We show its efficacy with respect to existing primitive fitting approaches and illustrate its applicative interest in compact mesh reconstruction, when combined with a plane assembly method.
-
Inverse rendering of complex material such as glossy, metal and mirror material is a long-standing ill-posed problem in this area, which has not been well solved. Previous approaches cannot tackle them well due to simplified BRDF and unsuitable illumination representations. In this paper, we present PhyIR, a neural inverse rendering method with a more completed SVBRDF representation and a physics-based in-network rendering layer, which can handle complex material and incorporate physical constraints by re-rendering realistic and detailed specular reflectance. Our framework estimates geometry, material and Spatially-Coherent (SC) illumination from a single indoor panorama. Due to the lack of panoramic datasets with completed SVBRDF and full-spherical light probes, we introduce an artist-designed dataset named FutureHouse with high-quality geometry, SVBRDF and per-pixel Spatially-Varying (SV) lighting. To ensure the coherence of SV lighting, a novel SC loss is proposed. Extensive experiments on both synthetic and real-world data show that the proposed method outperforms the state-of-the-arts quantitatively and qualitatively, and is able to produce photorealistic results for a number of applications such as dynamic virtual object insertion.
-
Image harmonization aims to achieve visual consistency in composite images by adapting a foreground to make it compatible with a background. However, existing methods always only use the real image as the positive sample to guide the training, and at most introduce the corresponding composite image as a single negative sample for an auxiliary constraint, which leads to limited distortion knowledge, and further causes a too large solution space, making the generated harmonized image distorted. Besides, none of them jointly constrain from the foreground self-style and foreground-background style consistency, which exacerbates this problem. Moreover, recent region-aware adaptive instance normalization achieves great success but only considers the global background feature distribution, making the aligned foreground feature distribution biased. To address these issues, we propose a self-consistent style contrastive learning scheme (SCS-Co). By dynamically generating multiple negative samples, our SCS-Co can learn more distortion knowledge and well regularize the generated harmonized image in the style representation space from two aspects of the foreground self-style and foreground-background style consistency, leading to a more photorealistic visual result. In addition, we propose a background-attentional adaptive instance normalization (BAIN) to achieve an attention-weighted background feature distribution according to the foreground-background feature similarity. Experiments demonstrate the superiority of our method over other state-of-the-art methods in both quantitative comparison and visual analysis.
-
Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window. Most current work uses a fixed single-scale window for modeling by default, ignoring the impact of window size on model performance. However, this may limit the modeling potential of these window-based models for multi-scale information. In this paper, we propose a novel method, named Dynamic Window Vision Transformer (DW-ViT). To the best of our knowledge, we are the first to use dynamic multi-scale windows to explore the upper limit of the effect of window settings on model performance. In DW-ViT, multi-scale information is obtained by assigning windows of different sizes to different head groups of window multi-head self-attention. Then, the information is dynamically fused by assigning different weights to the multi-scale window branches. We conducted a detailed performance evaluation on three datasets, ImageNet-1K, ADE20K, and COCO. Compared with related state-of-the-art (SoTA) methods, DW-ViT obtains the best performance. Specifically, compared with the current SoTA Swin Transformers [??], DW-ViT has achieved consistent and substantial improvements on all three datasets with similar parameters and computational costs. In addition, DW-ViT exhibits good scalability and can be easily inserted into any window-based visual transformers.
-
In this paper, we propose a new query-based detection framework for crowd detection. Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. Benefiting from the nature of the one-to-one label assignment rule, we propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries prone to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes. Equipped with our approach, Sparse RCNN achieves 92.0% \text AP , 41.4% \text MR ^ -2 and 83.2% \text JI on the challenging CrowdHuman [??] dataset, outperforming the box-based method MIP [??] that specifies in handling crowded scenarios. Moreover, the proposed method, robust to crowdedness, can still obtain consistent improvements on moderately and slightly crowded datasets like CityPersons [??] and COCO [??].
-
For Visible-Infrared person Re-IDentification (VI-ReID), existing modality-specific information compensation based models try to generate the images of missing modality from existing ones for reducing cross-modality discrepancy. However, because of the large modality discrepancy between visible and infrared images, the generated images usually have low qualities and introduce much more interfering information (e.g., color inconsistency). This greatly degrades the subsequent VI-ReID performance. Alternatively, we present a novel Feature-level Modality Compensation Network (FMCNet) for VIReID in this paper, which aims to compensate the missing modality-specific information in the feature level rather than in the image level, i.e., directly generating those missing modality-specific features of one modality from existing modality-shared features of the other modality. This will enable our model to mainly generate some discriminative person related modality-specific features and discard those non-discriminative ones for benefiting VI-ReID. For that, a single-modality feature decomposition module is first designed to decompose single-modality features into modality-specific ones and modality-shared ones. Then, a feature-level modality compensation module is present to generate those missing modality-specific features from existing modality-shared ones. Finally, a shared-specific feature fusion module is proposed to combine the existing and generated features for VI-ReID. The effectiveness of our proposed model is verified on two benchmark datasets.
-
The success of Generative Adversarial Networks (GANs) is largely built upon the adversarial training between a generator (G) and a discriminator (D). They are expected to reach a certain equilibrium where D cannot distinguish the generated images from the real ones. However, such an equilibrium is rarely achieved in practical GAN training, instead, D almost always surpasses G. We attribute one of its sources to the information asymmetry between D and G. We observe that D learns its own visual attention when determining whether an image is real or fake, but G has no explicit clue on which regions to focus on for a particular synthesis. To alleviate the issue of D dominating the competition in GANs, we aim to raise the spatial awareness of G. Randomly sampled multi-level heatmaps are encoded into the intermediate layers of G as an inductive bias. Thus G can purposefully improve the synthesis of certain image regions. We further propose to align the spatial awareness of G with the attention map induced from D. Through this way we effectively lessen the information gap between D and G. Extensive results show that our method pushes the two-player game in GANs closer to the equilibrium, leading to a better synthesis performance. As a byproduct, the introduced spatial awareness facilitates interactive editing over the output synthesis.
-
This work is concerned with representation of shapes while disentangling fine, local and possibly repeating geometry, from global, coarse structures. Achieving such disentanglement leads to two unrelated advantages: i) a significant compression in the number of parameters required to represent a given geometry; ii) the ability to manipulate either global geometry, or local details, without harming the other. At the core of our approach lies a novel pipeline and neural architecture, which are optimized to represent one specific atlas, representing one 3D surface. Our pipeline and architecture are designed so that disentanglement of global geometry from local details is accomplished through optimization, in a completely unsupervised manner. We show that this approach achieves better neural shape compression than the state of the art, as well as enabling manipulation and transfer of shape details.
-
Semantic segmentation of 3D medical images is a challenging task due to the high variability of the shape and pattern of objects (such as organs or tumors). Given the recent success of deep learning in medical image segmentation, Neural Architecture Search (NAS) has been introduced to find high-performance 3D segmentation network architectures. However, because of the massive computational requirements of 3D data and the discrete optimization nature of architecture search, previous NAS methods require a long search time or necessary continuous relaxation, and commonly lead to sub-optimal network architectures. While one-shot NAS can potentially address these disadvantages, its application in the segmentation domain has not been well studied in the expansive multi-scale multi-path search space. To enable one-shot NAS for medical image segmentation, our method, named HyperSegNAS, introduces a HyperNet to assist super-net training by incorporating architecture topology information. Such a HyperNet can be removed once the super-net is trained and introduces no overhead during architecture search. We show that HyperSegNAS yields better performing and more intuitive architectures compared to the previous state-of-the-art (SOTA) segmentation networks; furthermore, it can quickly and accurately find good architecture candidates under different computing constraints. Our method is evaluated on public datasets from the Medical Segmentation Decathlon (MSD) challenge, and achieves SOTA performances.
-
While datasets with single-label supervision have propelled rapid advances in image classification, additional annotations are necessary in order to quantitatively assess how models make predictions. To this end, for a subset of ImageNet samples, we collect segmentation masks for the entire object and 18 informative attributes. We call this dataset RIVAL10 (RIch Visual Attributes with Localization), consisting of roughly 26k instances over 10 classes. Using RIVAL10, we evaluate the sensitivity of a broad set of models to noise corruptions in foregrounds, backgrounds and attributes. In our analysis, we consider diverse state-of-the-art architectures (ResNets, Transformers) and training procedures (CLIP, SimCLR, DeiT, Adversarial Training). We find that, somewhat surprisingly, in ResNets, adversarial training makes models more sensitive to the background compared to foreground than standard training. Similarly, contrastively-trained models also have lower relative foreground sensitivity in both transformers and ResNets. Lastly, we observe intriguing adaptive abilities of transformers to increase relative foreground sensitivity as corruption level increases. Using saliency methods, we automatically discover spurious features that drive the background sensitivity of models and assess alignment of saliency maps with foregrounds. Finally, we quantitatively study the attribution problem for neural features by comparing feature saliency with ground-truth localization of semantic attributes.
-
Progress in 3D object understanding has relied on manually "canonicalized" shape datasets that contain instances with consistent position and orientation (3D pose). This has made it hard to generalize these methods to in-the-wild shapes, e.g., from internet model collections or depth sensors. ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds. We build on top of Tensor Field Networks (TFNs), a class of permutation- and rotation-equivariant, and translation-invariant 3D networks. During inference, our method takes an unseen full or partial 3D point cloud at an arbitrary pose and outputs an equivariant canonical pose. During training, this network uses self-supervision losses to learn the canonical pose from an un-canonicalized collection of full and partial 3D point clouds. ConDor can also learn to consistently co-segment object parts without any supervision. Extensive quantitative results on four new metrics show that our approach outperforms existing methods while enabling new applications such as operation on depth images and annotation transfer.
-
Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different. However, the training data in source domain required by most of the existing methods is usually unavailable in real-world applications due to privacy preserving policies. Recently, Source-Free Domain Adaptation (SFDA) has drawn much attention, which tries to tackle domain adaptation problem without using source data. In this work, we propose a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation. Firstly, we produce robust pseudo-labels for target data with spherical k-means clustering, whose initial class centers are the weight vectors (anchors) learned by the classifier of pretrained model. Furthermore, we propose to estimate the class-conditioned feature distribution of source domain by exploiting target data and corresponding anchors. Finally, we sample surrogate features from the estimated distribution, which are then utilized to align two domains by minimizing a contrastive adaptation loss function. Extensive experiments show that the proposed method achieves state-of-the-art performance on multiple DA benchmarks, and even outperforms traditional DA methods which require plenty of source data.
-
We consider distributed (gradient descent-based) learning scenarios where the server combines the gradients of learning objectives gathered from local clients. As individual data collection and learning environments can vary, some clients could transfer erroneous gradients e.g., due to adversarial data or gradient perturbations. Further, for data privacy and security, the identities of such affected clients are often unknown to the server. In such cases, naively aggregating the resulting gradients can mislead the learning process. We propose a new server-side learning algorithm that robustly combines gradients. Our algorithm embeds the local gradients into the manifold of normalized gradients and refines their combinations via simulating a diffusion process therein. The resulting algorithm is instantiated as a computationally simple and efficient weighted gradient averaging algorithm. In the experiments with five classification and three regression benchmark datasets, our algorithm demonstrated significant performance improvements over existing robust gradient combination algorithms as well as the baseline uniform gradient averaging algorithm.
-
Existing cross-domain detection methods mostly study the domain shifts where differences between domains are often caused by external environment and perceivable for humans. However, in real-world scenarios (e.g., MRI medical diagnosis, X-ray security inspection), there still exists another type of shift, named endogenous shift, where the differences between domains are mainly caused by the intrinsic factors (e.g., imaging mechanisms, hardware components, etc.), and usually inconspicuous. This shift can also severely harm the cross-domain detection performance but has been rarely studied. To support this study, we contribute the first Endogenous Domain Shift (EDS) benchmark, X-ray security inspection, where the endogenous shifts among the domains are mainly caused by different X-ray machine types with different hardware parameters, wear degrees, etc. EDS consists of 14,219 images including 31,654 common instances from three domains (X-ray machines), with bounding-box annotations from 10 categories. To handle the endogenous shift, we further introduce the Perturbation Suppression Network (PSN), motivated by the fact that this shift is mainly caused by two types of perturbations: category-dependent and category-independent ones. PSN respectively exploits local prototype alignment and global adversarial learning mechanism to suppress these two types of perturbations. The comprehensive evaluation results show that PSN outperforms SOTA methods, serving a new perspective to the cross-domain research community.
-
CNN image classifiers are widely used, thanks to their efficiency and accuracy. However, they can suffer from biases that impede their practical applications. Most existing bias investigation techniques are either inapplicable to general image classification tasks or require significant user efforts in perusing all data subgroups to manually specify which data attributes to inspect. We present VisCUIT, an interactive visualization system that reveals how and why a CNN classifier is biased. VisCUIT visually summarizes the subgroups on which the classifier underperforms and helps users discover and characterize the cause of the underperformances by revealing image concepts responsible for activating neurons that contribute to misclassifications. VisCUIT runs in modern browsers and is open-source, allowing people to easily access and extend the tool to other model architectures and datasets. VisCUIT is available at the following public demo link: https://poloclub.github.io/VisCUIT. A video demo is available at https://youtu.be/eNDbSyM4R_4.
-
Obtaining annotations for large training sets is expensive, especially in settings where domain knowledge is required, such as behavior analysis. Weak supervision has been studied to reduce annotation costs by using weak labels from task-specific labeling functions (LFs) to augment ground truth labels. However, domain experts still need to hand-craft different LFs for different tasks, limiting scalability. To reduce expert effort, we present AutoSWAP: a framework for automatically synthesizing data-efficient task-level LFs. The key to our approach is to efficiently represent expert knowledge in a reusable domain-specific language and more general domain-level LFs, with which we use state-of-the-art program synthesis techniques and a small labeled dataset to generate task-level LFs. Additionally, we propose a novel structural diversity cost that allows for efficient synthesis of diverse sets of LFs, further improving AutoSWAP's performance. We evaluate AutoSWAP in three behavior analysis domains and demonstrate that AutoSWAP outperforms existing approaches using only a fraction of the data. Our results suggest that AutoSWAP is an effective way to automatically generate LFs that can significantly reduce expert effort for behavior analysis.
-
Transfer learning has become a popular method for leveraging pre-trained models in computer vision. However, without performing computationally expensive fine-tuning, it is difficult to quantify which pre-trained source models are suitable for a specific target task, or, conversely, to which tasks a pre-trained source model can be easily adapted to. In this work, we propose Gaussian Bhattacharyya Coefficient (GBC), a novel method for quantifying transferability between a source model and a target dataset. In a first step we embed all target images in the feature space defined by the source model, and represent them with per-class Gaussians. Then, we estimate their pairwise class separability using the Bhattacharyya coefficient, yielding a simple and effective measure of how well the source model transfers to the target task. We evaluate GBC on image classification tasks in the context of dataset and architecture selection. Further, we also perform experiments on the more complex semantic segmentation transferability estimation task. We demonstrate that GBC outperforms state-of-the-art transferability metrics on most evaluation criteria in the semantic segmentation settings, matches the performance of top methods for dataset transferability in image classification, and performs best on architecture selection problems for image classification.
-
Human action recognition has recently become one ofthe popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in thetask of video action recognition with competitive results.However, these methods have suffered some fundamentallimitations such as lack of robustness and generalization,e.g., how does the temporal ordering of video frames af-fect the recognition results? This work presents a novelend-to-end Transformer-based Directed Attention (Direc-Former) framework1for robust action recognition. The method takes a simple but novel perspective of Transformer-based approach to understand the right order of sequence actions. Therefore, the contributions of this work are three-fold. Firstly, we introduce the problem of ordered temporal learning issues to the action recognition problem. Secondly, a new Directed Attention mechanism is introduced to understand and provide attentions to human actions in the right order. Thirdly, we introduce the conditional dependency in action sequence modeling that includes orders and classes. The proposed approach consistently achieves the state-of-the-art (SOTA) results compared with the recent action recognition methods [4, 15, 62, 64], on three standard large-scale benchmarks, i.e. Jester, Kinetics-400 and Something-Something-V2.
-
Most self-supervised video representation learning approaches focus on action recognition. In contrast, in this paper we focus on self-supervised video learning for movie understanding and propose a novel hierarchical self-supervised pretraining strategy that separately pretrains each level of our hierarchical movie understanding model. Specifically, we propose to pretrain the low-level video backbone using a contrastive learning objective, while pretrain the higher-level video contextualizer using an event mask prediction task, which enables the usage of different data sources for pretraining different levels of the hierarchy. We first show that our self-supervised pretraining strategies are effective and lead to improved performance on all tasks and metrics on VidSitu benchmark (e.g., improving on semantic role prediction from 47% to 61% CIDEr scores). We further demonstrate the effectiveness of our contextualized event features on LVU tasks, both when used alone and when combined with instance features, showing their complementarity.
-
Social presence, the feeling of being there with a "real" person, will fuel the next generation of communication systems driven by digital humans in virtual reality (VR). The best 3D video-realistic VR avatars that minimize the uncanny effect rely on person-specific (PS) models. However, these PS models are time-consuming to build and are typically trained with limited data variability, which results in poor generalization and robustness. Major sources of variability that affects the accuracy of facial expression transfer algorithms include using different VR headsets (e.g., camera configuration, slop of the headset), facial appearance changes over time (e.g., beard, make-up), and environmental factors (e.g., lighting, backgrounds). This is a major drawback for the scalability of these models in VR. This paper makes progress in overcoming these limitations by proposing an end-to-end multi-identity architecture (MIA) trained with specialized augmentation strategies. MIA drives the shape component of the avatar from three cameras in the VR headset (two eyes, one mouth), in untrained subjects, using minimal personalized information (i.e., neutral 3D mesh shape). Similarly, if the PS texture decoder is available, MIA is able to drive the full avatar (shape+texture) robustly outperforming PS models in challenging scenarios. Our key contribution to improve robustness and generalization, is that our method implicitly decouples, in an unsupervised manner, the facial expression from nuisance factors (e.g., headset, environment, facial appearance). We demonstrate the superior performance and robustness of the proposed method versus state-of-the-art PS approaches in a variety of experiments.
-
As clean ImageNet accuracy nears its ceiling, the research community is increasingly more concerned about robust accuracy under distributional shifts. While a variety of methods have been proposed to robustify neural networks, these techniques often target models trained on ImageNet classification. At the same time, it is a common practice to use ImageNet pretrained backbones for downstream tasks such as object detection, semantic segmentation, and image classification from different domains. This raises a question: Can these robust image classifiers transfer robustness to downstream tasks? For object detection and semantic segmentation, we find that a vanilla Swin Transformer, a variant of Vision Transformer tailored for dense prediction tasks, transfers robustness better than Convolutional Neural Networks that are trained to be robust to the corrupted version of ImageNet. For CIFAR10 classification, we find that models that are robustified for ImageNet do not retain robustness when fully fine-tuned. These findings suggest that current robustification techniques tend to emphasize ImageNet evaluations. Moreover, network architecture is a strong source of robustness when we consider transfer learning.
-
Semi-supervised learning (SSL) is a method to make better models using a large number of easily accessible unlabeled data along with a small number of labeled data obtained at a high cost. Most of existing SSL studies focus on the cases where sufficient amount of labeled samples are available, tens to hundreds labeled samples for each class, which still requires a lot of labeling cost. In this paper, we focus on SSL environment with extremely scarce labeled samples, only 1 or 2 labeled samples per class, where most of existing methods fail to learn. We propose a propagation regularizer which can achieve efficient and effective learning with extremely scarce labeled samples by suppressing confirmation bias. In addition, for the realistic model selection in the absence of the validation dataset, we also propose a model selection method based on our propagation regularizer. The proposed methods show 70.9%, 30.3%, and 78.9% accuracy on CIFAR-10, CIFAR-100, SVHN dataset with just one labeled sample per class, which are improved by 8.9% to 120.2% compared to the existing approaches. And our proposed methods also show good performance on a higher resolution dataset, STL-10.
-
Driving 3D characters to dance following a piece of music is highly challenging due to the spatial constraints applied to poses by choreography norms. In addition, the generated dance sequence also needs to maintain temporal coherency with different music genres. To tackle these challenges, we propose a novel music-to-dance framework, Bailando, with two powerful components: 1) a choreographic memory that learns to summarize meaningful dancing units from 3D pose sequence to a quantized codebook, 2) an actor-critic Generative Pre-trained Transformer (GPT) that composes these units to a fluent dance coherent to the music. With the learned choreographic memory, dance generation is realized on the quantized units that meet high choreography standards, such that the generated dancing sequences are confined within the spatial constraints. To achieve synchronized alignment between diverse motion tempos and music beats, we introduce an actor-critic-based reinforcement learning scheme to the GPT with a newly-designed beat-align reward function. Extensive experiments on the standard benchmark demonstrate that our proposed framework achieves state-of-the-art performance both qualitatively and quantitatively. Notably, the learned choreographic memory is shown to discover human-interpretable dancing-style poses in an unsupervised manner.
-
This paper presents a Generative prior ReciprocAted Invertible rescaling Network (GRAIN) for generating faithful high-resolution (HR) images from low-resolution (LR) invertible images with an extreme upscaling factor (64x). Previous researches have leveraged the prior knowledge of a pretrained GAN model to generate high-quality upscaling results. However, they fail to produce pixel-accurate results due to the highly ambiguous extreme mapping process. We remedy this problem by introducing a reciprocated invertible image rescaling process, in which high-resolution information can be delicately embedded into an invertible low-resolution image and generative prior for a faithful HR reconstruction. In particular, the invertible LR features not only carry significant HR semantics, but also are trained to predict scale-specific latent codes, yielding a preferable utilization of generative features. On the other hand, the enhanced generative prior is re-injected to the rescaling process, compensating the lost details of the invertible rescaling. Our reciprocal mechanism perfectly integrates the advantages of invertible encoding and generative prior, leading to the first feasible extreme rescaling solution. Extensive experiments demonstrate superior performance against state-of-the-art upscaling methods. Code is available at https://github.com/cszzx/GRAIN.
-
Transformer-based methods have achieved great success in the field of human-object interaction (HOI) detection. However, these models tend to adopt semantically ambiguous queries, which lowers the transformer's representation learning power. Moreover, there are a very limited number of labeled human-object pairs for most images in existing datasets, which constrains the transformer's set prediction power. To handle the first problem, we propose an efficient knowledge distillation model, named Distillation using Oracle Queries (DOQ), which shares parameters between teacher and student networks. The teacher network adopts oracle queries that are semantically clear and generates high-quality decoder embeddings. By mimicking both the attention maps and decoder embeddings of the teacher network, the representation learning power of the student network is significantly promoted. To address the second problem, we introduce an efficient data augmentation method, named Context-Consistent Stitching (CCS), which generates complicated images online. Each new image is obtained by stitching labeled human-object pairs cropped from multiple training images. By selecting source images with similar context, the new synthesized image is made visually realistic. Our methods significantly promote both the accuracy and training efficiency of transformer-based HOI detection models. Experimental results show that our proposed approach consistently outperforms state-of-the-art methods on three benchmarks: HICO-DET, HOI-A, and V-COCO. Code will be released soon.
-
Prototypical methods have recently gained a lot of attention due to their intrinsic interpretable nature, which is obtained through the prototypes. With growing use cases of model reuse and distillation, there is a need to also study transfer of interpretability from one model to another. We present Proto2Proto, a novel method to transfer interpretability of one prototypical part network to another via knowledge distillation. Our approach aims to add interpretability to the "dark" knowledge transferred from the teacher to the shallower student model. We propose two novel losses: "Global Explanation" loss and "Patch-Prototype Correspondence" loss to facilitate such a transfer. Global Explanation loss forces the student prototypes to be close to teacher prototypes, and Patch-Prototype Correspondence loss enforces the local representations of the student to be similar to that of the teacher. Further, we propose three novel metrics to evaluate the student's proximity to the teacher as measures of interpretability transfer in our settings. We qualitatively and quantitatively demonstrate the effectiveness of our method on CUB-200-2011 and Stanford Cars datasets. Our experiments show that the proposed method indeed achieves interpretability transfer from teacher to student while simultaneously exhibiting competitive performance. The code is available at https://github.com/archmaester/proto2proto
-
This paper studies the problem of multi-person pose estimation in a bottom-up fashion. With a new and strong observation that the localization issue of the center-offset formulation can be remedied in a local-window search scheme in an ideal situation, we propose a multi-person pose estimation approach, dubbed as LOGO-CAP, by learning the LOcal-GlObal Contextual Adaptation for human Pose. Specifically, our approach learns the keypoint attraction maps (KAMs) from the local keypoints expansion maps (KEMs) in small local windows in the first step, which are subsequently treated as dynamic convolutional kernels on the keypoints-focused global heatmaps for contextual adaptation, achieving accurate multi-person pose estimation. Our method is end-to-end trainable with near real-time inference speed in a single forward pass, obtaining state-of-the-art performance on the COCO keypoint benchmark for bottom-up human pose estimation. With the COCO trained model, our method also outperforms prior arts by a large margin on the challenging OCHuman dataset.
-
In this paper, we take an early step towards video representation learning of human actions with the help of largescale synthetic videos, particularly for human motion representation enhancement. Specifically, we first introduce an automatic action-related video synthesis pipeline based on a photorealistic video game. A large-scale human action dataset named GATA (GTA Animation Transformed Actions) is then built by the proposed pipeline, which includes 8.1 million action clips spanning over 28K action classes. Based on the presented dataset, we design a contrastive learning framework for human motion representation learning, which shows significant performance improvements on several typical video datasets for action recognition, e.g., Charades, HAA 500 and NTU-RGB. Besides, we further explore a domain adaptation method based on cross-domain positive pairs mining to alleviate the domain gap between synthetic and realistic data. Extensive properties analyses of learned representation are conducted to demonstrate the effectiveness of the proposed dataset for enhancing human motion representation learning.
-
As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it inappropriate for layout-specific applications, e.g., face recognition and medical image segmentation. We observe that these applications naturally exhibit the characteristics of large intra-image (spatial) variance and small cross-image variance. This observation motivates our efficient translation variant convolution (TVConv) for layout-aware visual processing. Technically, TVConv is composed of affinity maps and a weight-generating block. While affinity maps depict pixel-paired relationships gracefully, the weight-generating block can be explicitly overparameterized for better training while maintaining efficient inference. Although conceptually simple, TVConv significantly improves the efficiency of the convolution and can be readily plugged into various network architectures. Extensive experiments on face recognition show that TVConv reduces the computational cost by up to 3.1x and improves the corresponding throughput by 2.3x while maintaining a high accuracy compared to the depthwise convolution. Moreover, for the same computation cost, we boost the mean accuracy by up to 4.21%. We also conduct experiments on the optic disc/cup segmentation task and obtain better generalization performance, which helps mitigate the critical data scarcity issue. Code is available at https://github.com/JierunChen/TVConv.
-
Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super-resolution (SR) models trained on images from different devices. In this paper, we investigate a novel and practical task coded cross-device SR, which strives to adapt a real-world SR model trained on the paired images captured by one camera to low-resolution (LR) images captured by arbitrary target devices. The proposed task is highly challenging due to the absence of paired data from various imaging devices. To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera. DADA employs the Domain-Invariant Attention (DIA) module to establish the basis of target model training even without HR supervision. Furthermore, the dual framework of DADA facilitates an Inter-domain Adversarial Adaptation (InterAA) in one branch for two LR input images from two domains, and an Intra-domain Adversarial Adaptation (IntraAA) in two branches for an LR input image. InterAA and IntraAA together improve the model transferability from the source domain to the target. We empirically conduct experiments under six Real to Real adaptation settings among three different cameras, and achieve superior performance compared with existing state-of-the-art approaches. We also evaluate the proposed DADA to address the adaptation to the video camera, which presents a promising research topic to promote the wide applications of real-world super-resolution. Our source code is publicly available at https://github.com/lonelyhope/DADA.git.
-
6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity object CAD models. In this work, we study a new open set problem; the few-shot 6D object poses estimation: estimating the 6D pose of an unknown object by a few support views without extra training. To tackle the problem, we point out the importance of fully exploring the appearance and geometric relationship between the given support views and query scene patches and propose a dense prototypes matching framework by extracting and matching dense RGBD prototypes with transformers. Moreover, we show that the priors from diverse appearances and shapes are crucial to the generalization capability under the problem setting and thus propose a large-scale RGBD photorealistic dataset (ShapeNet6D) for network pre-training. A simple and effective online texture blending approach is also introduced to eliminate the domain gap from the synthesis dataset, which enriches appearance diversity at a low cost. Finally, we discuss possible solutions to this problem and establish benchmarks on popular datasets to facilitate future research.
-
We present a large-scale study of imitating human demonstrations on tasks that require a virtual robot to search for objects in new environments - (1) ObjectGoal Navigation (e.g. 'find & go to a chair') and (2) Pick&Place (e.g. 'find mug, pick mug, find counter, place mug on counter'). First, we develop a virtual teleoperation data-collection infrastructure - connecting Habitat simulator running in a web browser to Amazon Mechanical Turk, allowing remote users to teleoperate virtual robots, safely and at scale. We collect 80k demonstrations for ObjectNav and 12k demonstrations for Pick&Place, which is an order of magnitude larger than existing human demonstration datasets in simulation or on real robots. Our virtual teleoperation data contains 29.3M actions, and is equivalent to 22.6k hours of real-world teleoperation time, and illustrates rich, diverse strategies for solving the tasks. Second, we use this data to answer the question - how does large-scale imitation learning (IL) (which has not been hitherto possible) compare to reinforcement learning (RL) (which is the status quo)? On ObjectNav, we find that IL (with no bells or whistles) using 70k human demonstrations outperforms RL using 240k agent-gathered trajectories. This effectively establishes an 'exchange rate' - a single human demonstration appears to be worth 4 agent-gathered ones. More importantly, we find the IL-trained agent learns efficient object-search behavior from humans - it peeks into rooms, checks corners for small objects, turns in place to get a panoramic view - none of these are exhibited as prominently by the RL agent, and to induce these behaviors via contemporary RL techniques would require tedious reward engineering. Finally, accuracy vs. training data size plots show promising scaling behavior, suggesting that simply collecting more demonstrations is likely to advance the state of art further. On Pick&Place, the comparison is starker - IL agents achieve 18% success on episodes with new object-receptacle locations when trained with 9.5k human demonstrations, while RL agents fail to get beyond 0%. Overall, our work provides compelling evidence for investing in large-scale imitation learning. Project page: https://ram81.github.io/projects/habitat-web.
-
The estimation of the relative pose of two camera views is a fundamental problem in computer vision. Kneip et al. proposed to solve this problem by introducing the normal epipolar constraint (NEC). However, their approach does not take into account uncertainties, so that the accuracy of the estimated relative pose is highly dependent on accurate feature positions in the target frame. In this work, we introduce the probabilistic normal epipolar constraint (PNEC) that overcomes this limitation by accounting for anisotropic and inhomogeneous uncertainties in the feature positions. To this end, we propose a novel objective function, along with an efficient optimization scheme that effectively minimizes our objective while maintaining real-time performance. In experiments on synthetic data, we demonstrate that the novel PNEC yields more accurate rotation estimates than the original NEC and several popular relative rotation estimation algorithms. Furthermore, we integrate the proposed method into a state-of-the-art monocular rotation-only odometry system and achieve consistently improved results for the real-world KITTI dataset.
-
Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves cross-modal interaction between the two modalities: vision and language, since text is the written form of language. Concretely, we propose to learn contextualized, joint representations through vision-language pre-training, for the sake of enhancing the performance of scene text detectors. Towards this end, we devise a pre-training architecture with an image encoder, a text encoder and a cross-modal encoder, as well as three pretext tasks: image-text contrastive learning (ITC), masked language modeling (MLM) and word-in-image prediction (WIP). The pre-trained model is able to produce more informative representations with richer semantics, which could readily benefit existing scene text detectors (such as EAST and PSENet) in the down-stream text detection task. Extensive experiments on standard benchmarks demonstrate that the proposed paradigm can significantly improve the performance of various representative text detectors, outperforming previous pre-training approaches. The code and pre-trained models will be publicly released.
-
The inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific orientation. Discovering such symmetry patterns from an image thus benefits from an equivariant feature representation, which varies consistently with reflection and rotation of the image. In this work, we introduce a group-equivariant convolutional network for symmetry detection, dubbed EquiSym, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation. The proposed network is built end-to-end with dihedrally-equivariant layers and trained to output a spatial map for reflection axes or rotation centers. We also present a new dataset, DENse and DIverse symmetry (DENDI), which mitigates limitations of existing benchmarks for reflection and rotation symmetry detection. Experiments show that our method achieves the state of the arts in symmetry detection on LDRS and DENDI datasets.
-
In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can adaptively leverage the cluster assumption and consistency regularization of the unlabeled data according to the current learning status. This strategy can adaptively generate one-hot "hard" labels converted from task model predictions for better task model training. (2) For the unselected unlabeled images with low confidence, we introduce an Active learning (AL) algorithm to find the informative samples as the annotation candidates by exploiting virtual adversarial perturbation and model's density-aware entropy. These informative candidates are subsequently fed into the next training cycle for better SSL label propagation. Notably, the adaptive pseudo-labeling and informative active annotation form a learning closed-loop that are mutually collaborative to boost medical image SSL. To verify the effectiveness of the proposed method, we collected a metastatic epidural spinal cord compression (MESCC) dataset that aims to optimize MESCC diagnosis and classification for improved specialist referral and treatment. We conducted an extensive experimental study of BoostMIS on MESCC and another public dataset COVIDx. The experimental results verify our framework's effectiveness and generalisability for different medical image datasets with a significant improvement over various state-of-the-art methods.
-
Contrastive language image pretraining (CLIP) encoders have been shown to be beneficial for a range of visual tasks from classification and detection to captioning and image manipulation. We investigate the effectiveness of CLIP visual backbones for Embodied AI tasks. We build incredibly simple baselines, named EmbCLIP, with no task specific architectures, inductive biases (such as the use of semantic maps), auxiliary tasks during training, or depth maps--yet we find that our improved baselines perform very well across a range of tasks and simulators. EmbCLIP tops the RoboTHOR ObjectNav leaderboard by a huge margin of 20 pts (Success Rate). It tops the iTHOR 1-Phase Rearrangement leaderboard, beating the next best submission, which employs Active Neural Mapping, and more than doubling the % Fixed Strict metric (0.08 to 0.17). It also beats the winners of the 2021 Habitat ObjectNav Challenge, which employ auxiliary tasks, depth maps, and human demonstrations, and those of the 2019 Habitat PointNav Challenge. We evaluate the ability of CLIP's visual representations at capturing semantic information about input observations--primitives that are useful for navigation-heavy embodied tasks--and find that CLIP's representations encode these primitives more effectively than ImageNet-pretrained backbones. Finally, we extend one of our baselines, producing an agent capable of zero-shot object navigation that can navigate to objects that were not used as targets during training. Our code and models are available at https://github.com/allenai/embodied-clip.
-
Recently, Vision Transformers (ViT), with the self-attention (SA) as the de facto ingredients, have demonstrated great potential in the computer vision community. For the sake of trade-off between efficiency and performance, a group of works merely perform SA operation within local patches, whereas the global contextual information is abandoned, which would be indispensable for visual recognition tasks. To solve the issue, the subsequent global-local ViTs take a stab at marrying local SA with global one in parallel or alternative way in the model. Nevertheless, the exhaustively combined local and global context may exist redundancy for various visual data, and the receptive field within each layer is fixed. Alternatively, a more graceful way is that global and local context can adaptively contribute per se to accommodate different visual data. To achieve this goal, we in this paper propose a novel ViT architecture, termed NomMer, which can dynamically Nominate the synergistic global-local context in vision transforMer. By investigating the working pattern of our proposed NomMer, we further explore what context information is focused. Beneficial from this "dynamic nomination" mechanism, without bells and whistles, the NomMer can not only achieve 84.5% Top-1 classification accuracy on ImageNet with only 73M parameters, but also show promising performance on dense prediction tasks, i.e., object detection and semantic segmentation. The code and models are publicly available at https://github.com/TencentYoutuResearch/VisualRecognition-NomMer.
-
We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences collected by 9 participants interacting with 800 different object instances from 16 categories over 610 different indoor rooms. Frame-wise annotations for panoptic segmentation, motion segmentation, 3D hand pose, category-level object pose and hand action have also been provided, together with reconstructed object meshes and scene point clouds. With HOI4D, we establish three benchmarking tasks to promote category-level HOI from 4D visual signals including semantic segmentation of 4D dynamic point cloud sequences, category-level object pose tracking, and egocentric action segmentation with diverse interaction targets. In-depth analysis shows HOI4D poses great challenges to existing methods and produces huge research opportunities.
-
Grounded situation recognition is the task of predicting the main activity, entities playing certain roles within the activity, and bounding-box groundings of the entities in the given image. To effectively deal with this challenging task, we introduce a novel approach where the two processes for activity classification and entity estimation are interactive and complementary. To implement this idea, we propose Collaborative Glance-Gaze TransFormer (CoFormer) that consists of two modules: Glance transformer for activity classification and Gaze transformer for entity estimation. Glance transformer predicts the main activity with the help of Gaze transformer that analyzes entities and their relations, while Gaze transformer estimates the grounded entities by focusing only on the entities relevant to the activity predicted by Glance transformer. Our CoFormer achieves the state of the art in all evaluation metrics on the SWiG dataset. Training code and model weights are available at https://github.com/jhcho99/CoFormer.
-
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks. Despite the prevalence, current Rep methods simply re-parameterize all operations into an augmented network, including those that rarely contribute to the model's performance. As such, the price to pay is an expensive computational overhead to manipulate these unnecessary behaviors. To eliminate the above caveats, we aim to bootstrap the training with minimal cost by devising a dynamic re-parameterization (DyRep) method, which encodes Rep technique into the training process that dynamically evolves the network structures. Concretely, our proposal adaptively finds the operations which contribute most to the loss in the network, and applies Rep to enhance their representational capacity. Besides, to suppress the noisy and redundant operations introduced by Rep, we devise a de-parameterization technique for a more compact re-parameterization. With this regard, DyRep is more efficient than Rep since it smoothly evolves the given network instead of constructing an over-parameterized network. Experimental results demonstrate our effectiveness, e.g., DyRep improves the accuracy of ResNet-18 by 2.04% on ImageNet and reduces 22% runtime over the baseline.
-
Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data. To reduce the labels dependency, various active learning strategies have been proposed, typically based on the confidence of the detector. However, these methods are biased towards high-performing classes and can lead to acquired datasets that are not good representatives of the testing set data. In this work, we propose a unified framework for active learning, that considers both the uncertainty and the robustness of the detector, ensuring that the network performs well in all classes. Furthermore, our method leverages auto-labeling to suppress a potential distribution drift while boosting the performance of the model. Experiments on PASCAL VOC07+12 and MS-COCO show that our method consistently outperforms a wide range of active learning methods, yielding up to a 7.7% improvement in mAP, or up to 82% reduction in labeling cost. Code will be released upon acceptance of the paper.
-
In this paper, we tackle the problem of category-level 9D pose estimation in the wild, given a single RGB-D frame. Using supervised data of real-world 9D poses is tedious and erroneous, and also fails to generalize to unseen scenarios. Besides, category-level pose estimation requires a method to be able to generalize to unseen objects at test time, which is also challenging. Drawing inspirations from traditional point pair features (PPFs), in this paper, we design a novel Category-level PPF (CPPF) voting method to achieve accurate, robust and generalizable 9D pose estimation in the wild. To obtain robust pose estimation, we sample numerous point pairs on an object, and for each pair our model predicts necessary SE(3)-invariant voting statistics on object centers, orientations and scales. A novel coarse-to-fine voting algorithm is proposed to eliminate noisy point pair samples and generate final predictions from the population. To get rid of false positives in the orientation voting process, an auxiliary binary disambiguating classification task is introduced for each sampled point pair. In order to detect objects in the wild, we carefully design our sim-to-real pipeline by training on synthetic point clouds only, unless objects have ambiguous poses in geometry. Under this circumstance, color information is leveraged to disambiguate these poses. Results on standard benchmarks show that our method is on par with current state of the arts with real-world training data. Extensive experiments further show that our method is robust to noise and gives promising results under extremely challenging scenarios. Our code is available on https://github.com/qq456cvb/CPPF.
-
Unsupervised domain adaptive video action recognition aims to recognize actions of a target domain using a model trained with only out-of-domain (source) annotations. The inherent complexity of videos makes this task challenging but also provides ground for leveraging multi-modal inputs (e.g., RGB, Flow, Audio). Most previous works utilize the multi-modal information by either aligning each modality individually or learning representation via cross-modal self-supervision. Different from previous works, we find that the cross-domain alignment can be more effectively done by using cross-modal interaction first. Cross-modal knowledge interaction allows other modalities to supplement missing transferable information because of the cross-modal complementarity. Also, the most transferable aspects of data can be highlighted using cross-modal consensus. In this work, we present a novel model that jointly considers these two characteristics for domain adaptive action recognition. We achieve this by implementing two modules, where the first module exchanges complementary transferable information across modalities through the semantic space, and the second module finds the most transferable spatial region based on the consensus of all modalities. Extensive experiments validate that our proposed method can significantly outperform the state-of-the-art methods on multiple benchmark datasets, including the complex fine-grained dataset EPIC-Kitchens-100.
-
Learning visual concepts from raw images without strong supervision is a challenging task. In this work, we show the advantages of prototype representations for understanding and revising the latent space of neural concept learners. For this purpose, we introduce interactive Concept Swapping Networks (iCSNs), a novel framework for learning concept-grounded representations via weak supervision and implicit prototype representations. iCSNs learn to bind conceptual information to specific prototype slots by swapping the latent representations of paired images. This semantically grounded and discrete latent space facilitates human understanding and human-machine interaction. We support this claim by conducting experiments on our novel data set "Elementary Concept Reasoning" (ECR), focusing on visual concepts shared by geometric objects.
-
The objective of human parsing is to partition a human in an image into constituent parts. This task involves labeling each pixel of the human image according to the classes. Since the human body comprises hierarchically structured parts, each body part of an image can have its sole position distribution characteristic. Probably, a human head is less likely to be under the feet, and arms are more likely to be near the torso. Inspired by this observation, we make instance class distributions by accumulating the original human parsing label in the horizontal and vertical directions, which can be utilized as supervision signals. Using these horizontal and vertical class distribution labels, the network is guided to exploit the intrinsic position distribution of each class. We combine two guided features to form a spatial guidance map, which is then superimposed onto the baseline network by multiplication and concatenation to distinguish the human parts precisely. We conducted extensive experiments to demonstrate the effectiveness and superiority of our method on three well-known benchmarks: LIP, ATR, and CIHP databases.
-
This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach. Direct optimization, by gradient descent, of an evaluation metric, is not possible when it is non-differentiable, which is the case for recall in retrieval. A differentiable surrogate loss for the recall is proposed in this work. Using an implementation that sidesteps the hardware constraints of the GPU memory, the method trains with a very large batch size, which is essential for metrics computed on the entire retrieval database. It is assisted by an efficient mixup regularization approach that operates on pairwise scalar similarities and virtually increases the batch size further. The suggested method achieves state-of-the-art performance in several image retrieval benchmarks when used for deep metric learning. For instance-level recognition, the method outperforms similar approaches that train using an approximation of average precision.
-
We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. This task, which is often applied to novel view synthesis, is recently revolutionized by Neural Radiance Field (NeRF) for its state-of-the-art quality and flexibility. However, NeRF and its variants require a lengthy training time ranging from hours to days for a single scene. In contrast, our approach achieves NeRF-comparable quality and converges rapidly from scratch in less than 15 minutes with a single GPU. We adopt a representation consisting of a density voxel grid for scene geometry and a feature voxel grid with a shallow network for complex view-dependent appearance. Modeling with explicit and discretized volume representations is not new, but we propose two simple yet non-trivial techniques that contribute to fast convergence speed and high-quality output. First, we introduce the post-activation interpolation on voxel density, which is capable of producing sharp surfaces in lower grid resolution. Second, direct voxel density optimization is prone to suboptimal geometry solutions, so we robustify the optimization process by imposing several priors. Finally, evaluation on five inward-facing benchmarks shows that our method matches, if not surpasses, NeRF's quality, yet it only takes about 15 minutes to train from scratch for a new scene. We will make our code publicly available.
-
Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems are running in non-stationary and continually changing environments where the target domain distribution can change over time. Existing methods, which are mostly based on self-training and entropy regularization, can suffer from these non-stationary environments. Due to the distribution shift over time in the target domain, pseudo-labels become unreliable. The noisy pseudo-labels can further lead to error accumulation and catastrophic forgetting. To tackle these issues, we propose a continual test-time adaptation approach (CoTTA) which comprises two parts. Firstly, we propose to reduce the error accumulation by using weight-averaged and augmentation-averaged predictions which are often more accurate. On the other hand, to avoid catastrophic forgetting, we propose to stochastically restore a small part of the neurons to the source pre-trained weights during each iteration to help preserve source knowledge in the long-term. The proposed method enables the long-term adaptation for all parameters in the network. CoTTA is easy to implement and can be readily incorporated in off-the-shelf pre-trained models. We demonstrate the effectiveness of our approach on four classification tasks and a segmentation task for continual test-time adaptation, on which we outperform existing methods. Our code is available at https://qin.ee/cotta.
-
Retinex model-based methods have shown to be effective in layer-wise manipulation with well-designed priors for low-light image enhancement. However, the commonly used hand-crafted priors and optimization-driven solutions lead to the absence of adaptivity and efficiency. To address these issues, in this paper, we propose a Retinex-based deep unfolding network (URetinex-Net), which unfolds an optimization problem into a learnable network to decompose a low-light image into reflectance and illumination layers. By formulating the decomposition problem as an implicit priors regularized model, three learning-based modules are carefully designed, responsible for data-dependent initialization, high-efficient unfolding optimization, and user-specified illumination enhancement, respectively. Particularly, the proposed unfolding optimization module, introducing two networks to adaptively fit implicit priors in data-driven manner, can realize noise suppression and details preservation for the final decomposition results. Extensive experiments on real-world low-light images qualitatively and quantitatively demonstrate the effectiveness and superiority of the proposed method over state-of-the-art methods.
-
Recent years have witnessed significant progress in the area of single image dehazing, thanks to the employment of deep neural networks and diverse datasets. Most of the existing methods perform well when the training and testing are conducted on a single dataset. However, they are not able to handle different types of hazy images using a dehazing model trained on a particular dataset. One possible remedy is to perform training on multiple datasets jointly. However, we observe that this training strategy tends to compromise the model performance on individual datasets. Motivated by this observation, we propose a test-time training method which leverages a helper network to assist the dehazing model in better adapting to a domain of interest. Specifically, during the test time, the helper network evaluates the quality of the dehazing results, then directs the dehazing network to improve the quality by adjusting its parameters via self-supervision. Nevertheless, the inclusion of the helper network does not automatically ensure the desired performance improvement. For this reason, a meta-learning approach is employed to make the objectives of the dehazing and helper networks consistent with each other. We demonstrate the effectiveness of the proposed method by providing extensive supporting experiments.
-
The reconstruction of cortical surfaces from brain magnetic resonance imaging (MRI) scans is essential for quantitative analyses of cortical thickness and sulcal morphology. Although traditional and deep learning-based algorithmic pipelines exist for this purpose, they have two major drawbacks: lengthy runtimes of multiple hours (traditional) or intricate post-processing, such as mesh extraction and topology correction (deep learning-based). In this work, we address both of these issues and propose Vox2Cortex, a deep learning-based algorithm that directly yields topologically correct, three-dimensional meshes of the boundaries of the cortex. Vox2Cortex leverages convolutional and graph convolutional neural networks to deform an initial template to the densely folded geometry of the cortex represented by an input MRI scan. We show in extensive experiments on three brain MRI datasets that our meshes are as accurate as the ones reconstructed by state-of-the-art methods in the field, without the need for time- and resource-intensive post-processing. To accurately reconstruct the tightly folded cortex, we work with meshes containing about 168,000 vertices at test time, scaling deep explicit reconstruction methods to a new level.
-
Multi-view clustering has been shown to boost clustering performance by effectively mining the complementary information from multiple views. However, we observe that learning from data with more views is not guaranteed to achieve better clustering performance than from data with fewer views. To address this issue, we propose a general deep learning based framework that is guaranteed to reduce the risk of performance degradation caused by view increase. Concretely, the model is trained to simultaneously extract complementary information and discard the meaningless noise by automatically selecting features. These two learning procedures are incorporated into one unified framework by the proposed optimization objective. In theory, the empirical clustering risk of the model is no higher than learning from data before the view increase and data of the new increased single view. Also, the expected clustering risk of the model under divergence-based loss is no higher than that with high probability. Comprehensive experiments on benchmark datasets demonstrate the effectiveness and superiority of the proposed framework in achieving safe multi-view clustering.
-
Fine-grained image classification is a challenging computer vision task where various species share similar visual appearances, resulting in misclassification if merely based on visual clues. Therefore, it is helpful to leverage additional information, e.g., the locations and dates for data shooting, which can be easily accessible but rarely exploited. In this paper, we first demonstrate that existing multimodal methods fuse multiple features only on a single dimension, which essentially has insufficient help in feature discrimination. To fully explore the potential of multimodal information, we propose a dynamic MLP on top of the image representation, which interacts with multimodal features at a higher and broader dimension. The dynamic MLP is an efficient structure parameterized by the learned embeddings of variable locations and dates. It can be regarded as an adaptive nonlinear projection for generating more discriminative image representations in visual tasks. To our best knowledge, it is the first attempt to explore the idea of dynamic networks to exploit multimodal information in fine-grained image classification tasks. Extensive experiments demonstrate the effectiveness of our method. The t-SNE algorithm visually indicates that our technique improves the recognizability of image representations that are visually similar but with different categories. Furthermore, among published works across multiple fine-grained datasets, dynamic MLP consistently achieves SOTA results and takes third place in the iNaturalist challenge at FGVC8. Code is available at https://github.com/megvii-research/DynamicMLPForFinegrained.
-
Capsule networks are designed to present the objects by a set of parts and their relationships, which provide an insight into the procedure of visual perception. Although recent works have shown the success of capsule networks on simple objects like digits, the human faces with homologous structures, which are suitable for capsules to describe, have not been explored. In this paper, we propose a Hierarchical Parsing Capsule Network (HP-Capsule) for unsupervised face subpart-part discovery. When browsing large-scale face images without labels, the network first encodes the frequently observed patterns with a set of explainable subpart capsules. Then, the subpart capsules are assembled into part-level capsules through a Transformer-based Parsing Module (TPM) to learn the compositional relations between them. During training, as the face hierarchy is progressively built and refined, the part capsules adaptively encode the face parts with semantic consistency. HP-Capsule extends the application of capsule networks from digits to human faces and takes a step forward to show how the neural networks understand homologous objects without human intervention. Besides, HP-Capsule gives unsupervised face segmentation results by the covered regions of part capsules, enabling qualitative and quantitative evaluation. Experiments on BP4D and Multi-PIE datasets show the effectiveness of our method.
-
We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D scene. Unlike the 2D-question answering of VQA, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail the object identification from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, named ScanQA model, where the model learns a fused descriptor from 3D object proposals and encoded sentence embeddings. This learned descriptor correlates the language expressions with the underlying geometric features of the 3D scan and facilitates the regression of 3D bounding boxes to determine described objects in textual questions. We collected human-edited question-answer pairs with free-form answers that are grounded to 3D objects in each 3D scene. Our new ScanQA dataset contains over 40K question-answer pairs from the 800 indoor scenes drawn from the ScanNet dataset. To the best of our knowledge, ScanQA is the first large-scale effort to perform object-grounded question-answering in 3D environments.
-
Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding. One limitation of existing solutions is that they capture relevant knowledge from text-only knowledge bases, which merely contain facts expressed by first-order predicates or language descriptions while lacking complex but indispensable multimodal knowledge for visual understanding. How to construct vision-relevant and explainable multimodal knowledge for the VQA scenario has been less studied. In this paper, we propose MuKEA to represent multimodal knowledge by an explicit triplet to correlate visual objects and fact answers with implicit relations. To bridge the heterogeneous gap, we propose three objective losses to learn the triplet representations from complementary views: embedding structure, topological relation and semantic space. By adopting a pre-training and fine-tuning learning strategy, both basic and domain-specific multimodal knowledge are progressively accumulated for answer prediction. We outperform the state-of-the-art by 3.35% and 6.08% respectively on two challenging knowledge-required datasets: OK-VQA and KRVQA. Experimental results prove the complementary benefits of the multimodal knowledge with existing knowledge bases and the advantages of our end-to-end framework over the existing pipeline methods. The code is available at https://github.com/AndersonStra/MuKEA.
-
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and provides a principled way to maintain the representations of old models while adjusting to new tasks effectively. The proposed method estimates the relationship between the representation changes and the resulting loss increases incurred by model updates. It minimizes the upper bound of the loss increases using the representations, which exploits the estimated importance of each feature map within a backbone model. Based on the importance, the model restricts updates of important features for robustness while allowing changes in less critical features for flexibility. This optimization strategy effectively alleviates the notorious catastrophic forgetting problem despite the limited accessibility of data in the previous tasks. The experimental results show significant accuracy improvement of the proposed algorithm over the existing methods on the standard datasets. Code is available
-
In this paper, we are interested in modeling a how-to instructional procedure, such as a cooking recipe, with a meaningful and rich high-level representation. Specifically, we propose to represent cooking recipes and food images as cooking programs. Programs provide a structured representation of the task, capturing cooking semantics and sequential relationships of actions in the form of a graph. This allows them to be easily manipulated by users and executed by agents. To this end, we build a model that is trained to learn a joint embedding between recipes and food images via self-supervision and jointly generate a program from this embedding as a sequence. To validate our idea, we crowdsource programs for cooking recipes and show that: (a) projecting the image-recipe embeddings into programs leads to better cross-modal retrieval results; (b) generating programs from images leads to better recognition results compared to predicting raw cooking instructions; and (c) we can generate food images by manipulating programs via optimizing the latent code of a GAN. Code, data, and models are available online.
-
Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between meshes that have a certain degree of deformation. Existing methods either consider the local description of sampled points or discover correspondences based on global shape information. In this work, we investigate a hierarchical learning design, to which we incorporate local patch-level information and global shape-level structures. This flexible representation enables correspondence prediction and provides rich features for the matching stage. Finally, we propose a novel optimal transport solver by recurrently updating features on non-confident nodes to learn globally consistent correspondences between the shapes. Our results on publicly available datasets suggest robust performance in presence of severe deformations without the need of extensive training or refinement.
-
Outside-knowledge visual question answering (OK-VQA) requires the agent to comprehend the image, make use of relevant knowledge from the entire web, and digest all the information to answer the question. Most previous works address the problem by first fusing the image and question in the multi-modal space, which is inflexible for further fusion with a vast amount of external knowledge. In this paper, we call for an alternative paradigm for the OK-VQA task, which transforms the image into plain text, so that we can enable knowledge passage retrieval, and generative question-answering in the natural language space. This paradigm takes advantage of the sheer volume of gigantic knowledge bases and the richness of pre-trained language models. A Transform-Retrieve-Generate framework (TRiG) framework is proposed, which can be plug-and-played with alternative image-to-text models and textual knowledge bases. Experimental results show that our TRiG framework outperforms all state-of-the-art supervised methods by at least 11.1% absolute margin.
-
Federated Learning (FL) fuses collaborative models from local nodes without centralizing users' data. The permutation invariance property of neural networks and the non-i.i.d. data across clients make the locally updated parameters imprecisely aligned, disabling the coordinate-based parameter averaging. Traditional neurons do not explicitly consider position information. Hence, we propose Position-Aware Neurons (PANs) as an alternative, fusing position-related values (i.e., position encodings) into neuron outputs. PANs couple themselves to their positions and minimize the possibility of dislocation, even updating on heterogeneous data. We turn on/off PANs to disable/enable the permutation invariance property of neural networks. PANs are tightly coupled with positions when applied to FL, making parameters across clients pre-aligned and facilitating coordinate-based parameter averaging. PANs are algorithm-agnostic and could universally improve existing FL algorithms. Furthermore, "FL with PANs" is simple to implement and computationally friendly.
-
Learning visual representation of high quality is essential for image classification. Recently, a series of contrastive representation learning methods have achieved preeminent success. Particularly, SupCon outperformed the dominant methods based on cross-entropy loss in representation learning. However, we notice that there could be potential ethical risks in supervised contrastive learning. In this paper, we for the first time analyze unfairness caused by supervised contrastive learning and propose a new Fair Supervised Contrastive Loss (FSCL) for fair visual representation learning. Inheriting the philosophy of supervised contrastive learning, it encourages representation of the same class to be closer to each other than that of different classes, while ensuring fairness by penalizing the inclusion of sensitive attribute information in representation. In addition, we introduce a group-wise normalization to diminish the disparities of intra-group compactness and inter-class separability between demographic groups that arouse unfair classification. Through extensive experiments on CelebA and UTK Face, we validate that the proposed method significantly outperforms SupCon and existing state-of-the-art methods in terms of the trade-off between top-1 accuracy and fairness. Moreover, our method is robust to the intensity of data bias and effectively works in incomplete supervised settings. Our code is available at https://github.com/sungho-CoolG/FSCL
-
Visual Emotion Analysis (VEA) is attracting increasing attention. One of the biggest challenges of VEA is to bridge the affective gap between visual clues in a picture and the emotion expressed by the picture. As the granularity of emotions increases, the affective gap increases as well. Existing deep approaches try to bridge the gap by directly learning discrimination among emotions globally in one shot without considering the hierarchical relationship among emotions at different affective levels and the affective level of emotions to be classified. In this paper, we present the Multi-level Dependent Attention Network (MDAN) with two branches, to leverage the emotion hierarchy and the correlation between different affective levels and semantic levels. The bottom-up branch directly learns emotions at the highest affective level and strictly follows the emotion hierarchy while predicting emotions at lower affective levels. In contrast, the top-down branch attempt to disentangle the affective gap by one-to-one mapping between semantic levels and affective levels, namely, Affective Semantic Mapping. At each semantic level, a local classifier learns discrimination among emotions at the corresponding affective level. Finally, We integrate global learning and local learning into a unified deep framework and optimize the network simultaneously. Moreover, to properly extract and leverage channel dependencies and spatial attention while disentangling the affective gap, we carefully designed two attention modules: the Multi-head Cross Channel Attention module and the Level-dependent Class Activation Map module. Finally, the proposed deep framework obtains new state-of-the-art performance on six VEA benchmarks, where it outperforms existing state-of-the-art methods by a large margin, e.g., +3.85% on the WEBEmo dataset at 25 classes classification accuracy.
-
Hyperbolic neural networks have been popular in the recent past due to their ability to represent hierarchical data sets effectively and efficiently. The challenge in developing these networks lies in the nonlinearity of the embedding space namely, the Hyperbolic space. Hyperbolic space is a homogeneous Riemannian manifold of the Lorentz group which is a semi-Riemannian manifold, i.e. a manifold equipped with an indefinite metric. Most existing methods (with some exceptions) use local linearization to define a variety of operations paralleling those used in traditional deep neural networks in Euclidean spaces. In this paper, we present a novel fully hyperbolic neural network which uses the concept of projections (embeddings) followed by an intrinsic aggregation and a nonlinearity all within the hyperbolic space. The novelty here lies in the projection which is designed to project data on to a lower-dimensional embedded hyperbolic space and hence leads to a nested hyperbolic space representation independently useful for dimensionality reduction. The main theoretical contribution is that the proposed embedding is proved to be isometric and equivariant under the Lorentz transformations, which are the natural isometric transformations in hyperbolic spaces. This projection is computationally efficient since it can be expressed by simple linear operations, and, due to the aforementioned equivariance property, it allows for weight sharing. The nested hyperbolic space representation is the core component of our network and therefore, we first compare this representation - independent of the network - with other dimensionality reduction methods such as tangent PCA, principal geodesic analysis (PGA) and HoroPCA. Based on this equivariant embedding, we develop a novel fully hyperbolic graph convolutional neural network architecture to learn the parameters of the projection. Finally, we present experiments demonstrating comparative performance of our network on several publicly available data sets.
-
The images captured by under-display cameras (UDCs) are degraded by the screen in front of them. We model this degradation in terms of a) diffraction by the pixel grid, which attenuates high-spatial-frequency components of the image; and b) diffuse intensity and color changes caused by the multiple thin-film layers in an OLED, which modulate the low-spatial-frequency components of the image. We introduce a deep neural network with two branches to reverse each type of degradation, which is more effective than performing both restorations in a single forward network. We also propose an affine transform connection to replace the skip connection used in most existing DNNs for restoring UDC images. Confining the solution space to the linear transform domain reduces the blurring caused by convolution; and any gross color shift in the training images is eliminated by inverse color filtering. Trained on three datasets of UDC images, our network outperformed existing methods in terms of measures of distortion and of perceived image quality.
-
The raw depth image captured by the indoor depth sensor usually has an extensive range of missing depth values due to inherent limitations such as the inability to perceive transparent objects and limited distance range. The incomplete depth map burdens many downstream vision tasks, and a rising number of depth completion methods have been proposed to alleviate this issue. While most existing methods can generate accurate dense depth maps from sparse and uniformly sampled depth maps, they are not suitable for complementing the large contiguous regions of missing depth values, which is common and critical. In this paper, we design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incompleted depth images as input to predict a dense and completed depth map. The first branch employs an encoder-decoder structure to regress the local dense depth values from the raw depth map, with the help of local guidance information extracted from the RGB image. In the other branch, we propose an RGB-depth fusion GAN to transfer the RGB image to the fine-grained textured depth map. We adopt adaptive fusion modules named W-AdaIN to propagate the features across the two branches, and we append a confidence fusion head to fuse the two outputs of the branches for the final depth map. Extensive experiments on NYU-Depth V2 and SUN RGB-D demonstrate that our proposed method clearly improves the depth completion performance, especially in a more realistic setting of indoor environments with the help of the pseudo depth map.
-
Modeling in computer vision has long been dominated by convolutional neural networks (CNNs). Recently, in light of the excellent performances of self-attention mechanism in the language field, transformers tailored for visual data have drawn numerous attention and triumphed CNNs in various vision tasks. These vision transformers heavily rely on large-scale pre-training to achieve competitive accuracy, which not only hinders the freedom of architectural design in downstream tasks like object detection, but also causes learning bias and domain mismatch in the fine-tuning stages. To this end, we aim to get rid of the "pre-train & fine-tune" paradigm of vision transformer and train transformer based object detector from scratch. Some earlier work in the CNNs era have successfully trained CNNs based detectors without pre-training, unfortunately, their findings do not generalize well when the backbone is switched from CNNs to vision transformer. Instead of proposing a specific vision transformer based detector, in this work, our goal is to reveal the insights of training vision transformer based detectors from scratch. In particular, we expect those insights can help other researchers and practitioners, and inspire more interesting research in other fields, such as semantic segmentation, visual-linguistic pre-training, etc. One of the key findings is that both architectural changes and more epochs play critical roles in training vision transformer based detectors from scratch. Experiments on MS COCO datasets demonstrate that vision transformer based detectors trained from scratch can also achieve similar performances to their counterparts with ImageNet pre-training.
-
Temporal representation is the cornerstone of modern action detection techniques. State-of-the-art methods mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the temporal domain with a discretized grid, and then regress the accurate boundaries. In this paper, we revisit this foundational stage and introduce Recurrent Continuous Localization (RCL), which learns a fully continuous anchoring representation. Specifically, the proposed representation builds upon an explicit model conditioned with video embeddings and temporal coordinates, which ensure the capability of detecting segments with arbitrary length. To optimize the continuous representation, we develop an effective scale-invariant sampling strategy and recurrently refine the prediction in subsequent iterations. Our continuous anchoring scheme is fully differentiable, allowing to be seamlessly integrated into existing detectors, e.g., BMN and G-TAD. Extensive experiments on two benchmarks demonstrate that our continuous representation steadily surpasses other discretized counterparts by 2% mAP. As a result, RCL achieves 52.9% mAP@0.5 on THUMOS14 and 37.65% mAP on ActivtiyNet v1.3, outperforming all existing single-model detectors.
-
The backbone of most deep-learning-based continuous sign language recognition (CSLR) models consists of a visual module, a sequential module, and an alignment module. However, such CSLR backbones are hard to be trained sufficiently with a single connectionist temporal classification loss. In this work, we propose two auxiliary constraints to enhance the CSLR backbones from the perspective of consistency. The first constraint aims to enhance the visual module, which easily suffers from the insufficient training problem. Specifically, since sign languages convey information mainly with signers' faces and hands, we insert a keypoint-guided spatial attention module into the visual module to enforce it to focus on informative regions, i.e., spatial attention consistency. Nevertheless, only enhancing the visual module may not fully exploit the power of the backbone. Motivated by that both the output features of the visual and sequential modules represent the same sentence, we further impose a sentence embedding consistency constraint between them to enhance the representation power of both the features. Experimental results over three representative backbones validate the effectiveness of the two constraints. More remarkably, with a transformer-based backbone, our model achieves state-of-the-art or competitive performance on three benchmarks, PHOENIX-2014, PHOENIX-2014-T, and CSL.
-
Human trajectory prediction task aims to analyze human future movements given their past status, which is a crucial step for many autonomous systems such as self-driving cars and social robots. In real-world scenarios, it is unlikely to obtain sufficiently long observations at all times for prediction, considering inevitable factors such as tracking losses and sudden events. However, the problem of trajectory prediction with limited observations has not drawn much attention in previous work. In this paper, we study a task named momentary trajectory prediction, which reduces the observed history from a long time sequence to an extreme situation of two frames, one frame for social and scene contexts and both frames for the velocity of agents. We perform a rigorous study of existing state-of-the-art approaches in this challenging setting on two widely used benchmarks. We further propose a unified feature extractor, along with a novel pre-training mechanism, to capture effective information within the momentary observation. Our extractor can be adopted in existing prediction models and substantially boost their performance of momentary trajectory prediction. We hope our work will pave the way for more responsive, precise and robust prediction approaches, an important step toward real-world autonomous systems.
-
Stereo matching in foggy scenes is challenging as the scattering effect of fog blurs the image and makes the matching ambiguous. Prior methods deem the fog as noise and discard it before matching. Different from them, we propose to explore depth hints from fog and improve stereo matching via these hints. The exploration of depth hints is designed from the perspective of rendering. The rendering is conducted by reversing the atmospheric scattering process and removing the fog within a selected depth range. The quality of the rendered image reflects the correctness of the selected depth, as the closer it is to the real depth, the clearer the rendered image is. We introduce a fog volume representation to collect these depth hints from the fog. We construct the fog volume by stacking images rendered with depths computed from disparity candidates that are also used to build the cost volume. We fuse the fog volume with cost volume to rectify the ambiguous matching caused by fog. Experiments show that our fog volume representation significantly promotes the SOTA result on foggy scenes by 10% ~ 30% while maintaining a comparable performance in clear scenes.
-
We focus on the task of estimating a physically plausible articulated human motion from monocular video. Existing approaches that do not consider physics often produce temporally inconsistent output with motion artifacts, while state-of-the-art physics-based approaches have either been shown to work only in controlled laboratory conditions or consider simplified body-ground contact limited to feet. This paper explores how these shortcomings can be addressed by directly incorporating a fully-featured physics engine into the pose estimation process. Given an uncontrolled, real-world scene as input, our approach estimates the ground-plane location and the dimensions of the physical body model. It then recovers the physical motion by performing trajectory optimization. The advantage of our formulation is that it readily generalizes to a variety of scenes that might have diverse ground properties and supports any form of self-contact and contact between the articulated body and scene geometry. We show that our approach achieves competitive results with respect to existing physics-based methods on the Human3.6M benchmark, while being directly applicable without re-training to more complex dynamic motions from the AIST benchmark and to uncontrolled internet videos.
-
Despite the large augmentation family, only a few cherry-picked robust augmentation policies are beneficial to self-supervised image representation learning. In this paper, we propose a directional self-supervised learning paradigm (DSSL), which is compatible with significantly more augmentations. Specifically, we adapt heavy augmentation policies after the views lightly augmented by standard augmentations, to generate harder view (HV). HV usually has a higher deviation from the original image than the lightly augmented standard view (SV). Unlike previous methods equally pairing all augmented views to symmetrically maximize their similarities, DSSL treats augmented views of the same instance as a partially ordered set (with directions as SV\leftrightarrow SV, SV\leftarrowHV), and then equips a directional objective function respecting to the derived relationships among views. DSSL can be easily implemented with a few lines of codes and is highly flexible to popular self-supervised learning frameworks, including SimCLR, SimSiam, BYOL. Extensive experimental results on CIFAR and ImageNet demonstrated that DSSL can stably improve various baselines with compatibility to a wider range of augmentations. Code is available at: https://github.com/Yif-Yang/DSSL.
-
Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain data can be accessible all at once. However, for the real-world streaming data, this hinders the timely adaptation to changing data statistics and sufficient exploitation of increasing samples. In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID. This is challenging because it requires the model to continuously adapt to unlabeled data in the target environments while alleviating catastrophic forgetting for such a fine-grained person retrieval task. We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation. Specifically, a meta-based Coordinated Data Replay strategy is proposed to replay old data and update the network with a coordinated optimization direction for both adaptation and memorization. Moreover, we propose Relational Consistency Learning for old knowledge distillation/inheritance in line with the objective of retrieval-based tasks. We set up two evaluation settings to simulate the practical application scenarios. Extensive experiments demonstrate the effectiveness of our CLUDA-ReID for both scenarios with stationary target streams and scenarios with dynamic target streams.
-
We present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds. For quality assessment, deep neural network (DNN) has shown compelling performance on no-reference metric design. However, the most challenging issue for no-reference PCQA is that we lack large-scale subjective databases to drive robust networks. Our motivation is that the human visual system (HVS) is the decision-maker regardless of the type of media for quality assessment. Leveraging the rich subjective scores of the natural images, we can quest the evaluation criteria of human perception via DNN and transfer the capability of prediction to 3D point clouds. In particular, we treat natural images as the source domain and point clouds as the target domain, and infer point cloud quality via unsupervised adversarial domain adaptation. To extract effective latent features and minimize the domain discrepancy, we propose a hierarchical feature encoder and a conditional-discriminative network. Considering that the ultimate purpose is regressing objective score, we introduce a novel conditional cross entropy loss in the conditional-discriminative network to penalize the negative samples which hinder the convergence of the quality regression network. Experimental results show that the proposed method can achieve higher performance than traditional no-reference metrics, even comparable results with full-reference metrics. The proposed method also suggests the feasibility of assessing the quality of specific media content without the expensive and cumbersome subjective evaluations. Code is available at https://github.com/Qi-Yangsjtu/IT-PCQA.
-
Few-shot learning (FSL) aims to learn new categories with a few visual samples per class. Few-shot class representations are often biased due to data scarcity. To mitigate this issue, we propose to generate visual samples based on semantic embeddings using a conditional variational autoencoder (CVAE) model. We train this CVAE model on base classes and use it to generate features for novel classes. More importantly, we guide this VAE to strictly generate representative samples by removing non-representative samples from the base training set when training the CVAE model. We show that this training scheme enhances the representativeness of the generated samples and therefore, improves the few-shot classification results. Experimental results show that our method improves three FSL baseline methods by substantial margins, achieving state-of-the-art few-shot classification performance on miniImageNet and tieredImageNet datasets for both 1-shot and 5-shot settings.
-
Comprehending the rich semantics in an image and ordering them in linguistic order are essential to compose a visually-grounded and linguistically coherent description for image captioning. Modern techniques commonly capitalize on a pre-trained object detector/classifier to mine the semantics in an image, while leaving the inherent linguistic ordering of semantics under-exploited. In this paper, we propose a new recipe of Transformer-style structure, namely Comprehending and Ordering Semantics Networks (COS-Net), that novelly unifies an enriched semantic comprehending and a learnable semantic ordering processes into a single architecture. Technically, we initially utilize a cross-modal retrieval model to search the relevant sentences of each image, and all words in the searched sentences are taken as primary semantic cues. Next, a novel semantic comprehender is devised to filter out the irrelevant semantic words in primary semantic cues, and meanwhile infer the missing relevant semantic words visually grounded in the image. After that, we feed all the screened and enriched semantic words into a semantic ranker, which learns to allocate all semantic words in linguistic order as humans. Such sequence of ordered semantic words are further integrated with visual tokens of images to trigger sentence generation. Empirical evidences show that COS-Net clearly surpasses the state-of-the-art approaches on COCO and achieves to-date the best CIDEr score of 141.1% on Karpathy test split. Source code is available at https://github.com/YehLi/xmodaler/tree/master/configs/image_caption/cosnet.
-
Humans can not only see the collection of objects in visual scenes, but also identify the relationship between objects. The visual relationship in the scene can be abstracted into the semantic representation of triple
-
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset. Compared with existing copy detection datasets restricted by either video-level annotation or small-scale, VCSL not only has two orders of magnitude more segment-level labelled data, with 160k realistic video copy pairs containing more than 280k localized copied segment pairs, but also covers a variety of video categories and a wide range of video duration. All the copied segments inside each collected video pair are manually extracted and accompanied by precisely annotated starting and ending timestamps. Alongside the dataset, we also propose a novel evaluation protocol that better measures the prediction accuracy of copy overlapping segments between a video pair and shows improved adaptability in different scenarios. By benchmarking several baseline and state-of-the-art segment-level video copy detection methods with the proposed dataset and evaluation metric, we provide a comprehensive analysis that uncovers the strengths and weaknesses of current approaches, hoping to open up promising directions for future works. The VCSL dataset, metric and benchmark codes are all publicly available at https://github.com/alipay/VCSL.
-
Gaze object prediction is a newly proposed task that aims to discover the objects being stared at by humans. It is of great application significance but still lacks a unified solution framework. An intuitive solution is to incorporate an object detection branch into an existing gaze prediction method. However, previous gaze prediction methods usually use two different networks to extract features from scene image and head image, which would lead to heavy network architecture and prevent each branch from joint optimization. In this paper, we build a novel framework named GaTector to tackle the gaze object prediction problem in a unified way. Particularly, a specific-general-specific (SGS) feature extractor is firstly proposed to utilize a shared backbone to extract general features for both scene and head images. To better consider the specificity of inputs and tasks, SGS introduces two input-specific blocks before the shared backbone and three task-specific blocks after the shared backbone. Specifically, a novel Defocus layer is designed to generate object-specific features for the object detection task without losing information or requiring extra computations. Moreover, the energy aggregation loss is introduced to guide the gaze heatmap to concentrate on the stared box. In the end, we propose a novel wUoC metric that can reveal the difference between boxes even when they share no overlapping area. Extensive experiments on the GOO dataset verify the superiority of our method in all three tracks, i.e. object detection, gaze estimation, and gaze object prediction.
-
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough investigation of the architecture design of learned image compression, regarding both compression performance and running speed, is essential. In this paper, we first propose uneven channel-conditional adaptive coding, motivated by the observation of energy compaction in learned image compression. Combining the proposed uneven grouping model with existing context models, we obtain a spatial-channel contextual adaptive model to improve the coding performance without damage to running speed. Then we study the structure of the main transform and propose an efficient model, ELIC, to achieve state-of-the-art speed and compression ability. With superior performance, the proposed model also supports extremely fast preview decoding and progressive decoding, which makes the coming application of learning-based image compression more promising.
-
We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute whereas local self-attention often limits the field of interactions of each token. To address this issue, we develop the Cross-Shaped Window self-attention mechanism for computing self-attention in the horizontal and vertical stripes in parallel that form a cross-shaped window, with each stripe obtained by splitting the input feature into stripes of equal width. We provide a mathematical analysis of the effect of the stripe width and vary the stripe width for different layers of the Transformer network which achieves strong modeling capability while limiting the computation cost. We also introduce Locally-enhanced Positional Encoding (LePE), which handles the local positional information better than existing encoding schemes. LePE naturally supports arbitrary input resolutions and is thus especially effective and friendly for downstream tasks. Incorporated with these designs and a hierarchical structure, CSWin Transformer demonstrates competitive performance on common vision tasks. Specifically, it achieves 85.4% Top-1 accuracy on ImageNet-1K without any extra training data or label, 53.9 box AP and 46.4 mask AP on the COCO detection task, and 51.7 mIOU on the ADE20K semantic segmentation task, surpassing previous state-of-the-art Swin Transformer backbone by +1.2, +2.0, +1.4, and +2.0 respectively under the similar FLOPs setting. By further pretraining on the larger dataset ImageNet-21K, we achieve 87.5% Top-1 accuracy on ImageNet-1K and state-of-the-art segmentation performance on ADE20K with 55.7 mIoU.
-
We propose a novel multimodal architecture for Scene Text Visual Question Answering (STVQA), named Layout-Aware Transformer (LaTr). The task of STVQA requires models to reason over different modalities. Thus, we first investigate the impact of each modality, and reveal the importance of the language module, especially when enriched with layout information. Accounting for this, we propose a single objective pre-training scheme that requires only text and spatial cues. We show that applying this pre-training scheme on scanned documents has certain advantages over using natural images, despite the domain gap. Scanned documents are easy to procure, text-dense and have a variety of layouts, helping the model learn various spatial cues (e.g. left-of, below etc.) by tying together language and layout information. Compared to existing approaches, our method performs vocabulary-free decoding and, as shown, generalizes well beyond the training vocabulary. We further demonstrate that LaTr improves robustness towards OCR errors, a common reason for failure cases in STVQA. In addition, by leveraging a vision transformer, we eliminate the need for an external object detector. LaTr outperforms state-of-the-art STVQA methods on multiple datasets. In particular, +7.6% on TextVQA, +10.8% on ST-VQA and +4.0% on OCR-VQA (all absolute accuracy numbers).
-
Hierarchical multi-granularity classification (HMC) assigns hierarchical multi-granularity labels to each object and focuses on encoding the label hierarchy, e.g., ["Albatross", "Laysan Albatross"] from coarse-to-fine levels. However, the definition of what is fine-grained is subjective, and the image quality may affect the identification. Thus, samples could be observed at any level of the hierarchy, e.g., ["Albatross"] or ["Albatross", "Laysan Albatross"], and examples discerned at coarse categories are often neglected in the conventional setting of HMC. In this paper, we study the HMC problem in which objects are labeled at any level of the hierarchy. The essential designs of the proposed method are derived from two motivations: (1) learning with objects labeled at various levels should transfer hierarchical knowledge between levels; (2) lower-level classes should inherit attributes related to upper-level superclasses. The proposed combinatorial loss maximizes the marginal probability of the observed ground truth label by aggregating information from related labels defined in the tree hierarchy. If the observed label is at the leaf level, the combinatorial loss further imposes the multi-class cross-entropy loss to increase the weight of fine-grained classification loss. Considering the hierarchical feature interaction, we propose a hierarchical residual network (HRN), in which granularity-specific features from parent levels acting as residual connections are added to features of children levels. Experiments on three commonly used datasets demonstrate the effectiveness of our approach compared to the state-of-the-art HMC approaches. The code will be available at https://github.com/MonsterZhZh/HRN.
-
State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains. In this paper, we attempt to unfold an important factor that hinders the networks from generalizing across domains: through the lens of shortcut learning. We demonstrate that the learning of feature representations in stereo matching networks is heavily influenced by synthetic data artefacts (shortcut attributes). To mitigate this issue, we propose an Information-Theoretic Shortcut Avoidance (ITSA) approach to automatically restrict shortcut-related information from being encoded into the feature representations. As a result, our proposed method learns robust and shortcut-invariant features by minimizing the sensitivity of latent features to input variations. To avoid the prohibitive computational cost of direct input sensitivity optimization, we propose an effective yet feasible algorithm to achieve robustness. We show that using this method, state-of-the-art stereo matching networks that are trained purely on synthetic data can effectively generalize to challenging and previously unseen real data scenarios. Importantly, the proposed method enhances the robustness of the synthetic trained networks to the point that they outperform their fine-tuned counterparts (on real data) for challenging out-of-domain stereo datasets.
-
Attributed to both the development of deep networks and abundant data, automatic face recognition (FR) has quickly reached human-level capacity in the past few years. However, the FR problem is not perfectly solved in case of uncontrolled illumination and pose. In this paper, we propose to enhance face recognition with a bypass of self-supervised 3D reconstruction, which enforces the neural backbone to focus on the identity-related depth and albedo information while neglects the identity-irrelevant pose and illumination information. Specifically, inspired by the physical model of image formation, we improve the backbone FR network by introducing a 3D face reconstruction loss with two auxiliary networks. The first one estimates the pose and illumination from the input face image while the second one decodes the canonical depth and albedo from the intermediate feature of the FR backbone network. The whole network is trained in end-to-end manner with both classic face identification loss and the loss of 3D face reconstruction with the physical parameters. In this way, the self-supervised reconstruction acts as a regularization that enables the recognition network to understand faces in 3D view, and the learnt features are forced to encode more information of canonical facial depth and albedo, which is more intrinsic and beneficial to face recognition. Extensive experimental results on various face recognition benchmarks show that, without any cost of extra annotations and computations, our method outperforms state-of-the-art ones. Moreover, the learnt representations can also well generalize to other face-related downstream tasks such as the facial attribute recognition with limited labeled data.
-
In this paper, we propose HeadNeRF, a novel NeRF-based parametric head model that integrates the neural radiance field to the parametric representation of the human head. It can render high fidelity head images in real-time on modern GPUs, and supports directly controlling the generated images' rendering pose and various semantic attributes. Different from existing related parametric models, we use the neural radiance fields as a novel 3D proxy instead of the traditional 3D textured mesh, which makes that HeadNeRF is able to generate high fidelity images. However, the computationally expensive rendering process of the original NeRF hinders the construction of the parametric NeRF model. To address this issue, we adopt the strategy of integrating 2D neural rendering to the rendering process of NeRF and design novel loss terms. As a result, the rendering speed of HeadNeRF can be significantly accelerated, and the rendering time of one frame is reduced from 5s to 25ms. The well designed loss terms also improve the rendering accuracy, and the fine-level details of the human head, such as the gaps between teeth, wrinkles, and beards, can be represented and synthesized by HeadNeRF. Extensive experimental results and several applications demonstrate its effectiveness. The trained parametric model is available at https://github.com/CrisHY1995/headnerf.
-
Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate camera poses as input, which could be difficult to obtain in realistic settings. In this paper, we present FvOR, a learning-based object reconstruction method that predicts accurate 3D models given a few images with noisy input poses. The core of our approach is a fast and robust multi-view reconstruction algorithm to jointly refine 3D geometry and camera pose estimation using learnable neural network modules. We provide a thorough benchmark of state-of-the-art approaches for this problem on ShapeNet. Our approach achieves best-in-class results. It is also two orders of magnitude faster than the recent optimization-based approach IDR.
-
Transformers have achieved great success in pluralistic image inpainting recently. However, we find existing transformer based solutions regard each pixel as a token, thus suffer from information loss issue from two aspects: 1) They downsample the input image into much lower resolutions for efficiency consideration, incurring information loss and extra misalignment for the boundaries of masked regions. 2) They quantize 2563 RGB pixels to a small number (such as 512) of quantized pixels. The indices of quantized pixels are used as tokens for the inputs and prediction targets of transformer. Although an extra CNN network is used to upsample and refine the low-resolution results, it is difficult to retrieve the lost information back. To keep input information as much as possible, we propose a new transformer based framework "PUT". Specifically, to avoid input downsampling while maintaining the computation efficiency, we design a patch-based auto-encoder PVQVAE, where the encoder converts the masked image into non-overlapped patch tokens and the decoder recovers the masked regions from the inpainted tokens while keeping the unmasked regions unchanged. To eliminate the information loss caused by quantization, an Un-Quantized Transformer (UQ-Transformer) is applied, which directly takes the features from P-VQVAE encoder as input without quantization and regards the quantized tokens only as prediction targets. Extensive experiments show that PUT greatly outperforms state-of-the-art methods on image fidelity, especially for large masked regions and complex large-scale datasets.
-
In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k without the use of real images, human-, and self-supervision during the pre-training of Vision Transformers (ViTs). For example, ViT-Base pre-trained on ImageNet-21k shows 81.8% top-1 accuracy when fine-tuned on ImageNet-1k and FDSL shows 82.7% top-1 accuracy when pre-trained under the same conditions (number of images, hyperparameters, and number of epochs). Images generated by formulas avoid the privacy/copyright issues, labeling cost and errors, and biases that real images suffer from, and thus have tremendous potential for pre-training general models. To understand the performance of the synthetic images, we tested two hypotheses, namely (i) object contours are what matter in FDSL datasets and (ii) increased number of parameters to create labels affects performance improvement in FDSL pre-training. To test the former hypothesis, we constructed a dataset that consisted of simple object contour combinations. We found that this dataset can match the performance of fractals. For the latter hypothesis, we found that increasing the difficulty of the pre-training task generally leads to better fine-tuning accuracy.
-
Recent studies have shown that adversarial examples hand-crafted on one white box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which has raised security concerns for real-world DNNs applications. Nevertheless, existing works mostly focus on investigating the adversarial transferability across different deep models that share the same modality of input data. The cross-modal transferability of adversarial perturbation has never been explored. This paper investigates the transferability of adversarial perturbation across different modalities, i.e., leveraging adversarial perturbation generated on white-box image models to attack black-box video models. Specifically, motivated by the observation that the low-level feature space between images and video frames are similar, we propose a simple yet effective cross-modal attack method, named as Image To Video (I2V) attack. I2V generates adversarial frames by minimizing the cosine similarity between features of pre-trained image models from adversarial and benign examples, then combines the generated adversarial frames to perform black-box attacks on video recognition models. Extensive experiments demonstrate that I2V can achieve high attack success rates on different black-box video recognition models. On Kinetics-400 and UCF-101, I2V achieves an average attack success rate of 77.88% and 65.68%, respectively, which sheds light on the feasibility of cross-modal adversarial attacks.
-
Recently, transformer-based methods have achieved promising progresses in object detection, as they can eliminate the post-processes like NMS and enrich the deep representations. However, these methods cannot well cope with scene text due to its extreme variance of scales and aspect ratios. In this paper, we present a simple yet effective transformer-based architecture for scene text detection. Different from previous approaches that learn robust deep representations of scene text in a holistic manner, our method performs scene text detection based on a few representative features, which avoids the disturbance by background and reduces the computational cost. Specifically, we first select a few representative features at all scales that are highly relevant to foreground text. Then, we adopt a transformer for modeling the relationship of the sampled features, which effectively divides them into reasonable groups. As each feature group corresponds to a text instance, its bounding box can be easily obtained without any post-processing operation. Using the basic feature pyramid network for feature extraction, our method consistently achieves state-of-the-art results on several popular datasets for scene text detection.
-
It is a mystery which input features contribute to a neural network's output. Various explanations methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations point to different features as being important. The phenomenon raises the question, which explanation to trust? We propose a framework for evaluating the explanations using the neural network model itself. The framework leverages the network to generate input features that impose a particular behavior on the output. Using the generated features, we devise controlled experimental setups to evaluate whether an explanation method conforms to an axiom. Thus we propose an empirical framework for axiomatic evaluation of explanation methods. We evaluate well-known and promising explanation solutions using the proposed framework. The framework provides a toolset to reveal properties and drawbacks within existing and future explanation solutions.
-
Scaling Visual Question Answering (VQA) to the open-domain and multi-hop nature of web searches, requires fundamental advances in visual representation learning, knowledge aggregation, and language generation. In this work, we introduce WebQA, a challenging new benchmark that proves difficult for large-scale state-of-the-art models which lack language groundable visual representations for novel objects and the ability to reason, yet trivial for humans. WebQA mirrors the way humans use the web: 1) Ask a question, 2) Choose sources to aggregate, and 3) Produce a fluent language response. This is the behavior we should be expecting from IoT devices and digital assistants. Existing work prefers to assume that a model can either reason about knowledge in images or in text. WebQA includes a secondary text-only QA task to ensure improved visual performance does not come at the cost of language understanding. Our challenge for the community is to create unified multimodal reasoning models that answer questions regardless of the source modality, moving us closer to digital assistants that not only query language knowledge, but also the richer visual online world.
-
The occlusion problem heavily degrades the localization performance of face alignment. Most current solutions for this problem focus on annotating new occlusion data, introducing boundary estimation, and stacking deeper models to improve the robustness of neural networks. However, the performance degradation of models remains under extreme occlusion (average occlusion of over 50%) because of missing a large amount of facial context information. We argue that exploring neural networks to model the facial hierarchies is a more promising method for dealing with extreme occlusion. Surprisingly, in recent studies, little effort has been devoted to representing the facial hierarchies using neural networks. This paper proposes a new network architecture called GlomFace to model the facial hierarchies against various occlusions, which draws inspiration from the viewpoint-invariant hierarchy of facial structure. Specifically, GlomFace is functionally divided into two modules: the part-whole hierarchical module and the whole-part hierarchical module. The former captures the part-whole hierarchical dependencies of facial parts to suppress multi-scale occlusion information, whereas the latter injects structural reasoning into neural networks by building the whole-part hierarchical relations among facial parts. As a result, GlomFace has a clear topological interpretation due to its correspondence to the facial hierarchies. Extensive experimental results indicate that the proposed GlomFace performs comparably to existing state-of-the-art methods, especially in cases of extreme occlusion. Models are available at https://github.com/zhuccly/GlomFace-Face-Alignment.
-
A recurrent structure is a popular framework choice for the task of video super-resolution. The state-of-the-art method BasicVSR adopts bidirectional propagation with feature alignment to effectively exploit information from the entire input video. In this study, we redesign BasicVSR by proposing second-order grid propagation and flow-guided deformable alignment. We show that by empowering the recurrent framework with enhanced propagation and alignment, one can exploit spatiotemporal information across misaligned video frames more effectively. The new components lead to an improved performance under a similar computational constraint. In particular, our model BasicVSR++ surpasses BasicVSR by a significant 0.82 dB in PSNR with similar number of parameters. BasicVSR++ is generalizable to other video restoration tasks, and obtains three champions and one first runner-up in NTIRE 2021 video restoration challenge.
-
The lack of large-scale noisy-clean image pairs restricts supervised denoising methods' deployment in actual applications. While existing unsupervised methods are able to learn image denoising without ground-truth clean images, they either show poor performance or work under impractical settings (e.g., paired noisy images). In this paper, we present a practical unsupervised image denoising method to achieve state-of-the-art denoising performance. Our method only requires single noisy images and a noise model, which is easily accessible in practical raw image denoising. It performs two steps iteratively: (1) Constructing a noisier-noisy dataset with random noise from the noise model; (2) training a model on the noisier-noisy dataset and using the trained model to refine noisy images to obtain the targets used in the next round. We further approximate our full iterative method with a fast algorithm for more efficient training while keeping its original high performance. Experiments on real-world, synthetic, and correlated noise show that our proposed unsupervised denoising approach has superior performances over existing unsupervised methods and competitive performance with supervised methods. In addition, we argue that existing denoising datasets are of low quality and contain only a small number of scenes. To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes. The dataset can serve as a strong benchmark for better evaluating raw image denoising. Code and dataset will be released at https://github.com/zhangyi-3/IDR
-
Benefiting from the pioneering design of generic object detectors, significant achievements have been made in the field of face detection. Typically, the architectures of the backbone, feature pyramid layer, and detection head module within the face detector all assimilate the excellent experience from general object detectors. However, several effective methods, including label assignment and scale-level data augmentation strategy, fail to maintain consistent superiority when applying on the face detector directly. Concretely, the former strategy involves a vast body of hyper-parameters and the latter one suffers from the challenge of scale distribution bias between different detection tasks, which both limit their generalization abilities. Furthermore, in order to provide accurate face bounding boxes for facial down-stream tasks, the face detector imperatively requires the elimination of false alarms. As a result, practical solutions on label assignment, scale-level data augmentation, and reducing false alarms are necessary for advancing face detectors. In this paper, we focus on resolving three aforementioned challenges that exiting methods are difficult to finish off and present a novel face detector, termed MogFace. In our Mogface, three key components, Adaptive Online Incremental Anchor Mining Strategy, Selective Scale Enhancement Strategy and Hierarchical Context-Aware Module, are separately proposed to boost the performance of face detectors. Finally, to the best of our knowledge, our MogFace is the best face detector on the Wider Face leader-board, achieving all champions across different testing scenarios. The code is available at https://github.com/damo-cv/MogFace.
-
Depth completion has been widely studied to predict a dense depth image from its sparse measurement and a single color image. However, most state-of-the-art methods rely on static convolutional neural networks (CNNs) which are not flexible enough for capturing the dynamic nature of input contexts. In this paper, we propose GuideFormer, a fully transformer-based architecture for dense depth completion. We first process sparse depth and color guidance images with separate transformer branches to extract hierarchical and complementary token representations. Each branch consists of a stack of self-attention blocks and has key design features to make our model suitable for the task. We also devise an effective token fusion method based on guided-attention mechanism. It explicitly models information flow between the two branches and captures inter-modal dependencies that cannot be obtained from depth or color image alone. These properties allow GuideFormer to enjoy various visual dependencies and recover precise depth values while preserving fine details. We evaluate GuideFormer on the KITTI dataset containing real-world driving scenes and provide extensive ablation studies. Experimental results demonstrate that our approach significantly outperforms the state-of-the-art methods.
-
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are assigned a single label. This ambiguity biases models towards a single prediction, which could result in the suppression of classes that tend to co-occur in the data. Inspired by language emergence literature, we propose multi-label iterated learning (MILe) to incorporate the inductive biases of multi-label learning from single labels using the framework of iterated learning. MILe is a simple yet effective procedure that builds a multi-label description of the image by propagating binary predictions through successive generations of teacher and student networks with a learning bottleneck. Experiments show that our approach exhibits systematic benefits on ImageNet accuracy as well as ReaL F1 score, which indicates that MILe deals better with label ambiguity than the standard training procedure, even when fine-tuning from self-supervised weights. We also show that MILe is effective reducing label noise, achieving state-of-the-art performance on real-world large-scale noisy data such as WebVision. Furthermore, MILe improves performance in class incremental settings such as IIRC and it is robust to distribution shifts.
-
This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: 1) Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction. 2) Global Source Feature-Adaptive (SFA) branch further complements global identity-relevant cues for generating identity-consistent swapped faces. Besides, we propose a Face Mask Predictor (FMP) module incorporated with StyleGAN2 to predict identity-relevant soft facial masks in an unsupervised manner that is more practical for generating harmonious high-resolution faces. Abundant experiments qualitatively and quantitatively demonstrate the superiority of our method for generating more identity-consistent high-resolution swapped faces over SOTA methods, e.g., obtaining 96.70 ID retrieval that outperforms SOTA MegaFS by 5.87.
-
One of the major challenges in training text-to-image generation models is the need of a large number of high-quality text-image pairs. While image samples are often easily accessible, the associated text description typically requires careful human captioning, which is particularly time- and cost-consuming. In this paper, we propose the first work to train text-to-image generation models without any text data. It intelligently leverages the well-aligned cross-modal semantic space of the powerful pre-trained CLIP model: the requirement of text-conditioning is alleviated via generating text features from image features. Extensive experiments are conducted to illustrate the effectiveness of the proposed method. We obtain state-of-the-art results in the standard text-to-image generation tasks. Importantly, the proposed language-free model outperforms most existing models trained with full text-image pairs. Furthermore, our method can be applied in fine-tuning pre-trained models, which saves both training time and cost in training text-to-image generation models. Our pre-trained model obtains competitive results in zero-shot text-to-image generation on MS-COCO dataset, yet with around only 1% of the model size compared to the recently proposed large DALL-E model.
-
Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However, current methods are mainly based on convolutional neural networks and fail to explore the global information properly, thus usually resulting in incomplete object regions. In this paper, to address the aforementioned problem, we introduce Transformers, which naturally integrate global information, to generate more integral initial pseudo labels for end-to-end WSSS. Motivated by the inherent consistency between the self-attention in Transformers and the semantic affinity, we propose an Affinity from Attention (AFA) module to learn semantic affinity from the multi-head self-attention (MHSA) in Transformers. The learned affinity is then leveraged to refine the initial pseudo labels for segmentation. In addition, to efficiently derive reliable affinity labels for supervising AFA and ensure the local consistency of pseudo labels, we devise a Pixel-Adaptive Refinement module that incorporates low-level image appearance information to refine the pseudo labels. We perform extensive experiments and our method achieves 66.0% and 38.9% mIoU on the PASCAL VOC 2012 and MS COCO 2014 datasets, respectively, significantly outperforming recent end-to-end methods and several multi-stage competitors. Code is available at https://github.com/rulixiang/afa.
-
Ensemble methods based on decision trees, such as Random Forests or boosted forests, have long been established as some of the most powerful, off-the-shelf machine learning models, and have been widely used in computer vision and other areas. In recent years, a specific form of boosting, gradient boosting (GB), has gained prominence. This is partly because of highly optimized implementations such as XGBoost or LightGBM, which incorporate many clever modifications and heuristics. However, one gaping hole remains unexplored in GB: the construction of individual trees. To date, all successful GB versions use axis-aligned trees trained in a suboptimal way via greedy recursive partitioning. We address this gap by using a more powerful type of trees (having hyperplane splits) and an algorithm that can optimize, globally over all the tree parameters, the objective function that GB dictates. We show, in several benchmarks of image and other data types, that GB forests of these stronger, well-optimized trees consistently exceed the test accuracy of axis-aligned forests from XGBoost, LightGBM and other strong baselines. Further, this happens using many fewer trees and sometimes even fewer parameters overall.
-
We introduce a novel approach for generative 3D modeling that explicitly encourages the physical and thus functional consistency of the generated shapes. To this end, we advocate the use of online physical simulation as part of learning a generative model. Unlike previous related methods, our approach is trained end-to-end with a fully differentiable physical simulator in the training loop. We accomplish this by leveraging recent advances in differentiable programming, and introducing a fully differentiable point-based physical simulation layer, which accurately evaluates the shape's stability when subjected to gravity. We then incorporate this layer in a signed distance function (SDF) shape decoder. By augmenting a conventional SDF decoder with our simulation layer, we demonstrate through extensive experiments that online physical simulation improves the accuracy, visual plausibility and physical validity of the resulting shapes, while requiring no additional data or annotation effort.
-
We describe a method to extract persistent elements of a dynamic scene from an input video. We represent each scene element as a Deformable Sprite consisting of three components: 1) a 2D texture image for the entire video, 2) per-frame masks for the element, and 3) non-rigid deformations that map the texture image into each video frame. The resulting decomposition allows for applications such as consistent video editing. Deformable Sprites are a type of video auto-encoder model that is optimized on individual videos, and does not require training on a large dataset, nor does it rely on pre-trained models. Moreover, our method does not require object masks or other user input, and discovers moving objects of a wider variety than previous work. We evaluate our approach on standard video datasets and show qualitative results on a diverse array of Internet videos.
-
In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and 3D information in an "early-fusion" or "late-fusion" manner. Such one-size-fits-all approaches suffer from a dilemma of failing to fully utilize the characteristic of each modality or to maximize the inter-modality complementarity. To address the problem, we propose a novel end-to-end framework, called CamLiFlow. It consists of 2D and 3D branches with multiple bidirectional connections between them in specific layers. Different from previous work, we apply a point-based 3D branch to better extract the geometric features and design a symmetric learnable operator to fuse dense image features and sparse point features. Experiments show that CamLiFlow achieves better performance with fewer parameters. Our method ranks 1st on the KITTI Scene Flow benchmark, outperforming the previous art with 1/7 parameters. Code is available at https://github.com/MCG-NJU/CamLiFlow.
-
Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos. It is still ambiguous to evaluate whether performances of existing methods remain satisfactory in real-world application-oriented scenes. For example, the "Happy" expression with high intensity in Talk-Show is more discriminating than the same expression with low intensity in Official-Event. To fill this gap, we build a large-scale multi-scene dataset, coined as FERV39k. We analyze the important ingredients of constructing such a novel dataset in three aspects: (1) multi-scene hierarchy and expression class, (2) generation of candidate video clips, (3) trusted manual labelling process. Based on these guidelines, we select 4 scenarios subdivided into 22 scenes, annotate 86k samples automatically obtained from 4k videos based on the well-designed workflow, and finally build 38,935 video clips labeled with 7 classic expressions. Experiment benchmarks on four kinds of baseline frameworks were also provided and further analysis on their performance across different scenes and some challenges for future research were given. Besides, we systematically investigate key components of DFER by ablation studies. The baseline framework and our project are available on https://github.com/wangyanckxx/FERV39k.
-
Current 3D object detectors for autonomous driving are almost entirely trained on human-annotated data. Although of high quality, the generation of such data is laborious and costly, restricting them to a few specific locations and object types. This paper proposes an alternative approach entirely based on unlabeled data, which can be collected cheaply and in abundance almost everywhere on earth. Our approach leverages several simple common sense heuristics to create an initial set of approximate seed labels. For example, relevant traffic participants are generally not persistent across multiple traversals of the same route, do not fly, and are never under ground. We demonstrate that these seed labels are highly effective to bootstrap a surprisingly accurate detector through repeated self-training without a single human annotated label. Code is available at https://github.com/YurongYou/MODEST.
-
Dense 3D reconstruction from a stream of depth images is the key to many mixed reality and robotic applications. Although methods based on Truncated Signed Distance Function (TSDF) Fusion have advanced the field over the years, the TSDF volume representation is confronted with striking a balance between the robustness to noisy measurements and maintaining the level of detail. We present Bi-level Neural Volume Fusion (BNV-Fusion), which leverages recent advances in neural implicit representations and neural rendering for dense 3D reconstruction. In order to incrementally integrate new depth maps into a global neural implicit representation, we propose a novel bi-level fusion strategy that considers both efficiency and reconstruction quality by design. We evaluate the proposed method on multiple datasets quantitatively and qualitatively, demonstrating a significant improvement over existing methods.
-
This paper presents Probabilistic Video Contrastive Learning, a self-supervised representation learning method that bridges contrastive learning with probabilistic representation. We hypothesize that the clips composing the video have different distributions in short-term duration, but can represent the complicated and sophisticated video distribution through combination in a common embedding space. Thus, the proposed method represents video clips as normal distributions and combines them into a Mixture of Gaussians to model the whole video distribution. By sampling embeddings from the whole video distribution, we can circumvent the careful sampling strategy or transformations to generate augmented views of the clips, unlike previous deterministic methods that have mainly focused on such sample generation strategies for contrastive learning. We further propose a stochastic contrastive loss to learn proper video distributions and handle the inherent uncertainty from the nature of the raw video. Experimental results verify that our probabilistic embedding stands as a state-of-the-art video representation learning for action recognition and video retrieval on the most popular benchmarks, including UCF101 and HMDB51.
-
In Vision-and-Language Navigation (VLN), an agent needs to navigate through the environment based on natural language instructions. Due to limited available data for agent training and finite diversity in navigation environments, it is challenging for the agent to generalize to new, unseen environments. To address this problem, we propose EnvEdit, a data augmentation method that creates new environments by editing existing environments, which are used to train a more generalizable agent. Our augmented environments can differ from the seen environments in three diverse aspects: style, object appearance, and object classes. Training on these edit-augmented environments prevents the agent from overfitting to existing environments and helps generalize better to new, unseen environments. Empirically, on both the Room-to-Room and the multi-lingual Room-Across-Room datasets, we show that our proposed EnvEdit method gets significant improvements in all metrics on both pre-trained and non-pre-trained VLN agents, and achieves the new state-of-the-art on the test leaderboard. We further ensemble the VLN agents augmented on different edited environments and show that these edit methods are complementary.
-
Prior work has studied different visual modalities in isolation and developed separate architectures for recognition of images, videos, and 3D data. Instead, in this paper, we propose a single model which excels at classifying images, videos, and single-view 3D data using exactly the same model parameters. Our 'OMNIVORE' model leverages the flexibility of transformer-based architectures and is trained jointly on classification tasks from different modalities. OMNIVORE is simple to train, uses off-the-shelf standard datasets, and performs at-par or better than modality-specific models of the same size. A single OMNIVORE model obtains 86.0% on ImageNet, 84.1% on Kinetics, and 67.1% on SUN RGB-D. After finetuning, our models outperform prior work on a variety of vision tasks and generalize across modalities. OMNIVORE's shared visual representation naturally enables cross-modal recognition without access to correspondences between modalities. We hope our results motivate researchers to model visual modalities together.
-
Learning to autonomously assemble shapes is a crucial skill for many robotic applications. While the majority of existing part assembly methods focus on correctly posing semantic parts to recreate a whole object, we interpret assembly more literally: as mating geometric parts together to achieve a snug fit. By focusing on shape alignment rather than semantic cues, we can achieve across category generalization and scaling. In this paper, we introduce a novel task, pairwise 3D geometric shape mating, and propose Neural Shape Mating (NSM) to tackle this problem. Given point clouds of two object parts of an unknown category, NSM learns to reason about the fit of the two parts and predict a pair of 3D poses that tightly mate them together. In addition, we couple the training of NSM with an implicit shape reconstruction task, making NSM more robust to imperfect point cloud observations. To train NSM, we present a self-supervised data collection pipeline that generates pairwise shape mating data with ground truth by randomly cutting an object mesh into two parts, resulting in a dataset that consists of 200K shape mating pairs with numerous object meshes and diverse cut types. We train NSM on the collected dataset and compare it with several point cloud registration methods and one part assembly baseline approach. Extensive experimental results and ablation studies under various settings demonstrate the effectiveness of the proposed algorithm. Additional material is available at: neural-shape-mating.github.io.
-
Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as high-level tasks and is sensitive to the dropout operation. However, in this paper, we show that appropriate usage of dropout benefits SR networks and improves the generalization ability. Specifically, dropout is better embedded at the end of the network and is significantly helpful for the multi-degradation settings. This discovery breaks our common sense and inspires us to explore its working mechanism. We further use two analysis tools -- one is from recent network interpretation works, and the other is specially designed for this task. The analysis results provide side proofs to our experimental findings and show us a new perspective to understand SR networks.
-
We present a new domain generalized semantic segmentation network named WildNet, which learns domain-generalized features by leveraging a variety of contents and styles from the wild. In domain generalization, the low generalization ability for unseen target domains is clearly due to overfitting to the source domain. To address this problem, previous works have focused on generalizing the domain by removing or diversifying the styles of the source domain. These alleviated overfitting to the source-style but overlooked overfitting to the source-content. In this paper, we propose to diversify both the content and style of the source domain with the help of the wild. Our main idea is for networks to naturally learn domain-generalized semantic information from the wild. To this end, we diversify styles by augmenting source features to resemble wild styles and enable networks to adapt to a variety of styles. Furthermore, we encourage networks to learn class-discriminant features by providing semantic variations borrowed from the wild to source contents in the feature space. Finally, we regularize networks to capture consistent semantic information even when both the content and style of the source domain are extended to the wild. Extensive experiments on five different datasets validate the effectiveness of our WildNet, and we significantly outperform state-of-the-art methods. The source code and model are available online: https://github.com/suhyeonlee/WildNet.
-
Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data. However, recent studies have revealed that private information can still be leaked through shared gradient information. To further protect user's privacy, several defense mechanisms have been proposed to prevent privacy leakage via gradient information degradation methods, such as using additive noise or gradient compression before sharing it with the server. In this work, we validate that the private training data can still be leaked under certain defense settings with a new type of leakage, i.e., Generative Gradient Leakage (GGL). Unlike existing methods that only rely on gradient information to reconstruct data, our method leverages the latent space of generative adversarial networks (GAN) learned from public image datasets as a prior to compensate for the informational loss during gradient degradation. To address the nonlinearity caused by the gradient operator and the GAN model, we explore various gradient-free optimization methods (e.g., evolution strategies and Bayesian optimization) and empirically show their superiority in reconstructing high-quality images from gradients compared to gradient-based optimizers. We hope the proposed method can serve as a tool for empirically measuring the amount of privacy leakage to facilitate the design of more robust defense mechanisms.
-
Autonomous driving faces great safety challenges for a lack of global perspective and the limitation of long-range perception capabilities. It has been widely agreed that vehicle-infrastructure cooperation is required to achieve Level 5 autonomy. However, there is still NO dataset from real scenarios available for computer vision researchers to work on vehicle-infrastructure cooperation-related problems. To accelerate computer vision research and innovation for Vehicle-Infrastructure Cooperative Autonomous Driving (VICAD), we release DAIR-V2X Dataset, which is the first large-scale, multi-modal, multi-view dataset from real scenarios for VICAD. DAIR-V2X comprises 71254 LiDAR frames and 71254 Camera frames, and all frames are captured from real scenes with 3D annotations. The Vehicle-Infrastructure Cooperative 3D Object Detection problem (VIC3D) is introduced, formulating the problem of collaboratively locating and identifying 3D objects using sensory input from both vehicles and infrastructure. In addition to solving traditional 3D object detection problems, the solution of VIC3D needs to consider the time asynchrony problem between vehicle and infrastructure sensors and the data transmission cost between them. Furthermore, we propose Time Compensation Late Fusion (TCLF), a late fusion framework for the VIC3D task as a benchmark based on DAIR-V2X. Find data, code, and more up-to-date information at \href https://thudair.baai.ac.cn/index https://thudair.baai.ac.cn/index and \href https://github.com/AIR-THU/DAIR-V2X https://github.com/AIR-THU/DAIR-V2X .
-
Deep learning has become an increasingly popular and powerful methodology for modern pattern recognition systems. However, many deep neural networks have millions or billions of parameters, making them untenable for real-world applications due to constraints on memory size or latency requirements. As a result, efficient network compression techniques are often required for a widespread adoption of deep learning methods. We present DECORE, a reinforcement learning based approach to automate the network compression process. DECORE assigns an agent to each channel in the network along with a light policy gradient method to learn which neurons or channels to be kept or removed. Each agent in the network has just one parameter (keep or drop) to learn, which leads to a much faster training process compared to existing approaches. DECORE also gives state-of-the-art compression results on various network architectures and various datasets. For example, on the ResNet-110 architecture, DECORE achieves a 64.8% compression rate and 61.8% FLOPs reduction as compared to the baseline model without any major accuracy loss on the CIFAR-10 dataset. It can reduce the size of regular architectures like the VGG network by up to 99% with just a small accuracy drop of 2.28%. For a larger dataset like ImageNet it can compress the ResNet-50 architecture by 44.7% and reduces FLOPs by 42.3%, with just a 0.69% drop on Top-5 accuracy of the uncompressed model. We also demonstrate that DECORE can be used to search for compressed network architectures based on various constraints, such as memory and FLOPs.
-
While separately leveraging monocular 3D object detection and 2D multi-object tracking can be straightforwardly applied to sequence images in a frame-by-frame fashion, stand-alone tracker cuts off the transmission of the uncertainty from the 3D detector to tracking while cannot pass tracking error differentials back to the 3D detector. In this work, we propose jointly training 3D detection and 3D tracking from only monocular videos in an end-to-end manner. The key component is a novel spatial-temporal information flow module that aggregates geometric and appearance features to predict robust similarity scores across all objects in current and past frames. Specifically, we leverage the attention mechanism of the transformer, in which self-attention aggregates the spatial information in a specific frame, and cross-attention exploits relation and affinities of all objects in the temporal domain of sequence frames. The affinities are then supervised to estimate the trajectory and guide the flow of information between corresponding 3D objects. In addition, we propose a temporal-consistency loss that explicitly involves 3D target motion modeling into the learning, making the 3D trajectory smooth in the world coordinate system. Time3D achieves 21.4% AMOTA, 13.6% AMOTP on the nuScenes 3D tracking benchmark, surpassing all published competitors, and running at 38 FPS, while Time3D achieves 31.2% mAP, 39.4% NDS on the nuScenes 3D detection benchmark.
-
Due to the inherent ill-posed nature of 2D-3D projection, monocular 3D object detection lacks accurate depth recovery ability. Although the deep neural network (DNN) enables monocular depth-sensing from high-level learned features, the pixel-level cues are usually omitted due to the deep convolution mechanism. To benefit from both the powerful feature representation in DNN and pixel-level geometric constraints, we reformulate the monocular object depth estimation as a progressive refinement problem and propose a joint semantic and geometric cost volume to model the depth error. Specifically, we first leverage neural networks to learn the object position, dimension, and dense normalized 3D object coordinates. Based on the object depth, the dense coordinates patch together with the corresponding object features is reprojected to the image space to build a cost volume in a joint semantic and geometric error manner. The final depth is obtained by feeding the cost volume to a refinement network, where the distribution of semantic and geometric error is regularized by direct depth supervision. Through effectively mitigating depth error by the refinement framework, we achieve state-of-the-art results on both the KITTI and Waymo datasets.
-
Recognizing discriminative details such as eyes and beaks is important for distinguishing fine-grained classes since they have similar overall appearances. In this regard, we introduce Task Discrepancy Maximization (TDM), a simple module for fine-grained few-shot classification. Our objective is to localize the class-wise discriminative regions by highlighting channels encoding distinct information of the class. Specifically, TDM learns task-specific channel weights based on two novel components: Support Attention Module (SAM) and Query Attention Module (QAM). SAM produces a support weight to represent channel-wise discriminative power for each class. Still, since the SAM is basically only based on the labeled support sets, it can be vulnerable to bias toward such support set. Therefore, we propose QAM which complements SAM by yielding a query weight that grants more weight to object-relevant channels for a given query image. By combining these two weights, a class-wise task-specific channel weight is defined. The weights are then applied to produce task-adaptive feature maps more focusing on the discriminative details. Our experiments validate the effectiveness of TDM and its complementary benefits with prior methods in fine-grained few-shot classification.
-
Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data. However, the key challenge in federated learning is that the clients have significant statistical heterogeneity among their local data distributions, which would cause inconsistent optimized local models on the client-side. To address this fundamental dilemma, we propose a novel federated learning algorithm with local drift decoupling and correction (FedDC). Our FedDC only introduces lightweight modifications in the local training phase, in which each client utilizes an auxiliary local drift variable to track the gap between the local model parameter and the global model parameters. The key idea of FedDC is to utilize this learned local drift variable to bridge the gap, i.e., conducting consistency in parameter-level. The experiment results and analysis demonstrate that FedDC yields expediting convergence and better performance on various image classification tasks, robust in partial participation settings, non-iid data, and heterogeneous clients.
-
An increasing number of applications in computer vision, specially, in medical imaging and remote sensing, become challenging when the goal is to classify very large images with tiny informative objects. Specifically, these classification tasks face two key challenges: i) the size of the input image is usually in the order of mega- or giga-pixels, however, existing deep architectures do not easily operate on such big images due to memory constraints, consequently, we seek a memory-efficient method to process these images; and ii) only a very small fraction of the input images are informative of the label of interest, resulting in low region of interest (ROI) to image ratio. However, most of the current convolutional neural networks (CNNs) are designed for image classification datasets that have relatively large ROIs and small image sizes (sub-megapixel). Existing approaches have addressed these two challenges in isolation. We present an end-to-end CNN model termed Zoom-In network that leverages hierarchical attention sampling for classification of large images with tiny objects using a single GPU. We evaluate our method on four large-image histopathology, road-scene and satellite imaging datasets, and one gigapixel pathology dataset. Experimental results show that our model achieves higher accuracy than existing methods while requiring less memory resources.
-
Matching-based methods, especially those based on space-time memory, are significantly ahead of other solutions in semi-supervised video object segmentation (VOS). However, continuously growing and redundant template features lead to an inefficient inference. To alleviate this, we propose a novel Sequential Weighted Expectation-Maximization (SWEM) network to greatly reduce the redundancy of memory features. Different from the previous methods which only detect feature redundancy between frames, SWEM merges both intra-frame and inter-frame similar features by leveraging the sequential weighted EM algorithm. Further, adaptive weights for frame features endow SWEM with the flexibility to represent hard samples, improving the discrimination of templates. Besides, the proposed method maintains a fixed number of template features in memory, which ensures the stable inference complexity of the VOS system. Extensive experiments on commonly used DAVIS and YouTube-VOS datasets verify the high efficiency (36 FPS) and high performance (84.3% J&F on DAVIS 2017 validation dataset) of SWEM.
-
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. Directly employing previous distillation approaches yields inferior results due to the intrinsic challenges of point cloud, i.e., sparsity, randomness and varying density. To tackle the aforementioned problems, we propose the Point-to-Voxel Knowledge Distillation (PVD), which transfers the hidden knowledge from both point level and voxel level. Specifically, we first leverage both the pointwise and voxelwise output distillation to complement the sparse supervision signals. Then, to better exploit the structural information, we divide the whole point cloud into several supervoxels and design a difficultyaware sampling strategy to more frequently sample supervoxels containing less frequent classes and faraway objects. On these supervoxels, we propose inter-point and intervoxel affinity distillation, where the similarity information between points and voxels can help the student model better capture the structural information of the surrounding environment. We conduct extensive experiments on two popular LiDAR segmentation benchmarks, i.e., nuScenes [3] and SemanticKITTI [1]. On both benchmarks, our PVD consistently outperforms previous distillation approaches by a large margin on three representative backbones, i.e., Cylinder3D [27, 28], SPVNAS [20] and MinkowskiNet [5]. Notably, on the challenging nuScenes and SemanticKITTI datasets, our method can achieve roughly 75% MACs reduction and 2x speedup on the competitive Cylinder3D model and rank 1st on the SemanticKITTI leaderboard among all published algorithms. Our code is available at https://github.com/cardwing/Codes-for-PVKD.
-
Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate. Contrary to this, we find that applying existing fairness approaches to computer vision improve fairness by degrading the performance of classifiers across all groups (with increased degradation on the best performing groups). Extending the bias-variance decomposition for classification to fairness, we theoretically explain why the majority of fairness methods designed for low capacity models should not be used in settings involving high-capacity models, a scenario common to computer vision. We corroborate this analysis with extensive experimental support that shows that many of the fairness heuristics used in computer vision also degrade performance on the most disadvantaged groups. Building on these insights, we propose an adaptive augmentation strategy that, uniquely, of all methods tested, improves performance for the disadvantaged groups.
-
Occlusions are a common occurrence in unconstrained face images. Single image 3D reconstruction from such face images often suffers from corruption due to the presence of occlusions. Furthermore, while a plurality of 3D reconstructions is plausible in the occluded regions, existing approaches are limited to generating only a single solution. To address both of these challenges, we present Diverse3DFace, which is specifically designed to simultaneously generate a diverse and realistic set of 3D reconstructions from a single occluded face image. It consists of three components: a global+local shape fitting process, a graph neural network-based mesh VAE, and a Determinantal Point Process based diversity promoting iterative optimization procedure. Quantitative and qualitative comparisons of 3D reconstruction on occluded faces show that Diverse3DFace can estimate 3D shapes that are consistent with the visible regions in the target image while exhibiting high, yet realistic, levels of diversity on the occluded regions. On face images occluded by masks, glasses, and other random objects, Diverse3DFace generates a distribution of 3D shapes having 50% higher diversity on the occluded regions compared to the baselines. Moreover, our closest sample to the ground truth has 40% lower MSE than the singular reconstructions by existing approaches. Code and data available at: https://github.com/human-analysis/diverse3dface
-
As a fundamental problem in computer vision, 3D object detection is experiencing rapid growth. To extract the point-wise features from the irregularly and sparsely distributed points, previous methods usually take a feature grouping module to aggregate the point features to an object candidate. However, these methods have not yet leveraged the surface geometry of foreground objects to enhance grouping and 3D box generation. In this paper, we propose the RBGNet framework, a voting-based 3D detector for accurate 3D object detection from point clouds. In order to learn better representations of object shape to enhance cluster features for predicting 3D boxes, we propose a ray-based feature grouping module, which aggregates the point-wise features on object surfaces using a group of determined rays uniformly emitted from cluster centers. Considering the fact that foreground points are more meaningful for box estimation, we design a novel foreground biased sampling strategy in downsample process to sample more points on object surfaces and further boost the detection performance. Our model achieves state-of-the-art 3D detection performance on ScanNet V2 and SUN RGB-D with remarkable performance gains.
-
Motion, as the uniqueness of a video, has been critical to the development of video understanding models. Modern deep learning models leverage motion by either executing spatio-temporal 3D convolutions, factorizing 3D convolutions into spatial and temporal convolutions separately, or computing self-attention along temporal dimension. The implicit assumption behind such successes is that the feature maps across consecutive frames can be nicely aggregated. Nevertheless, the assumption may not always hold especially for the regions with large deformation. In this paper, we present a new recipe of inter-frame attention block, namely Stand-alone Inter-Frame Attention (SIFA), that novelly delves into the deformation across frames to estimate local self-attention on each spatial location. Technically, SIFA remoulds the deformable design via re-scaling the offset predictions by the difference between two frames. Taking each spatial location in the current frame as the query, the locally deformable neighbors in the next frame are regarded as the keys/values. Then, SIFA measures the similarity between query and keys as stand-alone attention to weighted average the values for temporal aggregation. We further plug SIFA block into ConvNets and Vision Transformer, respectively, to devise SIFA-Net and SIFA-Transformer. Extensive experiments conducted on four video datasets demonstrate the superiority of SIFA-Net and SIFA-Transformer as stronger backbones. More remarkably, SIFA-Transformer achieves an accuracy of 83.1% on Kinetics-400 dataset. Source code is available at https://github.com/FuchenUSTC/SIFA.
-
The advances in monocular 3D human pose estimation are dominated by supervised techniques that require large-scale 2D/3D pose annotations. Such methods often behave erratically in the absence of any provision to discard unfamiliar out-of-distribution data. To this end, we cast the 3D human pose learning as an unsupervised domain adaptation problem. We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations; a) model-free joint localization and b) model-based parametric regression. Such a design allows us to derive suitable measures to quantify prediction uncertainty at both pose and joint level granularity. While supervising only on labeled synthetic samples, the adaptation process aims to minimize the uncertainty for the unlabeled target images while maximizing the same for an extreme out-of-distribution dataset (backgrounds). Alongside synthetic-to-real 3D pose adaptation, the joint-uncertainties allow expanding the adaptation to work on in-the-wild images even in the presence of occlusion and truncation scenarios. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
-
Misinformation is now a major problem due to its potential high risks to our core democratic and societal values and orders. Out-of-context misinformation is one of the easiest and effective ways used by adversaries to spread viral false stories. In this threat, a real image is re-purposed to support other narratives by misrepresenting its context and/or elements. The internet is being used as the go-to way to verify information using different sources and modalities. Our goal is an inspectable method that automates this time-consuming and reasoning-intensive process by fact-checking the image-caption pairing using Web evidence. To integrate evidence and cues from both modalities, we introduce the concept of 'multi-modal cycle-consistency check'; starting from the image/caption, we gather textual/visual evidence, which will be compared against the other paired caption/image, respectively. Moreover, we propose a novel architecture, Consistency-Checking Network (CCN), that mimics the layered human reasoning across the same and different modalities: the caption vs. textual evidence, the image vs. visual evidence, and the image vs. caption. Our work offers the first step and benchmark for open-domain, content-based, multi-modal fact-checking, and significantly outperforms previous baselines that did not leverage external evidence.
-
Pan-sharpening aims to obtain high-resolution multispectral (MS) images for remote sensing systems and deep learning-based methods have achieved remarkable success. However, most existing methods are designed in a black-box principle, lacking sufficient interpretability. Additionally, they ignore the different characteristics of each band of MS images and directly concatenate them with panchromatic (PAN) images, leading to severe copy artifacts. To address the above issues, we propose an interpretable deep neural network, namely Memory-augmented Deep Conditional Unfolding Network with two specified core designs. Firstly, considering the degradation process, it formulates the Pan-sharpening problem as the minimization of a variational model with denoising-based prior and non-local auto-regression prior which is capable of searching the similarities between long-range patches, benefiting the texture enhancement. A novel iteration algorithm with built-in CNNs is exploited for transparent model design. Secondly, to fully explore the potentials of different bands of MS images, the PAN image is combined with each band of MS images, selectively providing the high-frequency details and alleviating the copy artifacts. Extensive experimental results validate the superiority of the proposed algorithm against other state-of-the-art methods.
-
We propose a semi-supervised network for wide-angle portraits correction. Wide-angle images often suffer from skew and distortion affected by perspective distortion, especially noticeable at the face regions. Previous deep learning based approaches need the ground-truth correction flow maps for training guidance. However, such labels are expensive, which can only be obtained manually. In this work, we design a semi-supervised scheme and build a high-quality unlabeled dataset with rich scenarios, allowing us to simultaneously use labeled and unlabeled data to improve performance. Specifically, our semi-supervised scheme takes advantage of the consistency mechanism, with several novel components such as direction and range consistency (DRC) and regression consistency (RC). Furthermore, different from the existing methods, we propose the Multi-Scale Swin-Unet (MS-Unet) based on the multi-scale swin transformer block (MSTB), which can simultaneously learn short-distance and long-distance information to avoid artifacts. Extensive experiments demonstrate that the proposed method is superior to the state-of-the-art methods and other representative baselines.
-
This paper aims to address the problem of pre-training for person re-identification (Re-ID) with noisy labels. To setup the pre-training task, we apply a simple online multi-object tracking system on raw videos of an existing unlabeled Re-ID dataset "LUPerson" and build the Noisy Labeled variant called "LUPerson-NL". Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning. In principle, joint learning of these three modules not only clusters similar examples to one prototype, but also rectifies noisy labels based on the prototype assignment. We demonstrate that learning directly from raw videos is a promising alternative for pre-training, which utilizes spatial and temporal correlations as weak supervision. This simple pre-training task provides a scalable way to learn SOTA Re-ID representations from scratch on "LUPerson-NL" without bells and whistles. For example, by applying on the same supervised Re-ID method MGN, our pre-trained model improves the mAP over the unsupervised pre-training counterpart by 5.7%, 2.2%, 2.3% on CUHK03, DukeMTMC, and MSMT17 respectively. Under the small-scale or few-shot setting, the performance gain is even more significant, suggesting a better transferability of the learned representation. Code is available at https://github.com/DengpanFu/LUPerson-NL
-
Multi-Object Tracking (MOT) is most often approached in the tracking-by-detection paradigm, where object detections are associated through time. The association step naturally leads to discrete optimization problems. As these optimization problems are often NP-hard, they can only be solved exactly for small instances on current hardware. Adiabatic quantum computing (AQC) offers a solution for this, as it has the potential to provide a considerable speedup on a range of NP-hard optimization problems in the near future. However, current MOT formulations are unsuitable for quantum computing due to their scaling properties. In this work, we therefore propose the first MOT formulation designed to be solved with AQC. We employ an Ising model that represents the quantum mechanical system implemented on the AQC. We show that our approach is competitive compared with state-of-the-art optimization-based approaches, even when using of-the-shelf integer programming solvers. Finally, we demonstrate that our MOT problem is already solvable on the current generation of real quantum computers for small examples, and analyze the properties of the measured solutions.
-
Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are often disturbed by Non-Pedestrian Occlusions (NPO) and Non-Target Pedestrians (NTP). Previous methods mainly focus on increasing the model's robustness against NPO while ignoring feature contamination from NTP. In this paper, we propose a novel Feature Erasing and Diffusion Network (FED) to simultaneously handle challenges from NPO and NTP. Specifically, aided by the NPO augmentation strategy that simulates NPO on holistic pedestrian images and generates precise occlusion masks, NPO features are explicitly eliminated by our proposed Occlusion Erasing Module (OEM). Subsequently, we diffuse the pedestrian representations with other memorized features to synthesize the NTP characteristics in the feature space through the novel Feature Diffusion Module (FDM). With the guidance of the occlusion scores from OEM, the feature diffusion process is conducted on visible body parts, thereby improving the quality of the synthesized NTP characteristics. We can greatly improve the model's perception ability towards TP and alleviate the influence of NPO and NTP by jointly optimizing OEM and FDM. Furthermore, the proposed FDM works as an auxiliary module for training and will not be engaged in the inference phase, thus with high flexibility. Experiments on occluded and holistic person ReID benchmarks demonstrate the superiority of FED over state-of-the-art methods.
-
Can an autonomous agent navigate in a new environment without building an explicit map? For the task of PointGoal navigation ('Go to (x, y)') under idealized settings (no RGB-D and actuation noise, perfect GPS+Compass), the answer is a clear 'yes' - map-less neural models composed of task-agnostic components (CNNs and RNNs) trained with large-scale reinforcement learning achieve 100% Success on a standard dataset (Gibson). However, for PointNav in a realistic setting (RGB-D and actuation noise, no GPS+Compass), this is an open question; one we tackle in this paper. The strongest published result for this task is 71.7% Success. First, we identify the main (perhaps, only) cause of the drop in performance: absence of GPS+Compass. An agent with perfect GPS+Compass faced with RGB-D sensing and actuation noise achieves 99.8% Success (Gibson-v2 val). This suggests that (to paraphrase a meme) robust visual odometry is all we need for realistic PointNav; if we can achieve that, we can ignore the sensing and actuation noise. With that as our operating hypothesis, we scale dataset size, model size, and develop human-annotation-free data-augmentation techniques to train neural models for visual odometry. We advance state of the art on the Habitat Realistic PointNav Challenge - SPL by 40% (relative), 53 to 74, and Success by 31% (relative), 71 to 94. While our approach does not saturate or 'solve' this dataset, this strong improvement combined with promising zero-shot sim2real transfer (to a LoCoBot robot) provides evidence consistent with the hypothesis that explicit mapping may not be necessary for navigation, even in realistic setting.
-
The large-scale whole-slide images (WSIs) facilitate the learning-based computational pathology methods. However, the gigapixel size of WSIs makes it hard to train a conventional model directly. Current approaches typically adopt multiple-instance learning (MIL) to tackle this problem. Among them, MIL combined with graph convolutional network (GCN) is a significant branch, where the sampled patches are regarded as the graph nodes to further discover their correlations. However, it is difficult to build correspondence across patches from different WSIs. Therefore, most methods have to perform non-ordered node pooling to generate the bag-level representation. Direct non-ordered pooling will lose much structural and contextual information, such as patch distribution and heterogeneous patterns, which is critical for WSI representation. In this paper, we propose a hierarchical global-to-local clustering strategy to build a Node-Aligned GCN (NAGCN) to represent WSI with rich local structural information as well as global distribution. We first deploy a global clustering operation based on the instance features in the dataset to build the correspondence across different WSIs. Then, we perform a local clustering-based sampling strategy to select typical instances belonging to each cluster within the WSI. Finally, we employ the graph convolution to obtain the representation. Since our graph construction strategy ensures the alignment among different WSIs, WSI-level representation can be easily generated and used for the subsequent classification. The experiment results on two cancer subtype classification datasets demonstrate our method achieves better performance compared with the state-of-the-art methods.
-
Class-agnostic counting (CAC) aims to count all instances in a query image given few exemplars. A standard pipeline is to extract visual features from exemplars and match them with query images to infer object counts. Two essential components in this pipeline are feature representation and similarity metric. Existing methods either adopt a pretrained network to represent features or learn a new one, while applying a naive similarity metric with fixed inner product. We find this paradigm leads to noisy similarity matching and hence harms counting performance. In this work, we propose a similarity-aware CAC framework that jointly learns representation and similarity metric. We first instantiate our framework with a naive baseline called Bilinear Matching Network (BMNet), whose key component is a learnable bilinear similarity metric. To further embody the core of our framework, we extend BMNet to BMNet+ that models similarity from three aspects: 1) representing the instances via their self-similarity to enhance feature robustness against intra-class variations; 2) comparing the similarity dynamically to focus on the key patterns of each exemplar; 3) learning from a supervision signal to impose explicit constraints on matching results. Extensive experiments on a recent CAC dataset FSC147 show that our models significantly outperform state-of-the-art CAC approaches. In addition, we also validate the cross-dataset generality of BMNet and BMNet+ on a car counting dataset CARPK. Code is at tiny.one/BMNet
-
We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training of video models. Our approach first randomly masks out a portion of the input sequence and then predicts the feature of the masked regions. We study five different types of features and find Histograms of Oriented Gradients (HOG), a hand-crafted feature descriptor, works particularly well in terms of both performance and efficiency. We observe that the local contrast normalization in HOG is essential for good results, which is in line with earlier work using HOG for visual recognition. Our approach can learn abundant visual knowledge and drive large-scale Transformer-based models. Without using extra model weights or supervision, MaskFeat pre-trained on unlabeled videos achieves unprecedented results of 86.7% with MViTv2-L on Kinetics-400, 88.3% on Kinetics-600, 80.4% on Kinetics-700, 38.8 mAP on AVA, and 75.0% on SSv2. MaskFeat further generalizes to image input, which can be interpreted as a video with a single frame and obtains competitive results on ImageNet.
-
Neural implicit functions have recently shown promising results on surface reconstructions from multiple views. However, current methods still suffer from excessive time complexity and poor robustness when reconstructing unbounded or complex scenes. In this paper, we present RegSDF, which shows that proper point cloud supervisions and geometry regularizations are sufficient to produce high-quality and robust reconstruction results. Specifically, RegSDF takes an additional oriented point cloud as input, and optimizes a signed distance field and a surface light field within a differentiable rendering framework. We also introduce the two critical regularizations for this optimization. The first one is the Hessian regularization that smoothly diffuses the signed distance values to the entire distance field given noisy and incomplete input. And the second one is the minimal surface regularization that compactly interpolates and extrapolates the missing geometry. Extensive experiments are conducted on DTU, BlendedMVS, and Tanks and Temples datasets. Compared with recent neural surface reconstruction approaches, RegSDF is able to reconstruct surfaces with fine details even for open scenes with complex topologies and unstructured camera trajectories.
-
Few-shot learning (FSL) has received a lot of attention due to its remarkable ability to adapt to novel classes. Although many techniques have been proposed for FSL, they mostly focus on improving FSL backbones. Some works also focus on learning on top of the features generated by these backbones to adapt them to novel classes. We present an unsupErvised discriminAnt Subspace lEarning (EASE) that improves transductive few-shot learning performance by learning a linear projection onto a subspace built from features of the support set and the unlabeled query set in the test time. Specifically, based on the support set and the unlabeled query set, we generate the similarity matrix and the dissimilarity matrix based on the structure prior for the proposed EASE method, which is efficiently solved with SVD. We also introduce conStraIned wAsserstein MEan Shift clustEring (SIAMESE) which extends Sinkhorn K-means by incorporating labeled support samples. SIAMESE works on the features obtained from EASE to estimate class centers and query predictions. On the mini-ImageNet, tiered-ImageNet, CIFAR-FS, CUB and OpenMIC benchmarks, both steps significantly boost the performance in transductive FSL and semi-supervised FSL.
-
Action recognition is a challenging task since the attributes of objects as well as their relationships change constantly in the video. Existing methods mainly use object-level graphs or scene graphs to represent the dynamics of objects and relationships, but ignore modeling the fine-grained relationship transitions directly. In this paper, we propose an Object-Relation Reasoning Graph (OR2G) for reasoning about action in videos. By combining an object-level graph (OG) and a relation-level graph (RG), the proposed OR2G catches the attribute transitions of objects and reasons about the relationship transitions between objects simultaneously. In addition, a graph aggregating module (GAM) is investigated by applying the multi-head edge-to-node message passing operation. GAM feeds back the information from the relation node to the object node and enhances the coupling between the object-level graph and the relation-level graph. Experiments in video action recognition demonstrate the effectiveness of our approach when compared with the state-of-the-art methods.
-
Typical vision backbones manipulate structured features. As a compromise, semantic segmentation has long been modeled as per-point prediction on dense regular grids. In this work, we present a novel and efficient modeling that starts from interpreting the image as a tessellation of learnable regions, each of which has flexible geometrics and carries homogeneous semantics. To model region-wise context, we exploit Transformer to encode regions in a sequence-to-sequence manner by applying multi-layer self-attention on the region embeddings, which serve as proxies of specific regions. Semantic segmentation is now carried out as per-region prediction on top of the encoded region embeddings using a single linear classifier, where a decoder is no longer needed. The proposed RegProxy model discards the common Cartesian feature layout and operates purely at region level. Hence, it exhibits the most competitive performance-efficiency trade-off compared with the conventional dense prediction methods. For example, on ADE20K, the small-sized RegProxy-S/16 outperforms the best CNN model using 25% parameters and 4% computation, while the largest RegProxy-L/16 achieves 52.9mIoU which outperforms the state-of-the-art by 2.1% with fewer resources. Codes and models are available at https://github.com/YiF-Zhang/RegionProxy.
-
Visual degradations caused by motion blur, raindrop, rain, snow, illumination, and fog deteriorate image quality and, subsequently, the performance of perception algorithms deployed in outdoor conditions. While degradation-specific image restoration techniques have been extensively studied, such algorithms are domain sensitive and fail in real scenarios where multiple degradations exist simultaneously. This makes a case for blind image restoration and reconstruction algorithms as practically relevant. However, the absence of a dataset diverse enough to encapsulate all variations hinders development for such an algorithm. In this paper, we utilize a synthetic degradation model that recursively applies sets of random degradations to generate naturalistic degradation images of varying complexity, which are used as input. Furthermore, as the degradation intensity can vary across an image, the spatially invariant convolutional filter cannot be applied for all degradations. Hence to enable spatial variance during image restoration and reconstruction, we design a transformer-based architecture to benefit from the long-range dependencies. In addition, to reduce the computational cost of transformers, we propose a multi-branch structure coupled with modifications such as a complimentary feature selection mechanism and the replacement of a feed-forward network with lightweight multiscale convolutions. Finally, to improve restoration and reconstruction, we integrate an auxiliary decoder branch to predict the degradation mask to ensure the underlying network can localize the degradation information. From empirical analysis on 10 datasets covering rain drop removal, deraining, dehazing, image enhancement, and deblurring, we demonstrate the efficacy of the proposed approach while obtaining SoTA performance.
-
In this paper, we present an end-to-end instance segmentation method that regresses a polygonal boundary for each object instance. This sparse, vectorized boundary representation for objects, while attractive in many downstream computer vision tasks, quickly runs into issues of parity that need to be addressed: parity in supervision and parity in performance when compared to existing pixel-based methods. This is due in part to object instances being annotated with ground-truth in the form of polygonal boundaries or segmentation masks, yet being evaluated in a convenient manner using only segmentation masks. Our method, named BoundaryFormer, is a Transformer based architecture that directly predicts polygons yet uses instance mask segmentations as the ground-truth supervision for computing the loss. We achieve this by developing an end-to-end differentiable model that solely relies on supervision within the mask space through differentiable rasterization. BoundaryFormer matches or surpasses the Mask R-CNN method in terms of instance segmentation quality on both COCO and Cityscapes while exhibiting significantly better transferability across datasets.
-
We present FaceVerse, a fine-grained 3D Neural Face Model, which is built from hybrid East Asian face datasets containing 60K fused RGB-D images and 2K high-fidelity 3D head scan models. A novel coarse-to-fine structure is proposed to take better advantage of our hybrid dataset. In the coarse module, we generate a base parametric model from large-scale RGB-D images, which is able to predict accurate rough 3D face models in different genders, ages, etc. Then in the fine module, a conditional StyleGAN architecture trained with high-fidelity scan models is introduced to enrich elaborate facial geometric and texture details. Note that different from previous methods, our base and detailed modules are both changeable, which enables an innovative application of adjusting both the basic attributes and the facial details of 3D face models. Furthermore, we propose a single-image fitting framework based on differentiable rendering. Rich experiments show that our method outperforms the state-of-the-art methods.
-
In Class Incremental Learning (CIL), a classification model is progressively trained at each incremental step on an evolving dataset of new classes, while at the same time, it is required to preserve knowledge of all the classes observed so far. Prototypical representations can be leveraged to model feature distribution for the past data and inject information of former classes in later incremental steps without resorting to stored exemplars. However, if not updated, those representations become increasingly outdated as the incremental learning progresses with new classes. To address the aforementioned problems, we propose a framework which aims to (i) model the semantic drift by learning the relationship between representations of past and novel classes among incremental steps, and (ii) estimate the feature drift, defined as the evolution of the representations learned by models at each incremental step. Semantic and feature drifts are then jointly exploited to infer up-to-date representations of past classes (evanescent representations), and thereby infuse past knowledge into incremental training. We experimentally evaluate our framework achieving exemplar-free SotA results on multiple benchmarks. In the ablation study, we investigate nontrivial relationships between evanescent representations and models.
-
Nowadays, robotics, AR, and 3D modeling applications attract considerable attention to single-view depth estimation (SVDE) as it allows estimating scene geometry from a single RGB image. Recent works have demonstrated that the accuracy of an SVDE method hugely depends on the diversity and volume of the training data. However, RGB-D datasets obtained via depth capturing or 3D reconstruction are typically small, synthetic datasets are not photorealistic enough, and all these datasets lack diversity. The large-scale and diverse data can be sourced from stereo images or stereo videos from the web. Typically being uncalibrated, stereo data provides disparities up to unknown shift (geometrically incomplete data), so stereo-trained SVDE methods cannot recover 3D geometry. It was recently shown that the distorted point clouds obtained with a stereo-trained SVDE method can be corrected with additional point cloud modules (PCM) separately trained on the geometrically complete data. On the contrary, we propose GP2, General-Purpose and Geometry-Preserving training scheme, and show that conventional SVDE models can learn correct shifts themselves without any post-processing, benefiting from using stereo data even in the geometry-preserving setting. Through experiments on different dataset mixtures, we prove that GP2-trained models outperform methods relying on PCM in both accuracy and speed, and report the state-of-the-art results in the general-purpose geometry-preserving SVDE. Moreover, we show that SVDE models can learn to predict geometrically correct depth even when geometrically complete data comprises the minor part of the training set.
-
Gesture recognition plays an important role in natural human-computer interaction and sign language recognition. Existing research on gesture recognition is limited to close-range interaction such as vehicle gesture control and face-to-face communication. To apply gesture recognition to long-distance interactive scenes such as meetings and smart homes, a large RGB-D video dataset LD-ConGR is established in this paper. LD-ConGR is distinguished from existing gesture datasets by its long-distance gesture collection, fine-grained annotations, and high video quality. Specifically, 1) the farthest gesture provided by the LD-ConGR is captured 4m away from the camera while existing gesture datasets collect gestures within 1m from the camera; 2) besides the gesture category, the temporal segmentation of gestures and hand location are also annotated in LD-ConGR; 3) videos are captured at high resolution (1280x720 for color streams and 640x576 for depth streams) and high frame rate (30 fps). On top of the LD-ConGR, a series of experimental and studies are conducted, and the proposed gesture region estimation and key frame sampling strategies are demonstrated to be effective in dealing with long-distance gesture recognition and the uncertainty of gesture duration. The dataset and experimental results presented in this paper are expected to boost the research of long-distance gesture recognition. The dataset is available at https://github.com/Diananini/LD-ConGR-CVPR2022.
-
Existing work on VQA explores data augmentation to achieve better generalization by perturbing the images in the dataset or modifying the existing questions and answers. While these methods exhibit good performance, the diversity of the questions and answers are constrained by the available image set. In this work we explore using synthetic computer-generated data to fully control the visual and language space, allowing us to provide more diverse scenarios. We quantify the effect of synthetic data in real-world VQA benchmarks and to which extent it produces results that generalize to real data. By exploiting 3D and physics simulation platforms, we provide a pipeline to generate synthetic data to expand and replace type-specific questions and answers without risking the exposure of sensitive or personal data that might be present in real images. We offer a comprehensive analysis while expanding existing hyper-realistic datasets to be used for VQA. We also propose Feature Swapping (F-SWAP) -- where we randomly switch object-level features during training to make a VQA model more domain invariant. We show that F-SWAP is effective for enhancing a currently existing VQA dataset of real images without compromising on the accuracy to answer existing questions in the dataset.
-
Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. However, it remains a significant challenge for current unsupervised methods when there is a large pose gap between the objects in the source and driving images. In this paper, a new end-to-end unsupervised motion transfer framework is proposed to overcome such issue. Firstly, we propose thin-plate spline motion estimation to produce a more flexible optical flow, which warps the feature maps of the source image to the feature domain of the driving image. Secondly, in order to restore the missing regions more realistically, we leverage multi-resolution occlusion masks to achieve more effective feature fusion. Finally, additional auxiliary loss functions are designed to ensure that there is a clear division of labor in the network modules, encouraging the network to generate high-quality images. Our method can animate a variety of objects, including talking faces, human bodies, and pixel animations. Experiments demonstrate that our method performs better on most benchmarks than the state of the art with visible improvements in pose-related metrics.
-
We propose a novel approach aimed at object and semantic scene completion from a partial scan represented as a 3D point cloud. Our architecture relies on three novel layers that are used successively within an encoder-decoder structure and specifically developed for the task at hand. The first one carries out feature extraction by matching the point features to a set of pre-trained local descriptors. Then, to avoid losing individual descriptors as part of standard operations such as max-pooling, we propose an alternative neighbor-pooling operation that relies on adopting the feature vectors with the highest activations. Finally, up-sampling in the decoder modifies our feature extraction in order to increase the output dimension. While this model is already able to achieve competitive results with the state of the art, we further propose a way to increase the versatility of our approach to process point clouds. To this aim, we introduce a second model that assembles our layers within a transformer architecture. We evaluate both architectures on object and indoor scene completion tasks, achieving state-of-the-art performance.
-
Interactive object understanding, or what we can do to objects and how is a long-standing goal of computer vision. In this paper, we tackle this problem through observation of human hands in in-the-wild egocentric videos. We demonstrate that observation of what human hands interact with and how can provide both the relevant data and the necessary supervision. Attending to hands, readily localizes and stabilizes active objects for learning and reveals places where interactions with objects occur. Analyzing the hands shows what we can do to objects and how. We apply these basic principles on the EPIC-KITCHENS dataset, and successfully learn state-sensitive features, and object affordances (regions of interaction and afforded grasps), purely by observing hands in egocentric videos.
-
Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique that approximately solves a robust optimization problem to minimize the worst-case loss and is widely regarded as the most effective defense against such attacks. Due to the high computation time for generating strong adversarial examples in the AT process, single-step approaches have been proposed to reduce training time. However, these methods suffer from catastrophic overfitting where adversarial accuracy drops during training, and although improvements have been proposed, they increase training time and robustness is far from that of multi-step AT. We develop a theoretical framework for adversarial training with FW optimization (FW-AT) that reveals a geometric connection between the loss landscape and the distortion of l-inf FW attacks (the attack's l-2 norm). Specifically, we analytically show that high distortion of FW attacks is equivalent to small gradient variation along the attack path. It is then experimentally demonstrated on various deep neural network architectures that l-inf attacks against robust models achieve near maximal l-2 distortion, while standard networks have lower distortion. Furthermore, it is experimentally shown that catastrophic overfitting is strongly correlated with low distortion of FW attacks. This mathematical transparency differentiates FW from the more popular Projected Gradient Descent (PGD) optimization. To demonstrate the utility of our theoretical framework we develop FW-AT-Adapt, a novel adversarial training algorithm which uses a simple distortion measure to adapt the number of attack steps during training to increase efficiency without compromising robustness. FW-AT-Adapt provides training time on par with single-step fast AT methods and improves closing the gap between fast AT methods and multi-step PGD-AT with minimal loss in adversarial accuracy in white-box and black-box settings.
-
Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region. But, currently, this robustness comes at a cost of degraded standard accuracies and slower inference times. We demonstrate how using vision transformers enables significantly better certified patch robustness that is also more computationally efficient and does not incur a substantial drop in standard accuracy. These improvements stem from the inherent ability of the vision transformer to gracefully handle largely masked images.
-
Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the model complexity and might fail in case of occlusion or complex motion, resulting in serious distortion and artifacts. In this paper, we propose to explore the role of explicit temporal difference modeling in both LR and HR space. Instead of directly feeding consecutive frames into a VSR model, we propose to compute the temporal difference between frames and divide those pixels into two subsets according to the level of difference. They are separately processed with two branches of different receptive fields in order to better extract complementary information. To further enhance the super-resolution result, not only spatial residual features are extracted, but the difference between consecutive frames in high-frequency domain is also computed. It allows the model to exploit intermediate SR results in both future and past to refine the current SR output. The difference at different time steps could be cached such that information from further distance in time could be propagated to the current frame for refinement. Experiments on several video super-resolution benchmark datasets demonstrate the effectiveness of the proposed method and its favorable performance against state-of-the-art methods.
-
Deep neural networks (DNNs) have witnessed great successes in semantic segmentation, which requires a large number of labeled data for training. We present a novel learning framework called Uncertainty guided Cross-head Co-training (UCC) for semi-supervised semantic segmentation. Our framework introduces weak and strong augmentations within a shared encoder to achieve co-training, which naturally combines the benefits of consistency and self-training. Every segmentation head interacts with its peers and, the weak augmentation result is used for supervising the strong. The consistency training samples' diversity can be boosted by Dynamic Cross-Set Copy-Paste (DCSCP), which also alleviates the distribution mismatch and class imbalance problems. Moreover, our proposed Uncertainty Guided Re-weight Module (UGRM) enhances the self-training pseudo labels by suppressing the effect of the low-quality pseudo labels from its peer via modeling uncertainty. Extensive experiments on Cityscapes and PASCAL VOC 2012 demonstrate the effectiveness of our UCC, our approach significantly outperforms other state-of-the-art semi-supervised semantic segmentation methods. It achieves 77.17%, 76.49% mIoU on Cityscapes and PASCAL VOC 2012 datasets respectively under 1/16 protocols, which are +10.1%, +7.91% better than the supervised baseline.
-
Capturing and rendering life-like hair is particularly challenging due to its fine geometric structure, complex physical interaction and the non-trivial visual appearance that must be captured. Yet, it is a critical component to create believable avatars. In this paper, we address the aforementioned problems: 1) we use a novel, volumetric hair representation that is composed of thousands of primitives. Each primitive can be rendered efficiently, yet realistically, by building on the latest advances in neural rendering. 2) To have a reliable control signal, we present a novel way of tracking hair on strand level. To keep the computational effort manageable, we use guide hairs and classic techniques to expand those into a dense head of hair. 3) To better enforce temporal consistency and generalization ability of our model, we further optimize the 3D scene flow of our representation with multiview optical flow, using volumetric raymarching. Our method can not only create realistic renders of recorded multi-view sequences, but also create renderings for new hair configurations by providing new control signals. We compare our method with existing work on viewpoint synthesis and drivable animation and achieve state-of-the-art results. https://ziyanw1.github.io/hvh/
-
Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI). While recent research showed that 2D neural networks are able to outperform previous traditional State-of-the-Art (SOTA) methods on correcting ToF-Data, little research on learning-based approaches has been done to make direct use of the 3D information present in depth images. In this paper, we propose an iterative correcting approach operating in 3D space, that is designed to learn on 2.5D data by enabling 3D point convolutions to correct the points' positions along the view direction. As labeled real world data is scarce for this task, we further train our network with a self-training approach on unlabeled real world data to account for real world statistics. We demonstrate that our method is able to outperform SOTA methods on several datasets, including two real world datasets and a new large-scale synthetic data set introduced in this paper.
-
Visual Geo-localization (VG) is the task of estimating the position where a given photo was taken by comparing it with a large database of images of known locations. To investigate how existing techniques would perform on a real-world city-wide VG application, we build San Francisco eXtra Large, a new dataset covering a whole city and providing a wide range of challenging cases, with a size 30x bigger than the previous largest dataset for visual geo-localization. We find that current methods fail to scale to such large datasets, therefore we design a new highly scalable training technique, called CosPlace, which casts the training as a classification problem avoiding the expensive mining needed by the commonly used contrastive learning. We achieve state-of-the-art performance on a wide range of datasets, and find that CosPlace is robust to heavy domain changes. Moreover, we show that, compared to previous state of the art, CosPlace requires roughly 80% less GPU memory at train time and achieves better results with 8x smaller descriptors, paving the way for city-wide real-world visual geo-localization. Dataset, code and trained models are available for research purposes at https://github.com/gmberton/CosPlace.
-
Multi-modality (i.e., multi-sensor) data is widely used in various vision tasks for more accurate or robust perception. However, the increased data modalities bring new challenges for data storage and transmission. The existing data compression approaches usually adopt individual codecs for each modality without considering the correlation between different modalities. This work proposes a multi-modality compression framework for infrared and visible image pairs by exploiting the cross-modality redundancy. Specifically, given the image in the reference modality (e.g., the infrared image), we use the channel-wise alignment module to produce the aligned features based on the affine transform. Then the aligned feature is used as the context information for compressing the image in the current modality (e.g., the visible image), and the corresponding affine coefficients are losslessly compressed at negligible cost. Furthermore, we introduce the Transformer-based spatial alignment module to exploit the correlation between the intermediate features in the decoding procedures for different modalities. Our framework is very flexible and easily extended for multi-modality video compression. Experimental results show our proposed framework outperforms the traditional and learning-based single modality compression methods on the FLIR and KAIST datasets.
-
Deep Neural Networks (DNNs) are known to make overconfident mistakes, which makes their use problematic in safety-critical applications. State-of-the-art (SOTA) calibration techniques improve on the confidence of predicted labels alone, and leave the confidence of non-max classes (e.g. top-2, top-5) uncalibrated. Such calibration is not suitable for label refinement using post-processing. Further, most SOTA techniques learn a few hyper-parameters post-hoc, leaving out the scope for image, or pixel specific calibration. This makes them unsuitable for calibration under domain shift, or for dense prediction tasks like semantic segmentation. In this paper, we argue for intervening at the train time itself, so as to directly produce calibrated DNN models. We propose a novel auxiliary loss function: Multi-class Difference in Confidence and Accuracy (MDCA), to achieve the same. MDCA can be used in conjunction with other application/task specific loss functions. We show that training with MDCA leads to better calibrated models in terms of Expected Calibration Error (ECE), and Static Calibration Error (SCE) on image classification, and segmentation tasks. We report ECE(SCE) score of 0.72 (1.60) on the CIFAR100 dataset, in comparison to 1.90 (1.71) by the SOTA. Under domain shift, a ResNet-18 model trained on PACS dataset using MDCA gives a average ECE(SCE) score of 19.7 (9.7) across all domains, compared to 24.2 (11.8) by the SOTA. For segmentation task, we report a 2x reduction in calibration error on PASCAL-VOC dataset in comparison to Focal Loss. Finally, MDCA training improves calibration even on imbalanced data, and for natural language classification tasks.
-
Vision transformers (ViTs) have gained increasing popularity as they are commonly believed to own higher modeling capacity and representation flexibility, than traditional convolutional networks. However, it is questionable whether such potential has been fully unleashed in practice, as the learned ViTs often suffer from over-smoothening, yielding likely redundant models. Recent works made preliminary attempts to identify and alleviate such redundancy, e.g., via regularizing embedding similarity or re-injecting convolution-like structures. However, a "head-to-toe assessment" regarding the extent of redundancy in ViTs, and how much we could gain by thoroughly mitigating such, has been absent for this field. This paper, for the first time, systematically studies the ubiquitous existence of redundancy at all three levels: patch embedding, attention map, and weight space. In view of them, we advocate a principle of diversity for training ViTs, by presenting corresponding regularizers that encourage the representation diversity and coverage at each of those levels, that enabling capturing more discriminative information. Extensive experiments on ImageNet with a number of ViT backbones validate the effectiveness of our proposals, largely eliminating the observed ViT redundancy and significantly boosting the model generalization. For example, our diversified DeiT obtains 0.70% 1.76% accuracy boosts on ImageNet with highly reduced similarity. Our codes are fully available in https://github.com/VITA-Group/Diverse-ViT.
-
Integrating a foreground object into a background scenewith illumination harmonization is an important but chal-lenging task in computer vision and augmented reality community. Existing methods mainly focus on foreground andbackground appearance consistency or the foreground object shadow generation, which rarely consider global appearance and illumination harmonization. In this paper,we formulate seamless illumination harmonization as anillumination exchange and aggregation problem. Specifi-cally, we firstly apply a physically-based rendering methodto construct a large-scale, high-quality dataset (named IH)for our task, which contains various types of foreground ob-jects and background scenes with different lighting conditions. Then, we propose a deep image-based illuminationharmonization GAN framework named DIH-GAN, whichmakes full use of a multi-scale attention mechanism and illumination exchange strategy to directly infer mapping rela-tionship between the inserted foreground object and the corresponding background scene. Meanwhile, we also use adversarial learning strategy to further refine the illuminationharmonization result. Our method can not only achieve har-monious appearance and illumination for the foregroundobject but also can generate compelling shadow cast bythe foreground object. Comprehensive experiments on bothour IH dataset and real-world images show that our pro-posed DIH-GAN provides a practical and effective solutionfor image-based object illumination harmonization editing,and validate the superiority of our method against state-of-the-art methods.
-
Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input source: the feature, the logit, or the softmax probability. However, the immense diversity of the OOD examples makes such methods fragile. There are OOD samples that are easy to identify in the feature space while hard to distinguish in the logit space and vice versa. Motivated by this observation, we propose a novel OOD scoring method named Virtual-logit Matching (ViM), which combines the class-agnostic score from feature space and the In-Distribution (ID) class-dependent logits. Specifically, an additional logit representing the virtual OOD class is generated from the residual of the feature against the principal space, and then matched with the original logits by a constant scaling. The probability of this virtual logit after softmax is the indicator of OOD-ness. To facilitate the evaluation of large-scale OOD detection in academia, we create a new OOD dataset for ImageNet-1K, which is human-annotated and is 8.8x the size of existing datasets. We conducted extensive experiments, including CNNs and vision transformers, to demonstrate the effectiveness of the proposed ViM score. In particular, using the BiT-S model, our method gets an average AUROC 90.91% on four difficult OOD benchmarks, which is 4% ahead of the best baseline. Code and dataset are available at https://github.com/haoqiwang/vim.
-
The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e. g. images, videos) and in low-data regimes. In this paper, we propose a novel method for batch AL called ALFA-Mix. We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions resulting from interventions on their representations. We construct interpolations between representations of labelled and unlabelled instances then examine the predicted labels. We show that inconsistencies in these predictions help discovering features that the model is unable to recognise in the unlabelled instances. We derive an efficient implementation based on a closed-form solution to the optimal interpolation causing changes in predictions. Our method outperforms all recent AL approaches in 30 different settings on 12 benchmarks of images, videos, and non-visual data. The improvements are especially significant in low-data regimes and on self-trained vision transformers, where ALFA-Mix outperforms the state-of-the-art in 59% and 43% of the experiments respectively.
-
Accurate facial landmarks are essential prerequisites for many tasks related to human faces. In this paper, an accurate facial landmark detector is proposed based on cascaded transformers. We formulate facial landmark detection as a coordinate regression task such that the model can be trained end-to-end. With self-attention in transformers, our model can inherently exploit the structured relationships between landmarks, which would benefit landmark detection under challenging conditions such as large pose and occlusion. During cascaded refinement, our model is able to extract the most relevant image features around the target landmark for coordinate prediction, based on deformable attention mechanism, thus bringing more accurate alignment. In addition, we propose a novel decoder that refines image features and landmark positions simultaneously. With few parameter increasing, the detection performance improves further. Our model achieves new state-of- the-art performance on several standard facial landmark detection benchmarks, and shows good generalization ability in cross-dataset evaluation.
-
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover, the model's judgment becomes noisier in real-world applications with extensive out-of-distribution data. To address this issue, we propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL), which is a drop-in helper to improve the pseudo-label quality and enhance the model's robustness in the real-world setting. Rather than treating real-world data as a union set, our method separately handles reliable in-distribution data with class-wise clustering for blending into downstream tasks and noisy out-of-distribution data with image-wise contrastive for better generalization. Furthermore, by applying target re-weighting, we successfully emphasize clean label learning and simultaneously reduce noisy label learning. Despite its simplicity, our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 and STL10. On the real-world dataset Semi-iNat 2021, we improve FixMatch by 9.80% and CoMatch by 3.18%. Code is available https://github.com/TencentYoutuResearch/Classification-SemiCLS.
-
We address the problem of map sparsification for longterm visual localization. A commonly employed assumption in map sparsification is that the pre-build map and the later capture localization query are consistent. However, this assumption can be easily violated in the dynamic world. Additionally, the map size grows as new data accumulate through time, causing large data overhead in the long term. In this paper, we aim to overcome the environmental changes and reduce the map size at the same time by selecting points that are valuable to future localization. Inspired by the recent progress in Graph Neural Network (GNN), we propose the first work that models SfM maps as heterogeneous graphs and predicts 3D point importance scores with a GNN, which enables us to directly exploit the rich information in the SfM map graph. Two novel supervisions are proposed: 1) a data-fitting term for selecting valuable points to future localization based on training queries; 2) a K-Cover term for selecting sparse points with full-map coverage. In the experiments on a long-term dataset with environmental changes, our method selected map points on stable and widely visible structures and outperformed baselines in localization performance. This work novelly connects SfM maps with the abundant modern GNN techniques and opens a new research avenue forward.
-
This work studies the bias issue of pseudo-labeling, a natural phenomenon that widely occurs but often overlooked by prior research. Pseudo-labels are generated when a classifier trained on source data is transferred to unlabeled target data. We observe heavy long-tailed pseudo-labels when a semi-supervised learning model FixMatch predicts labels on the unlabeled set even though the unlabeled data is curated to be balanced. Without intervention, the training model inherits the bias from the pseudo-labels and end up being sub-optimal. To eliminate the model bias, we propose a simple yet effective method DebiasMatch, comprising of an adaptive debiasing module and an adaptive marginal loss. The strength of debiasing and the size of margins can be automatically adjusted by making use of an online updated queue. Benchmarked on ImageNet-1K, DebiasMatch significantly outperforms previous state-of-the-arts by more than 26% and 10.5% on semi-supervised learning (0.2% annotated data) and zero-shot learning tasks respectively.
-
6-DoF object pose estimation from a monocular image is challenging, and a post-refinement procedure is generally needed for high-precision estimation. In this paper, we propose a framework based on a recurrent neural network (RNN) for object pose refinement, which is robust to erroneous initial poses and occlusions. During the recurrent iterations, object pose refinement is formulated as a non-linear least squares problem based on the estimated correspondence field (between a rendered image and the observed image). The problem is then solved by a differentiable Levenberg-Marquardt (LM) algorithm enabling end-to-end training. The correspondence field estimation and pose refinement are conducted alternatively in each iteration to recover the object poses. Furthermore, to improve the robustness to occlusion, we introduce a consistency-check mechanism based on the learned descriptors of the 3D model and observed 2D images, which downweights the unreliable correspondences during pose optimization. Extensive experiments on LINEMOD, Occlusion-LINEMOD, and YCB-Video datasets validate the effectiveness of our method and demonstrate state-of-the-art performance.
-
Digitizing physical objects into the virtual world has the potential to unlock new research and applications in embodied AI and mixed reality. This work focuses on recreating interactive digital twins of real-world articulated objects, which can be directly imported into virtual environments. We introduce Ditto to learn articulation model estimation and 3D geometry reconstruction of an articulated object through interactive perception. Given a pair of visual observations of an articulated object before and after interaction, Ditto reconstructs part-level geometry and estimates the articulation model of the object. We employ implicit neural representations for joint geometry and articulation modeling. Our experiments show that Ditto effectively builds digital twins of articulated objects in a category-agnostic way. We also apply Ditto to real-world objects and deploy the recreated digital twins in physical simulation. Code and additional results are available at https://ut-austin-rpl.github.io/Ditto/
-
Learning spatial-temporal relation among multiple actors is crucial for group activity recognition. Different group activities often show the diversified interactions between actors in the video. Hence, it is often difficult to model complex group activities from a single view of spatial-temporal actor evolution. To tackle this problem, we propose a distinct Dual-path Actor Interaction (Dual-AI) framework, which flexibly arranges spatial and temporal transformers in two complementary orders, enhancing actor relations by integrating merits from different spatio-temporal paths. Moreover, we introduce a novel Multi-scale Actor Contrastive Loss (MAC-Loss) between two interactive paths of Dual-AI. Via self-supervised actor consistency in both frame and video levels, MAC-Loss can effectively distinguish individual actor representations to reduce action confusion among different actors. Consequently, our Dual-AI can boost group activity recognition by fusing such discriminative features of different actors. To evaluate the proposed approach, we conduct extensive experiments on the widely used benchmarks, including Volleyball, Collective Activity, and NBA datasets. The proposed Dual-AI achieves state-of-the-art performance on all these datasets. It is worth noting the proposed Dual-AI with 50% training data outperforms a number of recent approaches with 100% training data. This confirms the generalization power of Dual-AI for group activity recognition, even under the challenging scenarios of limited supervision.
-
In many real-life image analysis applications, particularly in biomedical research domains, the objects of interest undergo multiple transformations that alters their visual properties while keeping the semantic content unchanged. Disentangling images into semantic content factors and transformations can provide significant benefits into many domain-specific image analysis tasks. To this end, we propose a generic unsupervised framework, Harmony, that simultaneously and explicitly disentangles semantic content from multiple parameterized transformations. Harmony leverages a simple cross-contrastive learning framework with multiple explicitly parameterized latent representations to disentangle content from transformations. To demonstrate the efficacy of Harmony, we apply it to disentangle image semantic content from several parameterized transformations (rotation, translation, scaling, and contrast). Harmony achieves significantly improved disentanglement over the baseline models on several image datasets of diverse domains. With such disentanglement, Harmony is demonstrated to incentivize bioimage analysis research by modeling structural heterogeneity of macromolecules from cryo-ET images and learning transformation-invariant representations of protein particles from single-particle cryo-EM images. Harmony also performs very well in disentangling content from 3D transformations and can perform coarse and fast alignment of 3D cryo-ET subtomograms. Therefore, Harmony is generalizable to many other imaging domains and can potentially be extended to domains beyond imaging as well.
-
Recent studies in talking face generation have focused on building a model that can generalize from any source speech to any target identity. A number of works have already claimed this functionality and have added that their models will also generalize to any language. However, we show, using languages from different language families, that these models do not translate well when the training language and the testing language are sufficiently different. We reduce the scope of the problem to building a languagerobust talking face generation system on seen identities, i.e., the target identity is the same as the training identity. In this work, we introduce a talking face generation system that generalizes to different languages. We evaluate the efficacy of our system using a multilingual text-to-speech system. We present the joint text-to-speech system and the talking face generation system as a neural dubber system. Our demo is available at https://bit.ly/ml-face-generation-cvpr22-demo. Also, our screencast is uploaded at https://youtu.be/F6h0s0M4vBI.
-
A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres
When coming up with phrases of movement, choreographers all have their habits as they are used to their skilled dance genres. Therefore, they tend to return certain patterns of the dance genres that they are familiar with. What if artificial intelligence could be used to help choreographers blend dance genres by suggesting various dances, and one that matches their choreographic style? Numerous task-specific variants of autoregressive networks have been developed for dance generation. Yet, a serious limitation remains that all existing algorithms can return repeated patterns for a given initial pose sequence, which may be inferior. To mitigate this issue, we propose MNET, a novel and scalable approach that can perform music-conditioned pluralistic dance generation synthesized by multiple dance genres using only a single model. Here, we learn a dance-genre aware latent representation by training a conditional generative adversarial network leveraging Transformer architecture. We conduct extensive experiments on AIST++ along with user studies. Compared to the state-of-the-art methods, our method synthesizes plausible and diverse outputs according to multiple dance genres as well as generates outperforming dance sequences qualitatively and quantitatively.
-
We design a Kernelized Few-shot Object Detector by leveraging kernelized matrices computed over multiple proposal regions, which yield expressive non-linear representations whose model complexity is learned on the fly. Our pipeline contains several modules. An Encoding Network encodes support and query images. Our Kernelized Autocorrelation unit forms the linear, polynomial and RBF kernelized representations from features extracted within support regions of support images. These features are then cross-correlated against features of a query image to obtain attention weights, and generate query proposal regions via an Attention Region Proposal Net. As the query proposal regions are many, each described by the linear, polynomial and RBF kernelized matrices, their formation is costly but that cost is reduced by our proposed Integral Region-of-Interest Aggregation unit. Finally, the Multi-head Relation Net combines all kernelized (second-order) representations with the first-order feature maps to learn support-query class relations and locations. We outperform the state of the art on novel classes by 3.8%, 5.4% and 5.7% mAP on PASCAL VOC 2007, FSOD, and COCO.
-
Previous works on vanishing point detection usually use geometric prior for line segment clustering. We find that image context can also contribute to accurate line classification. Based on this observation, we propose to classify line segments into three groups according to three unknown-but-sought vanishing points with Manhattan world assumption, using both geometric information and image context in this work. To achieve this goal, we propose a novel Transformer based Line segment Classifier (TLC) that can group line segments in images and estimate the corresponding vanishing points. In TLC, we design a line segment descriptor to represent line segments using their positions, directions and local image contexts. Transformer based feature fusion module is used to capture global features from all line segments, which is proved to improve the classification performance significantly in our experiments. By using a network to score line segments for outlier rejection, vanishing points can be got by Singular Value Decomposition (SVD) from the classified lines. The proposed method runs at 25 fps on one NVIDIA 2080Ti card for vanishing point detection. Experimental results on synthetic and real-world datasets demonstrate that our method is superior to other state-of-the-art methods on the balance between accuracy and efficiency, while keeping stronger generalization capability when trained and evaluated on different datasets.
-
Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved. It is a challenging task since representation optimization and feature retention can only be achieved under supervision from new classes. To address this problem, we propose a novel self-sustaining representation expansion scheme. Our scheme consists of a structure reorganization strategy that fuses main-branch expansion and side-branch updating to maintain the old features, and a main-branch distillation scheme to transfer the invariant knowledge. Furthermore, a prototype selection mechanism is proposed to enhance the discrimination between the old and new classes by selectively incorporating new samples into the distillation process. Extensive experiments on three benchmarks demonstrate significant incremental performance, outperforming the state-of-the-art methods by a margin of 3% , 3% and 6% , respectively.
-
Deep learning in the presence of noisy annotations has been studied extensively in classification, but much less in segmentation tasks. In this work, we study the learning dynamics of deep segmentation networks trained on inaccurately-annotated data. We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations. However, in contrast to classification, memorization in segmentation does not arise simultaneously for all semantic categories. Inspired by these findings, we propose a new method for segmentation from noisy annotations with two key elements. First, we detect the beginning of the memorization phase separately for each category during training. This allows us to adaptively correct the noisy annotations in order to exploit early learning. Second, we incorporate a regularization term that enforces consistency across scales to boost robustness against annotation noise. Our method outperforms standard approaches on a medical-imaging segmentation task where noises are synthesized to mimic human annotation errors. It also provides robustness to realistic noisy annotations present in weakly-supervised semantic segmentation, achieving state-of-the-art results on PASCAL VOC 2012. Code is available at https://github.com/Kangningthu/ADELE
-
The performance of nighttime semantic segmentation is restricted by the poor illumination and a lack of pixel-wise annotation, which severely limit its application in autonomous driving. Existing works, e.g., using the twilight as the intermediate target domain to perform the adaptation from daytime to nighttime, may fail to cope with the inherent difference between datasets caused by the camera equipment and the urban style. Faced with these two types of domain shifts, i.e., the illumination and the inherent difference of the datasets, we propose a novel domain adaptation framework via cross-domain correlation distillation, called CCDistill. The invariance of illumination or inherent difference between two images is fully explored so as to make up for the lack of labels for nighttime images. Specifically, we extract the content and style knowledge contained in features, calculate the degree of inherent or illumination difference between two images. The domain adaptation is achieved using the invariance of the same kind of difference. Extensive experiments on Dark Zurich and ACDC demonstrate that CCDistill achieves the state-of-the-art performance for nighttime semantic segmentation. Notably, our method is a one-stage domain adaptation network which can avoid affecting the inference time. Our implementation is available at https://github.com/ghuan99/CCDistill.
-
With the ubiquity of rolling shutter (RS) cameras, it is becoming increasingly attractive to recover the latent global shutter (GS) video from two consecutive RS frames, which also places a higher demand on realism. Existing solutions, using deep neural networks or optimization, achieve promising performance. However, these methods generate intermediate GS frames through image warping based on the RS model, which inevitably result in black holes and noticeable motion artifacts. In this paper, we alleviate these issues by proposing a context-aware GS video reconstruction architecture. It facilitates the advantages such as occlusion reasoning, motion compensation, and temporal abstraction. Specifically, we first estimate the bilateral motion field so that the pixels of the two RS frames are warped to a common GS frame accordingly. Then, a refinement scheme is proposed to guide the GS frame synthesis along with bilateral occlusion masks to produce high-fidelity GS video frames at arbitrary times. Furthermore, we derive an approximated bilateral motion field model, which can serve as an alternative to provide a simple but effective GS frame initialization for related tasks. Experiments on synthetic and real data show that our approach achieves superior performance over state-of-the-art methods in terms of objective metrics and subjective visual quality.
-
Classic black-box adversarial attacks can take advantage of transferable adversarial examples generated by a similar substitute model to successfully fool the target model. However, these substitute models need to be trained by target models' training data, which is hard to acquire due to privacy or transmission reasons. Recognizing the limited availability of real data for adversarial queries, recent works proposed to train substitute models in a data-free black-box scenario. However, their generative adversarial networks (GANs) based framework suffers from the convergence failure and the model collapse, resulting in low efficiency. In this paper, by rethinking the collaborative relationship between the generator and the substitute model, we design a novel black-box attack framework. The proposed method can efficiently imitate the target model through a small number of queries and achieve high attack success rate. The comprehensive experiments over six datasets demonstrate the effectiveness of our method against the state-of-the-art attacks. Especially, we conduct both label-only and probability-only attacks on the Microsoft Azure online model, and achieve a 100% attack success rate with only 0.46% query budget of the SOTA method [??].
-
Contrastive learning relies on an assumption that positive pairs contain related views that share certain underlying information about an instance, e.g., patches of an image or co-occurring multimodal signals of a video. What if this assumption is violated? The literature suggests that contrastive learning produces suboptimal representations in the presence of noisy views, e.g., false positive pairs with no apparent shared information. In this work, we propose a new contrastive loss function that is robust against noisy views. We provide rigorous theoretical justifications by showing connections to robust symmetric losses for noisy binary classification and by establishing a new contrastive bound for mutual information maximization based on the Wasserstein distance measure. The proposed loss is completely modality-agnostic and a simple drop-in replacement for the InfoNCE loss, which makes it easy to apply to existing contrastive frameworks. We show that our approach provides consistent improvements over the state-of-the-art on image, video, and graph contrastive learning benchmarks that exhibit a variety of real-world noise patterns.
-
In this paper we present VDTTS, a Visually-Driven Text-to-Speech model. Motivated by dubbing, VDTTS takes advantage of video frames as an additional input alongside text, and generates speech that matches the video signal. We demonstrate how this allows VDTTS to, unlike plain TTS models, generate speech that not only has prosodic variations like natural pauses and pitch, but is also synchronized to the input video. Experimentally, we show our model produces well-synchronized outputs, approaching the video-speech synchronization quality of the ground-truth, on several challenging benchmarks including "in-the-wild" content from VoxCeleb2. Supplementary demo videos demonstrating video-speech synchronization, robustness to speaker ID swapping, and prosody, presented at the project page.
-
This work digs into a root question in human perception: can face geometry be gleaned from one's voices? Previous works that study this question only adopt developments in image synthesis and convert voices into face images to show correlations, but working on the image domain unavoidably involves predicting attributes that voices cannot hint, including facial textures, hairstyles, and backgrounds. We instead investigate the ability to reconstruct 3D faces to concentrate on only geometry, which is much more physiologically grounded. We propose our analysis framework, Cross-Modal Perceptionist, under both supervised and unsupervised learning. First, we construct a dataset, Voxceleb-3D, which extends Voxceleb and includes paired voices and face meshes, making supervised learning possible. Second, we use a knowledge distillation mechanism to study whether face geometry can still be gleaned from voices without paired voices and 3D face data under limited availability of 3D face scans. We break down the core question into four parts and perform visual and numerical analyses as responses to the core question. Our findings echo those in physiology and neuroscience about the correlation between voices and facial structures. The work provides future human-centric cross-modal learning with explainable foundations. See our project page.
-
In the real world, humans have the ability to accumulate new knowledge in any conditions. However, deeplearning suffers from the phenomenon so-called catastrophic forgetting of the previously observed knowledge after learning a new task. Many recent methods focus on preventing catastrophic forgetting under a typical assumption of thetrain and test data following a similar distribution. In thiswork, we consider the more realistic scenario of continuallearning under domain shifts where the model is able to gen-eralize its inference to a an unseen domain. To this end, wepropose to make use of sample correlations of the learning tasks in the classifiers where the subsequent optimization isperformed over similarity measures obtained in a similar fashion to the Mahalanobis distance computation. In addition, we also propose an approach based on the exponential moving average of the parameters for better knowledge distillation, allowing a further adaptation to the old model. We demonstrate in our experiments that, to a great extent, the past continual learning algorithms fail to handle the forgetting issue under multiple distributions, while our proposed approach identifies the task under domain shift where insome cases can boost up the performance up to 10% on the challenging datasets e.g., DomainNet and OfficeHome.
-
Space-time video super-resolution (STVSR) is the task of interpolating videos with both Low Frame Rate (LFR) and Low Resolution (LR) to produce High-Frame-Rate (HFR) and also High-Resolution (HR) counterparts. The existing methods based on Convolutional Neural Network (CNN) succeed in achieving visually satisfied results while suffer from slow inference speed due to their heavy architectures. We propose to resolve this issue by using a spatial-temporal transformer that naturally incorporates the spatial and temporal super resolution modules into a single model. Unlike CNN-based methods, we do not explicitly use separated building blocks for temporal interpolations and spatial super-resolutions; instead, we only use a single end-to-end transformer architecture. Specifically, a reusable dictionary is built by encoders based on the input LFR and LR frames, which is then utilized in the decoder part to synthesize the HFR and HR frames. Compared with the state-of-the-art TMNet, our network is 60% smaller (4.5M vs 12.3M parameters) and 80% faster (26.2fps vs 14.3fps on 720 x 576 frames) without sacrificing much performance. The source code is available at https://github.com/llmpass/RSTT.
-
This paper tackles the cross-modality person re-identification (re-ID) problem by suppressing the modality discrepancy. In cross-modality re-ID, the query and gallery images are in different modalities. Given a training identity, the popular deep classification baseline shares the same proxy (i.e., a weight vector in the last classification layer) for two modalities. We find that it has considerable tolerance for the modality gap, because the shared proxy acts as an intermediate relay between two modalities. In response, we propose a Memory-Augmented Unidirectional Metric (MAUM) learning method consisting of two novel designs, i.e., unidirectional metrics, and memory-based augmentation. Specifically, MAUM first learns modality-specific proxies (MS-Proxies) independently under each modality. Afterward, MAUM uses the already-learned MS-Proxies as the static references for pulling close the features in the counterpart modality. These two unidirectional metrics (IR image to RGB proxy and RGB image to IR proxy) jointly alleviate the relay effect and benefit cross-modality association. The cross-modality association is further enhanced by storing the MS-Proxies into memory banks to increase the reference diversity. Importantly, we show that MAUM improves cross-modality re-ID under the modality-balanced setting and gains extra robustness against the modality-imbalance problem. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate the superiority of MAUM over the state-of-the-art. The code will be available.
-
Modern GANs excel at generating high-quality and diverse images. However, when transferring the pretrained GANs on small target data (e.g., 10-shot), the generator tends to replicate the training samples. Several methods have been proposed to address this few-shot image generation task, but there is a lack of effort to analyze them under a unified framework. As our first contribution, we propose a framework to analyze existing methods during the adaptation. Our analysis discovers that while some methods have a disproportionate focus on diversity preserving which impedes quality improvement, all methods achieve similar quality after convergence. Therefore, the better methods are those that can slow down diversity degradation. Furthermore, our analysis reveals that there is still plenty of room to further slow down diversity degradation. Informed by our analysis and to slow down diversity degradation of the target generator during adaptation, our second contribution proposes to apply mutual information (MI) maximization to retain the source domain's rich multi-level diversity information in the target domain generator. We propose to perform MI maximization by contrastive loss (CL), leverage the generator and discriminator as two feature encoders to extract different multi-level features for computing CL. We refer to our method as Dual ContrastiveLearning (DCL). Extensive experiments on several public datasets show that, while leading to a slower diversity-degrading generator during adaptation, our proposed DCL brings visually pleasant quality and state-of-the-art quantitative performance.
-
A commonly observed failure mode of Neural Radiance Field (NeRF) is fitting incorrect geometries when given an insufficient number of input views. One potential reason is that standard volumetric rendering does not enforce the constraint that most of a scene's geometry consist of empty space and opaque surfaces. We formalize the above assumption through DS-NeRF (Depth-supervised Neural Radiance Fields), a loss for learning radiance fields that takes advantage of readily-available depth supervision. We leverage the fact that current NeRF pipelines require images with known camera poses that are typically estimated by running structure-from-motion (SFM). Crucially, SFM also produces sparse 3D points that can be used as "free" depth supervision during training: we add a loss to encourage the distribution of a ray's terminating depth matches a given 3D keypoint, incorporating depth uncertainty. DS-NeRF can render better images given fewer training views while training 2-3x faster. Further, we show that our loss is compatible with other recently proposed NeRF methods, demonstrating that depth is a cheap and easily digestible supervisory signal. And finally, we find that DS-NeRF can support other types of depth supervision such as scanned depth sensors and RGBD reconstruction outputs.
-
The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system. In this paper, different from most cross-domain works that utilize some (or full) source domain supervision, we approach a relatively new and very practical Unsupervised Domain Generalization (UDG) setup of having no training supervision in neither source nor target domains. Our approach is based on self-supervised learning of a Bridge Across Domains (BrAD) - an auxiliary bridge domain accompanied by a set of semantics preserving visual (image-to-image) mappings to BrAD from each of the training domains. The BrAD and mappings to it are learned jointly (end-to-end) with a contrastive self-supervised representation model that semantically aligns each of the domains to its BrAD-projection, and hence implicitly drives all the domains (seen or unseen) to semantically align to each other. In this work, we show how using an edge-regularized BrAD our approach achieves significant gains across multiple benchmarks and a range of tasks, including UDG, Few-shot UDA, and unsupervised generalization across multi-domain datasets (including generalization to unseen domains and classes).
-
Current attention-based methods for semantic segmentation mainly model pixel relation through pairwise affinity and coarse segmentation. For the first time, this paper explores modeling pixel relation via Class Activation Map (CAM). Beyond the previous CAM generated from image-level classification, we present Partial CAM, which subdivides the task into region-level prediction and achieves better localization performance. In order to eliminate the intra-class inconsistency caused by the variances of local context, we further propose Partial Class Activation Attention (PCAA) that simultaneously utilizes local and global class-level representations for attention calculation. Once obtained the partial CAM, PCAA collects local class centers and computes pixel-to-class relation locally. Applying local-specific representations ensures reliable results under different local contexts. To guarantee global consistency, we gather global representations from all local class centers and conduct feature aggregation. Experimental results confirm that Partial CAM outperforms the previous two strategies as pixel relation. Notably, our method achieves state-of-the-art performance on several challenging benchmarks including Cityscapes, Pascal Context, and ADE20K. Code is available at https://github.com/lsa1997/PCAA.
-
Video deblurring has achieved remarkable progress thanks to the success of deep neural networks. Most methods solve for the deblurring end-to-end with limited information propagation from the video sequence. However, different frame regions exhibit different characteristics and should be provided with corresponding relevant information. To achieve fine-grained deblurring, we designed a memory branch to memorize the blurry-sharp feature pairs in the memory bank, thus providing useful information for the blurry query input. To enrich the memory of our memory bank, we further designed a bidirectional recurrency and multi-scale strategy based on the memory bank. Experimental results demonstrate that our model outperforms other state-of-the-art methods while keeping the model complexity and inference time low. The code is available at https://github.com/jibo27/MemDeblur.
-
This work presents SkinningNet, an end-to-end Two-Stream Graph Neural Network architecture that computes skinning weights from an input mesh and its associated skeleton, without making any assumptions on shape class and structure of the provided mesh. Whereas previous methods pre-compute handcrafted features that relate the mesh and the skeleton or assume a fixed topology of the skeleton, the proposed method extracts this information in an end-to-end learnable fashion by jointly learning the best relationship between mesh vertices and skeleton joints. The proposed method exploits the benefits of the novel Multi-Aggregator Graph Convolution that combines the results of different aggregators during the summarizing step of the Message-Passing scheme, helping the operation to generalize for unseen topologies. Experimental results demonstrate the effectiveness of the contributions of our novel architecture, with SkinningNet outperforming current state-of-the-art alternatives.
-
We present a scalable combinatorial algorithm for globally optimizing over the space of geometrically consistent mappings between 3D shapes. We use the mathematically elegant formalism proposed by Windheuser et al. (ICCV, 2011) where 3D shape matching was formulated as an integer linear program over the space of orientation-preserving diffeomorphisms. Until now, the resulting formulation had limited practical applicability due to its complicated constraint structure and its large size. We propose a novel primal heuristic coupled with a Lagrange dual problem that is several orders of magnitudes faster compared to previous solvers. This allows us to handle shapes with substantially more triangles than previously solvable. We demonstrate compelling results on diverse datasets, and, even showcase that we can address the challenging setting of matching two partial shapes without availability of complete shapes. Our code is publicly available at http://github.com/paul0noah/sm-comb.
-
Video super-resolution (VSR) aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts. Although some progress has been made, there are grand challenges to effectively utilize temporal dependency in entire video sequences. Existing approaches usually align and aggregate video frames from limited adjacent frames (e.g., 5 or 7 frames), which prevents these approaches from satisfactory results. In this paper, we take one step further to enable effective spatio-temporal learning in videos. We propose a novel Trajectory-aware Transformer for Video Super-Resolution (TTVSR). In particular, we formulate video frames into several pre-aligned trajectories which consist of continuous visual tokens. For a query token, self-attention is only learned on relevant visual tokens along spatio-temporal trajectories. Compared with vanilla vision Transformers, such a design significantly reduces the computational cost and enables Transformers to model long-range features. We further propose a cross-scale feature tokenization module to overcome scale-changing problems that often occur in long-range videos. Experimental results demonstrate the superiority of the proposed TTVSR over state-of-the-art models, by extensive quantitative and qualitative evaluations in four widely-used video super-resolution benchmarks.
-
Recently, self-attention mechanisms have shown impressive performance in various NLP and CV tasks, which can help capture sequential characteristics and derive global information. In this work, we explore how to extend self-attention modules to better learn subtle feature embeddings for recognizing fine-grained objects, e.g., different bird species or person identities. To this end, we propose a dual cross-attention learning (DCAL) algorithm to coordinate with self-attention learning. First, we propose global-local cross-attention (GLCA) to enhance the interactions between global images and local high-response regions, which can help reinforce the spatial-wise discriminative clues for recognition. Second, we propose pair-wise cross-attention (PWCA) to establish the interactions between image pairs. PWCA can regularize the attention learning of an image by treating another image as distractor and will be removed during inference. We observe that DCAL can reduce misleading attentions and diffuse the attention response to discover more complementary parts for recognition. We conduct extensive evaluations on fine-grained visual categorization and object re-identification. Experiments demonstrate that DCAL performs on par with state-of-the-art methods and consistently improves multiple self-attention baselines, e.g., surpassing DeiT-Tiny and ViT-Base by 2.8% and 2.4% mAP on MSMT17, respectively.
-
Recently self-supervised representation learning has drawn considerable attention from the scene text recognition community. Different from previous studies using contrastive learning, we tackle the issue from an alternative perspective, i.e., by formulating the representation learning scheme in a generative manner. Typically, the neighboring image patches among one text line tend to have similar styles, including the strokes, textures, colors, etc. Motivated by this common sense, we augment one image patch and use its neighboring patch as guidance to recover itself. Specifically, we propose a Similarity-Aware Normalization (SimAN) module to identify the different patterns and align the corresponding styles from the guiding patch. In this way, the network gains representation capability for distinguishing complex patterns such as messy strokes and cluttered backgrounds. Experiments show that the proposed SimAN significantly improves the representation quality and achieves promising performance. Moreover, we surprisingly find that our self-supervised generative network has impressive potential for data synthesis, text image editing, and font interpolation, which suggests that the proposed SimAN has a wide range of practical applications.
-
We propose a theoretical framework that generalizes simple and fast algorithms for hierarchical agglomerative clustering to weighted graphs with both attractive and repulsive interactions between the nodes. This framework defines GASP, a Generalized Algorithm for Signed graph Partitioning, and allows us to explore many combinations of different linkage criteria and cannot-link constraints. We prove the equivalence of existing clustering methods to some of those combinations and introduce new algorithms for combinations that have not been studied before. We study both theoretical and empirical properties of these combinations and prove that some of these define an ultrametric on the graph. We conduct a systematic comparison of various instantiations of GASP on a large variety of both synthetic and existing signed clustering problems, in terms of accuracy but also efficiency and robustness to noise. Lastly, we show that some of the algorithms included in our framework, when combined with the predictions from a CNN model, result in a simple bottom-up instance segmentation pipeline. Going all the way from pixels to final segments with a simple procedure, we achieve state-of-the-art accuracy on the CREMI 2016 EM segmentation benchmark without requiring domain-specific superpixels.
-
In machine learning, a question of great interest is understanding what examples are challenging for a model to classify. Identifying atypical examples ensures the safe deployment of models, isolates samples that require further human inspection, and provides interpretability into model behavior. In this work, we propose Variance of Gradients (VoG) as a valuable and efficient metric to rank data by difficulty and to surface a tractable subset of the most challenging examples for human-in-the-loop auditing. We show that data points with high VoG scores are far more difficult for the model to learn and over-index on corrupted or memorized examples. Further, restricting the evaluation to the test set instances with the lowest VoG improves the model's generalization performance. Finally, we show that VoG is a valuable and efficient ranking for out-of-distribution detection
-
Image hashing is a principled approximate nearest neighbor approach to find similar items to a query in a large collection of images. Hashing aims to learn a binary-output function that maps an image to a binary vector. For optimal retrieval performance, producing balanced hash codes with low-quantization error to bridge the gap between the learning stage's continuous relaxation and the inference stage's discrete quantization is important. However, in the existing deep supervised hashing methods, coding balance and low-quantization error are difficult to achieve and involve several losses. We argue that this is because the existing quantization approaches in these methods are heuristically constructed and not effective to achieve these objectives. This paper considers an alternative approach to learning the quantization constraints. The task of learning balanced codes with low quantization error is re-formulated as matching the learned distribution of the continuous codes to a pre-defined discrete, uniform distribution. This is equivalent to minimizing the distance between two distributions. We then propose a computationally efficient distributional distance by leveraging the discrete property of the hash functions. This distributional distance is a valid distance and enjoys lower time and sample complexities. The proposed single-loss quantization objective can be integrated into any existing supervised hashing method to improve code balance and quantization error. Experiments confirm that the proposed approach substantially improves the performance of several representative hashing methods.
-
Blind deblurring has attracted much interest with its wide applications in reality. The blind deblurring problem is usually solved by estimating the intermediate kernel and the intermediate image alternatively, which will finally converge to the blurring kernel of the observed image. Numerous works have been proposed to obtain intermediate images with fewer undesirable artifacts by designing delicate regularization on the latent solution. However, these methods still fail while dealing with images containing saturations and large blurs. To address this problem, we propose an intermediate image correction method which utilizes Bayes posterior estimation to screen through the intermediate image and exclude those unfavorable pixels to reduce their influence for kernel estimation. Extensive experiments have proved that the proposed method can effectively improve the accuracy of the final derived kernel against the state-of-the-art methods on benchmark datasets by both quantitative and qualitative comparisons.
-
Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to generate more complete and precise pseudo masks for segmentation. In this study, we propose weakly-supervised pixel-to-prototype contrast that can provide pixel-level supervisory signals to narrow the gap. Guided by two intuitive priors, our method is executed across different views and within per single view of an image, aiming to impose cross-view feature semantic consistency regularization and facilitate intra(inter)-class compactness(dispersion) of the feature space. Our method can be seamlessly incorporated into existing WSSS models without any changes to the base networks and does not incur any extra inference burden. Extensive experiments manifest that our method consistently improves two strong baselines by large margins, demonstrating the effectiveness. Specifically, built on top of SEAM, we improve the initial seed mIoU on PASCAL VOC 2012 from 55.4% to 61.5%. Moreover, armed with our method, we increase the segmentation mIoU of EPS from 70.8% to 73.6%, achieving new state-of-the-art.
-
We propose a method to interactively control the animation of fluid elements in still images to generate cinemagraphs. Specifically, we focus on the animation of fluid elements like water, smoke, fire, which have the properties of repeating textures and continuous fluid motion. Taking inspiration from prior works, we represent the motion of such fluid elements in the image in the form of a constant 2D optical flow map. To this end, we allow the user to provide any number of arrow directions and their associated speeds along with a mask of the regions the user wants to animate. The user-provided input arrow directions, their corresponding speed values, and the mask are then converted into a dense flow map representing a constant optical flow map (F_D). We observe that F_D, obtained using simple exponential operations can closely approximate the plausible motion of elements in the image. We further refine computed dense optical flow map F_D using a generative-adversarial network (GAN) to obtain a more realistic flow map. We devise a novel UNet based architecture to autoregressively generate future frames using the refined optical flow map by forward-warping the input image features at different resolutions. We conduct extensive experiments on a publicly available dataset and show that our method is superior to the baselines in terms of qualitative and quantitative metrics. In addition, we show the qualitative animations of the objects in directions that did not exist in the training set and provide a way to synthesize videos that otherwise would not exist in the real world. Project url: https://controllable-cinemagraphs.github.io/
-
Light curtain systems are designed for detecting the presence of objects within a user-defined 3D region of space, which has many applications across vision and robotics. However, the shape of light curtains have so far been limited to ruled surfaces, i.e., surfaces composed of straight lines. In this work, we propose Holocurtains: a light-efficient approach to producing light curtains of arbitrary shape. The key idea is to synchronize a rolling-shutter camera with a 2D holographic projector, which steers (rather than block) light to generate bright structured light patterns. Our prototype projector uses a binary digital micromirror device (DMD) to generate the holographic interference patterns at high speeds. Our system produces 3D light curtains that cannot be achieved with traditional light curtain setups and thus enables all-new applications, including the ability to simultaneously capture multiple light curtains in a single frame, detect subtle changes in scene geometry, and transform any 3D surface into an optical touch interface.
-
Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the hardware cannot withstand the ever-increasing memory requirements as the video length increases. 2) Storing lots of information inevitably introduces lots of noise, which is not conducive to reading the most important information from the memory bank. In this paper, we propose a Recurrent Dynamic Embedding (RDE) to build a memory bank of constant size. Specifically, we explicitly generate and update RDE by the proposed Spatio-temporal Aggregation Module (SAM), which exploits the cue of historical information. To avoid error accumulation owing to the recurrent usage of SAM, we propose an unbiased guidance loss during the training stage, which makes SAM more robust in long videos. Moreover, the predicted masks in the memory bank are inaccurate due to the inaccurate network inference, which affects the segmentation of the query frame. To address this problem, we design a novel self-correction strategy so that the network can repair the embeddings of masks with different qualities in the memory bank. Extensive experiments show our method achieves the best tradeoff between performance and speed.
-
Humans are able to recognize structured relations in observation, allowing us to decompose complex scenes into simpler parts and abstract the visual world in multiple levels. However, such hierarchical reasoning ability of human perception remains largely unexplored in current literature of semantic segmentation. Existing work is often aware of flatten labels and predicts target classes exclusively for each pixel. In this paper, we instead address hierarchical semantic segmentation (HSS), which aims at structured, pixel-wise description of visual observation in terms of a class hierarchy. We devise HSSN, a general HSS framework that tackles two critical issues in this task: i) how to efficiently adapt existing hierarchy-agnostic segmentation networks to the HSS setting, and ii) how to leverage the hierarchy information to regularize HSS network learning. To address i), HSSN directly casts HSS as a pixel-wise multi-label classification task, only bringing minimal architecture change to current segmentation models. To solve ii), HSSN first explores inherent properties of the hierarchy as a training objective, which enforces segmentation predictions to obey the hierarchy structure. Further, with hierarchy-induced margin constraints, HSSN reshapes the pixel embedding space, so as to generate well-structured pixel representations and improve segmentation eventually. We conduct experiments on four semantic segmentation datasets (i.e., Mapillary Vistas 2.0, Cityscapes, LIP, and PASCAL-Person-Part), with different class hierarchies, segmentation network architectures and backbones, showing the generalization and superiority of HSSN.
-
Shape-from-Template (SfT) methods estimate 3D surface deformations from a single monocular RGB camera while assuming a 3D state known in advance (a template). This is an important yet challenging problem due to the under-constrained nature of the monocular setting. Existing SfT techniques predominantly use geometric and simplified deformation models, which often limits their reconstruction abilities. In contrast to previous works, this paper proposes a new SfT approach explaining 2D observations through physical simulations accounting for forces and material properties. Our differentiable physics simulator regularises the surface evolution and optimises the material elastic properties such as bending coefficients, stretching stiffness and density. We use a differentiable renderer to minimise the dense reprojection error between the estimated 3D states and the input images and recover the deformation parameters using an adaptive gradient-based optimisation. For the evaluation, we record with an RGB-D camera challenging real surfaces exposed to physical forces with various material properties and textures. Our approach significantly reduces the 3D reconstruction error compared to multiple competing methods. For the source code and data, see https://4dqv.mpi-inf.mpg.de/phi-SfT/.
-
Continual learning is a challenging real-world problem for constructing a mature AI system when data are provided in a streaming fashion. Despite recent progress in continual classification, the researches of continual object detection are impeded by the diverse sizes and numbers of objects in each image. Different from previous works that tune the whole network for all tasks, in this work, we present a simple and flexible framework for continual object detection via pRotOtypical taSk corrElaTion guided gaTing mechAnism (ROSETTA). Concretely, a unified framework is shared by all tasks while task-aware gates are introduced to automatically select sub-models for specific tasks. In this way, various knowledge can be successively memorized by storing their corresponding sub-model weights in this system. To make ROSETTA automatically determine which experience is available and useful, a prototypical task correlation guided Gating Diversity Controller (GDC) is introduced to adaptively adjust the diversity of gates for the new task based on class-specific prototypes. GDC module computes class-to-class correlation matrix to depict the cross-task correlation, and hereby activates more exclusive gates for the new task if a significant domain gap is observed. Comprehensive experiments on COCO-VOC, KITTI-Kitchen, class-incremental detection on VOC and sequential learning of four tasks show that ROSETTA yields state-of-the-art performance on both task-based and class-based continual object detection.
-
The paradigm of training models on massive data without label through self-supervised learning (SSL) and finetuning on many downstream tasks has become a trend recently. However, due to the high training costs and the unconsciousness of downstream usages, most self-supervised learning methods lack the capability to correspond to the diversities of downstream scenarios, as there are various data domains, latency constraints and etc. Neural architecture search (NAS) is one universally acknowledged fashion to conquer the issues above, but applying NAS on SSL seems impossible as there is no label or metric provided for judging model selection. In this paper, we present DATA, a simple yet effective NAS approach specialized for SSL that provides Domain-Aware and Task-Aware pre-training. Specifically, we (i) train a supernet which could be deemed as a set of millions of networks covering a wide range of model scales without any label, (ii) propose a flexible searching mechanism compatible with SSL that enables finding networks of different computation costs, for various downstream vision tasks and data domains without explicit metric provided. Instantiated With MoCov2, our method achieves promising results across a wide range of computation costs on downstream tasks, including image classification, object detection and semantic segmentation. DATA is orthogonal to most existing SSL methods and endows them the ability of customization on downstream needs. Extensive experiments on other SSL methods, including BYOL, ReSSL and DenseCL demonstrate the generalizability of the proposed method. Code would be made available soon.
-
We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation. To leverage the unlabeled data to boost model performance, we present a novel Two-Way Inter-label Self-Training framework named TWIST. It exploits inherent correlations between semantic understanding and instance information of a scene. Specifically, we consider two kinds of pseudo labels for semantic- and instance-level supervision. Our key design is to provide object-level information for denoising pseudo labels and make use of their correlation for two-way mutual enhancement, thereby iteratively promoting the pseudo-label qualities. TWIST attains leading performance on both ScanNet and S3DIS, compared to recent 3D pre-training approaches, and can cooperate with them to further enhance performance, e.g., +4.4% AP50 on 1%-label ScanNet data-efficient benchmark. Code is available at https://github.com/dvlab-research/TWIST.
-
Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to apply the self-attention underlying transformer on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space. To solve this issue, existing methods usually compute self-attention locally by grouping the points into clusters of the same size, or perform convolutional self-attention on a discretized representation. However, the former results in stochastic point dropout, while the latter typically has narrow attention field. In this paper, we propose a novel voxel-based architecture, namely Voxel Set Transformer (VoxSeT), to detect 3D objects from point clouds by means of set-to-set translation. VoxSeT is built upon a voxel-based set attention (VSA) module, which reduces the self-attention in each voxel by two cross-attentions and models features in a hidden space induced by a group of latent codes. With the VSA module, VoxSeT can manage voxelized point clusters with arbitrary size in a wide range, and process them in parallel with linear complexity. The proposed VoxSeT integrates the high performance of transformer with the efficiency of voxel-based model, which can be used as a good alternative to the convolutional and point-based backbones. VoxSeT reports competitive results on the KITTI and Waymo detection benchmarks. The source code of VoxSeT will be released.
-
This paper proposes a real-world rolling shutter (RS) correction dataset, BS-RSC, and a corresponding model to correct the RS frames in a distorted video. Mobile devices in the consumer market with CMOS-based sensors for video capture often result in rolling shutter effects when relative movements occur during the video acquisition process, calling for RS effect removal techniques. However, current state-of-the-art RS correction methods often fail to remove RS effects in real scenarios since the motions are various and hard to model. To address this issue, we propose a real-world RS correction dataset BS-RSC. Real distorted videos with corresponding ground truth are recorded simultaneously via a well-designed beam-splitter-based acquisition system. BS-RSC contains various motions of both camera and objects in dynamic scenes. Further, an RS correction model with adaptive warping is proposed. Our model can warp the learned RS features into global shutter counterparts adaptively with predicted multiple displacement fields. These warped features are aggregated and then reconstructed into high-quality global shutter frames in a coarse-to-fine strategy. Experimental results demonstrate the effectiveness of the proposed method, and our dataset can improve the model's ability to remove the RS effects in the real world.
-
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions formed from seen state and object during training. Since the same state may be various in the visual appearance while entangled with different objects, CZSL is still a challenging task. Some methods recognize state and object with two trained classifiers, ignoring the impact of the interaction between object and state; the other methods try to learn the joint representation of the state-object compositions, leading to the domain gap between seen and unseen composition sets. In this paper, we propose a novel Siamese Contrastive Embedding Network (SCEN) for unseen composition recognition. Considering the entanglement between state and object, we embed the visual feature into a Siamese Contrastive Space to capture prototypes of them separately, alleviating the interaction between state and object. In addition, we design a State Transition Module (STM) to increase the diversity of training compositions, improving the robustness of the recognition model. Extensive experiments indicate that our method significantly outperforms the state-of-the-art approaches on three challenging benchmark datasets, including the recent proposed C-QGA dataset.
-
A significant gap remains between today's visual pattern recognition models and human-level visual cognition especially when it comes to few-shot learning and compositional reasoning of novel concepts. We introduce Bongard-HOI, a new visual reasoning benchmark that focuses on compositional learning of human-object interactions (HOIs) from natural images. It is inspired by two desirable characteristics from the classical Bongard problems (BPs): 1) few-shot concept learning, and 2) context-dependent reasoning. We carefully curate the few-shot instances with hard negatives, where positive and negative images only disagree on action labels, making mere recognition of object categories insufficient to complete our benchmarks. We also design multiple test sets to systematically study the generalization of visual learning models, where we vary the overlap of the HOI concepts between the training and test sets of few- shot instances, from partial to no overlaps. Bongard-HOI presents a substantial challenge to today's visual recognition models. The state-of-the-art HOI detection model achieves only 62% accuracy on few-shot binary prediction while even amateur human testers on MTurk have 91% accuracy. With the Bongard-HOI benchmark, we hope to further advance research efforts in visual reasoning, especially in holistic perception-reasoning systems and better representation learning.
-
We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an input 3D shape into two parts, resulting in a binary tree hierarchy. Each level of the tree corresponds to an assembly of shape parts, represented as implicit functions, to reconstruct the input shape. At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level. As an implicit field decoder, the part decoder is designed to decompose a sub-shape, via a two-way branched reconstruction, where each branch predicts a set of parameters defining a Gaussian to serve as a local point distribution for shape reconstruction. With reconstruction losses accounted for at each hierarchy level and a decomposition loss at each node, our network training does not require any ground-truth segmentations, let alone hierarchies. Through extensive experiments and comparisons to state-of-the-art alternatives, we demonstrate the quality, consistency, and interpretability of hierarchical structural inference by RIM-Net.
-
Data often has many semantic attributes that are causally associated with each other. But do attribute-specific learned representations of data also respect the same causal relations? We answer this question in three steps. First, we introduce NCINet, an approach for observational causal discovery from high-dimensional data. It is trained purely on synthetically generated representations and can be applied to real representations, and is specifically designed to mitigate the domain gap between the two. Second, we apply NCINet to identify the causal relations between image representations of different pairs of attributes with known and unknown causal relations between the labels. For this purpose, we consider image representations learned for predicting attributes on the 3D Shapes, CelebA, and the CASIA-WebFace datasets, which we annotate with multiple multi-class attributes. Third, we analyze the effect on the underlying causal relation between learned representations induced by various design choices in representation learning. Our experiments indicate that (1) NCINet significantly outperforms existing observational causal discovery approaches for estimating the causal relation between pairs of random samples, both in the presence and absence of an unobserved confounder, (2) under controlled scenarios, learned representations can indeed satisfy the underlying causal relations between their respective labels, and (3) the causal relations are positively correlated with the predictive capability of the representations. Code and annotations are available at: https://github.com/human-analysis/causal-relations-between-representations.
-
Establishing correspondences from image to 3D has been a key task of 6DoF object pose estimation for a long time. To predict pose more accurately, deeply learned dense maps replaced sparse templates. Dense methods also improved pose estimation in the presence of occlusion. More recently researchers have shown improvements by learning object fragments as segmentation. In this work, we present a discrete descriptor, which can represent the object surface densely. By incorporating a hierarchical binary grouping, we can encode the object surface very efficiently. Moreover, we propose a coarse to fine training strategy, which enables fine-grained correspondence prediction. Finally, by matching predicted codes with object surface and using a PnP solver, we estimate the 6DoF pose. Results on the public LM-O and YCB-V datasets show major improvement over the state of the art w.r.t. ADD(-S) metric, even surpassing RGB-D based methods in some cases.
-
Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of generating caption given an image. In this work, we repurpose such models to generate a descriptive text given an image at inference time, without any further training or tuning step. This is done by combining the visual-semantic model with a large language model, benefiting from the knowledge in both web-scale models. The resulting captions are much less restrictive than those obtained by supervised captioning methods. Moreover, as a zero-shot learning method, it is extremely flexible and we demonstrate its ability to perform image arithmetic in which the inputs can be either images or text and the output is a sentence. This enables novel high-level vision capabilities such as comparing two images or solving visual analogy tests. Our code is available at: https://github.com/YoadTew/zero-shot-image-to-text.
-
Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks, given only a few examples. To handle the limited-data in few-shot regimes, recent methods tend to collectively use a set of local features to densely represent an image instead of using a mixed global feature. They generally explore a unidirectional paradigm, e.g., find the nearest support feature for every query feature and aggregate these local matches for a joint classification. In this paper, we propose a novel Mutual Centralized Learning (MCL) to fully affiliate these two disjoint dense features sets in a bidirectional paradigm. We first associate each local feature with a particle that can bidirectionally random walk in a discrete feature space. To estimate the class probability, we propose the dense features' accessibility that measures the expected number of visits to the dense features of that class in a Markov process. We relate our method to learning a centrality on an affiliation network and demonstrate its capability to be plugged in existing methods by highlighting centralized local features. Experiments show that our method achieves the new state-of-the-art.
-
We introduce CAPRI-Net, a self-supervised neural network for learning compact and interpretable implicit representations of 3D computer-aided design (CAD) models, in the form of adaptive primitive assemblies. Given an input 3D shape, our network reconstructs it by an assembly of quadric surface primitives via constructive solid geometry (CSG) operations. Without any ground-truth shape assemblies, our self-supervised network is trained with a reconstruction loss, leading to faithful 3D reconstructions with sharp edges and plausible CSG trees. While the parametric nature of CAD models does make them more predictable locally, at the shape level, there is much structural and topological variation, which presents a significant generalizability challenge to state-of-the-art neural models for 3D shapes. Our network addresses this challenge by adaptive training with respect to each test shape, with which we fine-tune the network that was pre-trained on a model collection. We evaluate our learning framework on both ShapeNet and ABC, the largest and most diverse CAD dataset to date, in terms of reconstruction quality, sharp edges, compactness, and interpretability, to demonstrate superiority over current alternatives for neural CAD reconstruction.
-
Although the Trajectory Prediction (TP) model has achieved great success in computer vision and robotics fields, its architecture and training scheme design rely on heavy manual work and domain knowledge, which is not friendly to common users. Besides, the existing works ignore Federated Learning (FL) scenarios, failing to make full use of distributed multi-source datasets with rich actual scenes to learn more a powerful TP model. In this paper, we make up for the above defects and propose ATPFL to help users federate multi-source trajectory datasets to automatically design and train a powerful TP model. In ATPFL, we build an effective TP search space by analyzing and summarizing the existing works. Then, based on the characters of this search space, we design a relation-sequence-aware search strategy, realizing the automatic design of the TP model. Finally, we find appropriate federated training methods to respectively support the TP model search and final model training under the FL framework, ensuring both the search efficiency and the final model performance. Extensive experimental results show that ATPFL can help users gain well-performed TP models, achieving better results than the existing TP models trained on the single-source dataset.
-
Batch Normalization is a staple of computer vision models, including those employed in few-shot learning. Batch Normalization layers in convolutional neural networks are composed of a normalization step, followed by a shift and scale of these normalized features applied via the per-channel trainable affine parameters gamma and beta. These affine parameters were introduced to maintain the expressive powers of the model following normalization. While this hypothesis holds true for classification within the same domain, this work illustrates that these parameters are detrimental to downstream performance on common few-shot transfer tasks. This effect is studied with multiple methods on well-known benchmarks such as few-shot classification on miniImageNet and cross-domain few-shot learning (CD-FSL). Experiments reveal consistent performance improvements on CNNs with affine unaccompanied Batch Normalization layers; particularly in large domain-shift few-shot transfer settings. As opposed to common practices in few-shot transfer learning where the affine parameters are fixed during the adaptation phase, we show fine-tuning them can lead to improved performance.
-
Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class activation map (CAM) to generate a localization map; however, a CAM identifies only the most discriminative parts of a target object rather than the entire object region. In this work, we find the gap between classification and localization in terms of the misalignment of the directions between an input feature and a class-specific weight. We demonstrate that the misalignment suppresses the activation of CAM in areas that are less discriminative but belong to the target object. To bridge the gap, we propose a method to align feature directions with a class-specific weight. The proposed method achieves a state-of-the-art localization performance on the CUB-200-2011 and ImageNet-1K benchmarks.
-
This paper proposes a new transformer-based framework to learn class-specific object localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to form a class-agnostic localization map, we investigate if the transformer model can also effectively capture class-specific attention for more discriminative object localization by learning multiple class tokens within the transformer. To this end, we propose a Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens. The proposed MCTformer can successfully produce class-discriminative object localization maps from the class-to-patch attentions corresponding to different class tokens. We also propose to use a patch-level pairwise affinity, which is extracted from the patch-to-patch transformer attention, to further refine the localization maps. Moreover, the proposed framework is shown to fully complement the Class Activation Mapping (CAM) method, leading to remarkably superior WSSS results on the PASCAL VOC and MS COCO datasets. These results underline the importance of the class token for WSSS.
-
We introduce 3D Moments, a new computational photography effect. As input we take a pair of near-duplicate photos, i.e., photos of moving subjects from similar viewpoints, common in people's photo collections. As output, we produce a video that smoothly interpolates the scene motion from the first photo to the second, while also producing camera motion with parallax that gives a heightened sense of 3D. To achieve this effect, we represent the scene as a pair of feature-based layered depth images augmented with scene flow. This representation enables motion interpolation along with independent control of the camera viewpoint. Our system produces photorealistic space-time videos with motion parallax and scene dynamics, while plausibly recovering regions occluded in the original views. We conduct extensive experiments demonstrating superior performance over baselines on public datasets and in-the-wild photos. Project page: https://3d-moments.github.io/.
-
Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging visual learning tasks, which can be cast as a feature distribution matching problem. With the assumption of Gaussian feature distribution, conventional feature distribution matching methods usually match the mean and standard deviation of features. However, the feature distributions of real-world data are usually much more complicated than Gaussian, which cannot be accurately matched by using only the first-order and second-order statistics, while it is computationally prohibitive to use high-order statistics for distribution matching. In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space. Particularly, a fast EHM algorithm, named Sort-Matching, is employed to perform EFDM in a plug-and-play manner with minimal cost. The effectiveness of our proposed EFDM method is verified on a variety of AST and DG tasks, demonstrating new state-of-the-art results. Codes are available at https://github.com/YBZh/EFDM.
-
Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile, supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised denoisers, which learn only from single noisy images, solve the data collection problem. However, self-supervised denoising methods, especially blindspot-driven ones, suffer sizable information loss during input or network design. The absence of valuable information dramatically reduces the upper bound of denoising performance. In this paper, we propose a simple yet efficient approach called Blind2Unblind to overcome the information loss in blindspot-driven denoising methods. First, we introduce a global-aware mask mapper that enables global perception and accelerates training. The mask mapper samples all pixels at blind spots on denoised volumes and maps them to the same channel, allowing the loss function to optimize all blind spots at once. Second, we propose a re-visible loss to train the denoising network and make blind spots visible. The denoiser can learn directly from raw noise images without losing information or being trapped in identity mapping. We also theoretically analyze the convergence of the re-visible loss. Extensive experiments on synthetic and real-world datasets demonstrate the superior performance of our approach compared to previous work. Code is available at https://github.com/demonsjin/Blind2Unblind.
-
Instance-level feature matching is significantly important to the success of modern one-shot object detectors. Recently, the methods based on the metric-learning paradigm have achieved an impressive process. Most of these works only measure the relations between query and target objects on a single level, resulting in suboptimal performance overall. In this paper, we introduce the balanced and hierarchical learning for our detector. The contributions are two-fold: firstly, a novel Instance-level Hierarchical Relation (IHR) module is proposed to encode the contrastive-level, salient-level, and attention-level relations simultaneously to enhance the query-relevant similarity representation. Secondly, we notice that the batch training of the IHR module is substantially hindered by the positive-negative sample imbalance in the one-shot scenario. We then introduce a simple but effective Ratio-Preserving Loss (RPL) to protect the learning of rare positive samples and suppress the effects of negative samples. Our loss can adjust the weight for each sample adaptively, ensuring the desired positive-negative ratio consistency and boosting query-related IHR learning. Extensive experiments show that our method outperforms the state-of-the-art method by 1.6% and 1.3% on PASCAL VOC and MS COCO datasets for unseen classes, respectively. The code will be available at https://github.com/hero-y/BHRL.
-
Recent video and language pretraining frameworks lack the ability to generate sentences. We present Multimodal Video Generative Pretraining (MV-GPT), a new pretraining framework for learning from unlabelled videos which can be effectively used for generative tasks such as multimodal video captioning. Unlike recent video-language pretraining frameworks, our framework trains both a multimodal video encoder and a sentence decoder jointly. To overcome the lack of captions in unlabelled videos, we leverage the future utterance as an additional text source and propose a bidirectional generation objective -- we generate future utterances given the present mulitmodal context, and also the present utterance given future observations. With this objective, we train an encoder-decoder model end-to-end to generate a caption from raw pixels and transcribed speech directly. Our model achieves state-of-the-art performance for multimodal video captioning on four standard benchmarks, as well as for other video understanding tasks such as generative and discriminative VideoQA, video retrieval and action classification.
-
Recently, Vision Transformers have achieved impressive results on various Vision tasks. Yet, their generalization ability under different distribution shifts is poorly understood. In this work, we provide a comprehensive study on the out-of-distribution generalization of Vision Transformers. To support a systematic investigation, we first present a taxonomy of distribution shifts by categorizing them into five conceptual levels: corruption shift, background shift, texture shift, destruction shift, and style shift. Then we perform extensive evaluations of Vision Transformer variants under different levels of distribution shifts and compare their generalization ability with Convolutional Neural Network (CNN) models. Several important observations are obtained: 1) Vision Transformers generalize better than CNNs under multiple distribution shifts. With the same or less amount of parameters, Vision Transformers are ahead of corresponding CNNs by more than 5% in top-1 accuracy under most types of distribution shift. In particular, Vision Transformers lead by more than 10% under the corruption shifts. 2) larger Vision Transformers gradually narrow the in-distribution (ID) and out-of-distribution (OOD) performance gap. To further improve the generalization of Vision Transformers, we design the enhanced Vision Transformers through self-supervised learning, information theory, and adversarial learning. By investigating these three types of generalization-enhanced Transformers, we observe the gradient-sensitivity of Vision Transformers and design a smoother learning strategy to achieve a stable training process. With modified training schemes, we achieve improvements on performance towards out-of-distribution data by 4% from vanilla Vision Transformers. We comprehensively compare these three types of generalization-enhanced Vision Transformers with their corresponding CNN models and observe that: 1) For the enhanced model, larger Vision Transformers still benefit more from the out-of-distribution generalization. 2) generalization-enhanced Vision Transformers are more sensitive to the hyper-parameters than their corresponding CNN models. We hope our comprehensive study could shed light on the design of more generalizable learning systems.
-
Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over-smoothed scene reconstructions and have difficulty scaling up to large scenes. These limitations are mainly due to their simple fully-connected network architecture that does not incorporate local information in the observations. In this paper, we present NICE-SLAM, a dense SLAM system that incorporates multi-level local information by introducing a hierarchical scene representation. Optimizing this representation with pre-trained geometric priors enables detailed reconstruction on large indoor scenes. Compared to recent neural implicit SLAM systems, our approach is more scalable, efficient, and robust. Experiments on five challenging datasets demonstrate competitive results of NICE-SLAM in both mapping and tracking quality. Project page: https://pengsongyou.github.io/nice-slam
-
A bathtub in a library, a sink in an office, a bed in a laundry room - the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects. In this paper, we propose HyperDet3D to explore scene-conditioned prior knowledge for 3D object detection. Existing methods strive for better representation of local elements and their relations without sceneconditioned knowledge, which may cause ambiguity merely based on the understanding of individual points and object candidates. Instead, HyperDet3D simultaneously learns scene-agnostic embeddings and scene-specific knowledge through scene-conditioned hypernetworks. More specifically, our HyperDet3D not only explores the sharable abstracts from various 3D scenes, but also adapts the detector to the given scene at test time. We propose a discriminative Multi-head Scene-specific Attention (MSA) module to dynamically control the layer parameters of the detector conditioned on the fusion of scene-conditioned knowledge. Our HyperDet3D achieves state-of-the-art results on the 3D object detection benchmark of the ScanNet and SUN RGB-D datasets. Moreover, through cross-dataset evaluation, we show the acquired scene-conditioned prior knowledge still takes effect when facing 3D scenes with domain gap.
-
Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states. Unlike existing stochastic trajectory prediction methods which usually use a latent variable to represent multi-modality, we explicitly simulate the process of human motion variation from indeterminate to determinate. In this paper, we present a new framework to formulate the trajectory prediction task as a reverse process of motion indeterminacy diffusion (MID), in which we progressively discard indeterminacy from all the walkable areas until reaching the desired trajectory. This process is learned with a parameterized Markov chain conditioned by the observed trajectories. We can adjust the length of the chain to control the degree of indeterminacy and balance the diversity and determinacy of the predictions. Specifically, we encode the history behavior information and the social interactions as a state embedding and devise a Transformer-based diffusion model to capture the temporal dependencies of trajectories. Extensive experiments on the human trajectory prediction benchmarks including the Stanford Drone and ETH/UCY datasets demonstrate the superiority of our method. Code is available at https://github.com/gutianpei/MID.
-
Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a traffic sign with high-level semantics, whereas it owns the specific local pattern which needs detailed low-level features to localize accurately. Using different feature levels is of great importance for accurate lane detection, but it is still under-explored. In this work, we present Cross Layer Refinement Network (CLRNet) aiming at fully utilizing both high-level and low-level features in lane detection. In particular, it first detects lanes with high-level semantic features then performs refinement based on low-level features. In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy. We present ROIGather to gather global context, which further enhances the feature representation of lanes. In addition to our novel network design, we introduce Line IoU loss which regresses the lane line as a whole unit to improve the localization accuracy. Experiments demonstrate that the proposed method greatly outperforms the state-of-the-art lane detection approaches. Code is available at:https://github.com/Turoad/CLRNet.
-
We consider the problem of Vision-and-Language Navigation (VLN). The majority of current methods for VLN are trained end-to-end using either unstructured memory such as LSTM, or using cross-modal attention over the egocentric observations of the agent. In contrast to other works, our key insight is that the association between language and vision is stronger when it occurs in explicit spatial representations. In this work, we propose a cross-modal map learning model for vision-and-language navigation that first learns to predict the top-down semantics on an egocentric map for both observed and unobserved regions, and then predicts a path towards the goal as a set of waypoints. In both cases, the prediction is informed by the language through cross-modal attention mechanisms. We experimentally test the basic hypothesis that language-driven navigation can be solved given a map, and then show competitive results on the full VLN-CE benchmark.
-
In light of the success of contrastive learning in the image domain, current self-supervised video representation learning methods usually employ contrastive loss to facilitate video representation learning. When naively pulling two augmented views of a video closer, the model however tends to learn the common static background as a shortcut but fails to capture the motion information, a phenomenon dubbed as background bias. Such bias makes the model suffer from weak generalization ability, leading to worse performance on downstream tasks such as action recognition. To alleviate such bias, we propose Foreground-background Merging (FAME) to deliberately compose the moving foreground region of the selected video onto the static background of others. Specifically, without any off-the-shelf detector, we extract the moving foreground out of background regions via the frame difference and color statistics, and shuffle the background regions among the videos. By leveraging the semantic consistency between the original clips and the fused ones, the model focuses more on the motion patterns and is debiased from the background shortcut. Extensive experiments demonstrate that FAME can effectively resist background cheating and thus achieve the state-of-the-art performance on downstream tasks across UCF101, HMDB51, and Diving48 datasets. The code and configurations are released at https://github.com/Mark12Ding/FAME.
-
Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures. Some specific methods can only tackle regular textures while losing holistic structures due to the limited receptive fields of convolutional neural networks (CNNs). On the other hand, attention-based models can learn better long-range dependency for the structure recovery, but they are limited by the heavy computation for inference with large image sizes. To address these issues, we propose to leverage an additional structure restorer to facilitate the image inpainting incrementally. The proposed model restores holistic image structures with a powerful attention-based transformer model in a fixed low-resolution sketch space. Such a grayscale space is easy to be upsampled to larger scales to convey correct structural information. Our structure restorer can be integrated with other pretrained inpainting models efficiently with the zero-initialized residual addition. Furthermore, a masking positional encoding strategy is utilized to improve the performance of the proposed model with large irregular masks. Extensive experiments on various datasets validate the efficacy of our model compared with other competitors.
-
We propose an embarrassingly simple point annotation scheme to collect weak supervision for instance segmentation. In addition to bounding boxes, we collect binary labels for a set of points uniformly sampled inside each bounding box. We show that the existing instance segmentation models developed for full mask supervision can be seamlessly trained with point-based supervision collected via our scheme. Remarkably, Mask R-CNN trained on COCO, PASCAL VOC, Cityscapes, and LVIS with only 10 annotated random points per object achieves 94%-98% of its fully-supervised performance, setting a strong baseline for weakly-supervised instance segmentation. The new point annotation scheme is approximately 5 times faster than annotating full object masks, making high-quality instance segmentation more accessible in practice. Inspired by the point-based annotation form, we propose a modification to PointRend instance segmentation module. For each object, the new architecture, called Implicit PointRend, generates parameters for a function that makes the final point-level mask prediction. Implicit PointRend is more straightforward and uses a single point-level mask loss. Our experiments show that the new module is more suitable for the point-based supervision.
-
Automatic generation of ophthalmic reports using data-driven neural networks has great potential in clinical practice. When writing a report, ophthalmologists make inferences with prior clinical knowledge. This knowledge has been neglected in prior medical report generation methods. To endow models with the capability of incorporating expert knowledge, we propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG), in which clinical relation triples are injected into the visual features as prior knowledge to drive the decoding procedure. However, two major common Knowledge Noise (KN) issues may affect models' effectiveness. 1) Existing general biomedical knowledge bases such as the UMLS may not align meaningfully to the specific context and language of the report, limiting their utility for knowledge injection. 2) Incorporating too much knowledge may divert the visual features from their correct meaning. To overcome these limitations, we design an automatic information extraction scheme based on natural language processing to obtain clinical entities and relations directly from in-domain training reports. Given a set of ophthalmic images, our CGT first restores a sub-graph from the clinical graph and injects the restored triples into visual features. Then visible matrix is employed during the encoding procedure to limit the impact of knowledge. Finally, reports are predicted by the encoded cross-modal features via a Transformer decoder. Extensive experiments on the large-scale FFA-IR benchmark demonstrate that the proposed CGT is able to outperform previous benchmark methods and achieve state-of-the-art performances.
-
Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decoder for triplet prediction, or utilize two parallel decoders to detect individual objects and interactions separately, and compose triplets by a matching process. In contrast, we decouple the triplet prediction into human-object pair detection and interaction classification. Our main motivation is that detecting the human-object instances and classifying interactions accurately needs to learn representations that focus on different regions. To this end, we present Disentangled Transformer, where both encoder and decoder are disentangled to facilitate learning of two subtasks. To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder. Extensive experiments show that our method outperforms prior work on two public HOI benchmarks by a sizeable margin. Code will be available.
-
To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target). Despite impressive progress, prior methods always need to access the raw source data and develop data-dependent alignment approaches to recognize the target samples in a transductive learning manner, which may raise privacy concerns from source individuals. Several recent studies resort to an alternative solution by exploiting the well-trained white-box model from the source domain, yet, it may still leak the raw data via generative adversarial learning. This paper studies a practical and interesting setting for UDA, where only black-box source models (i.e., only network predictions are available) are provided during adaptation in the target domain. To solve this problem, we propose a new two-step knowledge adaptation framework called DIstill and fine-tuNE (DINE). Taking into consideration the target data structure, DINE first distills the knowledge from the source predictor to a customized target model, then fine-tunes the distilled model to further fit the target domain. Besides, neural networks are not required to be identical across domains in DINE, even allowing effective adaptation on a low-resource device. Empirical results on three UDA scenarios (i.e., single-source, multi-source, and partial-set) confirm that DINE achieves highly competitive performance compared to state-of-the-art data-dependent approaches. Code is available at https://github.com/tim-learn/DINE/.
-
3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or horizon-depth. We present that using horizon-depth along with room height can obtain omnidirectional-geometry awareness of room layout in both horizontal and vertical directions. In addition, we propose a planar-geometry aware loss function with normals and gradients of normals to supervise the planeness of walls and turning of corners. We propose an efficient network, LGT-Net, for room layout estimation, which contains a novel Transformer architecture called SWG-Transformer to model geometry relations. SWG-Transformer consists of (Shifted) Window Blocks and Global Blocks to combine the local and global geometry relations. Moreover, we design a novel relative position embedding of Transformer to enhance the spatial identification ability for the panorama. Experiments show that the proposed LGT-Net achieves better performance than current state-of-the-arts (SOTA) on benchmark datasets.
-
Referring image segmentation aims to segment a referent via a natural linguistic expression. Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing approaches use pretrained models to facilitate learning, yet separately transfer the language/vision knowledge from pretrained models, ignoring the multi-modal corresponding information. Inspired by the recent advance in Contrastive Language-Image Pretraining (CLIP), in this paper, we propose an end-to-end CLIP-Driven Referring Image Segmentation framework (CRIS). To transfer the multi-modal knowledge effectively, CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. More specifically, we design a vision-language decoder to propagate fine-grained semantic information from textual representations to each pixel-level activation, which promotes consistency between the two modalities. In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances. The experimental results on three benchmark datasets demonstrate that our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
-
We propose an analysis-by-synthesis method for fast multi-view 3D reconstruction of opaque objects with arbitrary materials and illumination. State-of-the-art methods use both neural surface representations and neural rendering. While flexible, neural surface representations are a significant bottleneck in optimization runtime. Instead, we represent surfaces as triangle meshes and build a differentiable rendering pipeline around triangle rasterization and neural shading. The renderer is used in a gradient descent optimization where both a triangle mesh and a neural shader are jointly optimized to reproduce the multi-view images. We evaluate our method on a public 3D reconstruction dataset and show that it can match the reconstruction accuracy of traditional baselines and neural approaches while surpassing them in optimization runtime. Additionally, we investigate the shader and find that it learns an interpretable representation of appearance, enabling applications such as 3D material editing.
-
Recently, significant progress has been made on image denoising with strong supervision from large-scale datasets. However, obtaining well-aligned noisy-clean training image pairs for each specific scenario is complicated and costly in practice. Consequently, applying a conventional supervised denoising network on in-the-wild noisy inputs is not straightforward. Although several studies have challenged this problem without strong supervision, they rely on less practical assumptions and cannot be applied to practical situations directly. To address the aforementioned challenges, we propose a novel and powerful self-supervised denoising method called CVF-SID based on a Cyclic multi-Variate Function (CVF) module and a self-supervised image disentangling (SID) framework. The CVF module can output multiple decomposed variables of the input and take a combination of the outputs back as an input in a cyclic manner. Our CVF-SID can disentangle a clean image and noise maps from the input by leveraging various self-supervised loss terms. Unlike several methods that only consider the signal-independent noise models, we also deal with signal-dependent noise components for real-world applications. Furthermore, we do not rely on any prior assumptions about the underlying noise distribution, making CVF-SID more generalizable toward realistic noise. Extensive experiments on real-world datasets show that CVF-SID achieves state-of-the-art self-supervised image denoising performance and is comparable to other existing approaches. The code is publicly available from this link.
-
Thermal infrared imaging is widely used in body temperature measurement, security monitoring, and so on, but its safety research attracted attention only in recent years. We proposed the infrared adversarial clothing, which could fool infrared pedestrian detectors at different angles. We simulated the process from cloth to clothing in the digital world and then designed the adversarial "QR code" pattern. The core of our method is to design a basic pattern that can be expanded periodically, and make the pattern after random cropping and deformation still have an adversarial effect, then we can process the flat cloth with an adversarial pattern into any 3D clothes. The results showed that the optimized "QR code" pattern lowered the Average Precision (AP) of YOLOv3 by 87.7%, while the random "QR code" pattern and blank pattern lowered the AP of YOLOv3 by 57.9% and 30.1%, respectively, in the digital world. We then manufactured an adversarial shirt with a new material: aerogel. Physical-world experiments showed that the adversarial "QR code" pattern clothing lowered the AP of YOLOv3 by 64.6%, while the random "QR code" pattern clothing and fully heat-insulated clothing lowered the AP of YOLOv3 by 28.3% and 22.8%, respectively. We used the model ensemble technique to improve the attack transferability to unseen models.
-
In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. Different from existing top-down and bottom-up methods, the proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. This leads to a simplified pipeline with enhanced efficiency. In addition, DAS learns the true distribution of body joints for the regression of their positions, rather than making a simple Laplacian or Gaussian assumption as previous works. This provides valuable priors for model prediction and thus boosts the regression-based scheme to achieve competitive performance with volumetric-base ones. Moreover, DAS exploits a recursive update strategy for progressively approaching to regression target, alleviating the optimization difficulty and further lifting the regression performance. DAS is implemented with a fully Convolutional Neural Network and end-to-end learnable. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model, specifically 1.5x speedup over previous best model, and its stat-of-the-art accuracy for multi-person 3D pose estimation.
-
Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with limited context, occasionally resulting in inaccurate lip movements. To tackle this limitation, we propose a Transformer-based autoregressive model, FaceFormer, which encodes the long-term audio context and autoregressively predicts a sequence of animated 3D face meshes. To cope with the data scarcity issue, we integrate the self-supervised pre-trained speech representations. Also, we devise two biased attention mechanisms well suited to this specific task, including the biased cross-modal multi-head (MH) attention and the biased causal MH self-attention with a periodic positional encoding strategy. The former effectively aligns the audio-motion modalities, whereas the latter offers abilities to generalize to longer audio sequences. Extensive experiments and a perceptual user study show that our approach outperforms the existing state-of-the-arts. The code and the video are available at: https://evelynfan.github.io/audio2face/.
-
Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence. However, the methods often ignore the diverse semantic relation within the images. To address this, here we propose a novel semantic relation consistency (SRC) regularization along with the decoupled contrastive learning (DCL), which utilize the diverse semantics by focusing on the heterogeneous semantics between the image patches of a single image. To further improve the performance, we present a hard negative mining by exploiting the semantic relation. We verified our method for three tasks: single-modal and multi-modal image translations, and GAN compression task for image translation. Experimental results confirmed the state-of-art performance of our method in all the three tasks.
-
We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure attributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark-driven structure transfer latent direction. The disentangled latent code produces rich generative features that incorporate feature blending to produce a plausible swapping result. We further extend our method to video face swapping by enforcing two spatio-temporal constraints on the latent space and the image space. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art image/video face swapping methods in terms of hallucination quality and consistency.
-
Customizing Convolution Neural Networks (CNN) for production use has been a challenging task for DL practitioners. This paper intends to expedite the model customization with a model hub that contains the optimized models tiered by their inference latency using Neural Architecture Search (NAS). To achieve this goal, we build a distributed NAS system to search on a novel search space that consists of prominent factors to impact latency and accuracy. Since we target GPU, we name the NAS optimized models as GPUNet, which establishes a new SOTA Pareto frontier in inference latency and accuracy. Within 1ms, GPUNet is 2x faster than EfficientNet-X and FBNetV3 with even better accuracy. We also validate GPUNet on detection tasks, and GPUNet consistently outperforms EfficientNet-X and FBNetV3 on COCO detection tasks in both latency and accuracy. All of these data validate that our NAS system is effective and generic to handle different design tasks. With this NAS system, we expand GPUNet to cover more latency groups to be directly reusable to DL practitioners in various deployment scenarios.
-
Heatmap regression methods have dominated face alignment area in recent years while they ignore the inherent relation between different landmarks. In this paper, we propose a Sparse Local Patch Transformer (SLPT) for learning the inherent relation. The SLPT generates the representation of each single landmark from a local patch and aggregates them by an adaptive inherent relation based on the attention mechanism. The subpixel coordinate of each landmark is predicted independently based on the aggregated feature. Moreover, a coarse-to-fine framework is further introduced to incorporate with the SLPT, which enables the initial landmarks to gradually converge to the target facial landmarks using fine-grained features from dynamically resized local patches. Extensive experiments carried out on three popular benchmarks, including WFLW, 300W and COFW, demonstrate that the proposed method works at the state-of-the-art level with much less computational complexity by learning the inherent relation between facial landmarks. The code is available at the project website.
-
In recent years, with the advances of generative models, many powerful face manipulation systems have been developed based on Deep Neural Networks (DNNs), called DeepFakes. If DeepFakes are not controlled timely and properly, they would become a real threat to both celebrities and ordinary people. Precautions such as adding perturbations to the source inputs will make DeepFake results look distorted from the perspective of human eyes. However, previous method doesn't explore whether the disrupted images can still spoof DeepFake detectors. This is critical for many applications where DeepFake detectors are used to discriminate between DeepFake data and real data due to the huge cost of examining a large amount of data manually. We argue that the detectors do not share a similar perspective as human eyes, which might still be spoofed by the disrupted data. Besides, the existing disruption methods rely on iteration-based perturbation generation algorithms, which is time-consuming. In this paper, we propose a novel DeepFake disruption algorithm called "DeepFake Disrupter". By training a perturbation generator, we can add the human-imperceptible perturbations to source images that need to be protected without any backpropagation update. The DeepFake results of these protected source inputs would not only look unrealistic by the human eye but also can be distinguished by DeepFake detectors easily. For example, experimental results show that by adding our trained perturbations, fake images generated by StarGAN can result in a 10 20% increase in F1-score evaluated by various DeepFake detectors.
-
Rotation equivariance has recently become a strongly desired property in the 3D deep learning community. Yet most existing methods focus on equivariance regarding a global input rotation while ignoring the fact that rotation symmetry has its own spatial support. Specifically, we consider the object detection problem in 3D scenes, where an object bounding box should be equivariant regarding the object pose, independent of the scene motion. This suggests a new desired property we call object-level rotation equivariance. To incorporate object-level rotation equivariance into 3D object detectors, we need a mechanism to extract equivariant features with local object-level spatial support while being able to model cross-object context information. To this end, we propose Equivariant Object detection Network (EON) with a rotation equivariance suspension design to achieve object-level equivariance. EON can be applied to modern point cloud object detectors, such as VoteNet and PointRCNN, enabling them to exploit object rotation symmetry in scene-scale inputs. Our experiments on both indoor scene and autonomous driving datasets show that significant improvements are obtained by plugging our EON design into existing state-of-the-art 3D object detectors. Project website: https://kovenyu.com/EON/.
-
The recently developed DEtection TRansformer (DETR) establishes a new object detection paradigm by eliminating a series of hand-crafted components. However, DETR suffers from extremely slow convergence, which increases the training cost significantly. We observe that the slow convergence is largely attributed to the complication in matching object queries with target features in different feature embedding spaces. This paper presents SAM-DETR, a Semantic-Aligned-Matching DETR that greatly accelerates DETR's convergence without sacrificing its accuracy. SAM-DETR addresses the convergence issue from two perspectives. First, it projects object queries into the same embedding space as encoded image features, where the matching can be accomplished efficiently with aligned semantics. Second, it explicitly searches salient points with the most discriminative features for semantic-aligned matching, which further speeds up the convergence and boosts detection accuracy as well. Being like a plug and play, SAM-DETR complements existing convergence solutions well yet only introduces slight computational overhead. Extensive experiments show that the proposed SAM-DETR achieves superior convergence as well as competitive detection accuracy. The implementation codes are publicly available at https://github.com/ZhangGongjie/SAM-DETR.
-
Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on large-scale image datasets to achieve top performance. In this paper, we empirically demonstrate that self-supervised pretraining of video transformers on video-only datasets can lead to action recognition results that are on par or better than those obtained with supervised pretraining on large-scale image datasets, even massive ones such as ImageNet-21K. Since transformer-based models are effective at capturing dependencies over extended temporal spans, we propose a simple learning procedure that forces the model to match a long-term view to a short-term view of the same video. Our approach, named Long-Short Temporal Contrastive Learning (LSTCL), enables video transformers to learn an effective clip-level representation by predicting temporal context captured from a longer temporal extent. To demonstrate the generality of our findings, we implement and validate our approach under three different self-supervised contrastive learning frameworks (MoCo v3, BYOL, SimSiam) using two distinct video-transformer architectures, including an improved variant of the Swin Transformer augmented with space-time attention. We conduct a thorough ablation study and show that LSTCL achieves competitive performance on multiple video benchmarks and represents a convincing alternative to supervised image-based pretraining.
-
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply enlarging receptive field also gives rise to several concerns. On the one hand, using dense attention e.g., in ViT, leads to excessive memory and computational cost, and features can be influenced by irrelevant parts which are beyond the region of interests. On the other hand, the sparse attention adopted in PVT or Swin Trans-former is data agnostic and may limit the ability to model long range relations. To mitigate these issues, we propose a novel deformable self-attention module, where the positions of key and value pairs in self-attention are selected in a data-dependent way. This flexible scheme enables the self-attention module to focus on relevant regions and cap-ture more informative features. On this basis, we present Deformable Attention Transformer, a general backbone model with deformable attention for both image classifi-cation and dense prediction tasks. Extensive experiments show that our models achieve consistently improved results on comprehensive benchmarks.
-
Computer vision systems today are primarily N-purpose systems, designed and trained for a predefined set of tasks. Adapting such systems to new tasks is challenging and often requires non-trivial modifications to the network architecture (e.g. adding new output heads) or training process (e.g. adding new losses). To reduce the time and expertise required to develop new applications, we would like to create general purpose vision systems that can learn and perform a range of tasks without any modification to the architecture or learning process. In this paper, we propose GPV-1, a task-agnostic vision-language architecture that can learn and perform tasks that involve receiving an image and producing text and/or bounding boxes, including classification, localization, visual question answering, captioning, and more. We also propose evaluations of generality of architecture, skill-concept transfer, and learning efficiency that may inform future work on general purpose vision. Our experiments indicate GPV-1 is effective at multiple tasks, reuses some concept knowledge across tasks, can perform the Referring Expressions task zero-shot, and further improves upon the zero-shot performance using a few training samples.
-
Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here, we address these issues by injecting deep vanishing point detection networks with prior knowledge. This prior knowledge no longer needs to be learned from data, saving valuable annotation efforts and compute, unlocking realistic few-sample scenarios, and reducing the impact of domain changes. Moreover, the interpretability of the priors allows to adapt deep networks to minor problem variations such as switching between Manhattan and non-Manhattan worlds. We seamlessly incorporate two geometric priors: (i) Hough Transform -- mapping image pixels to straight lines, and (ii) Gaussian sphere -- mapping lines to great circles whose intersections denote vanishing points. Experimentally, we ablate our choices and show comparable accuracy to existing models in the large-data setting. We validate our model's improved data efficiency, robustness to domain changes, adaptability to non-Manhattan settings.
-
Unsupervised methods have showed promising results on monocular depth estimation. However, the training data must be captured in scenes without moving objects. To push the envelope of accuracy, recent methods tend to increase their model parameters. In this paper, an unsupervised learning framework is proposed to jointly predict monocular depth and complete 3D motion including the motions of moving objects and camera. (1) Recurrent modulation units are used to adaptively and iteratively fuse encoder and decoder features. This improves the single-image depth inference without overspending model parameters. (2) Instead of using a single set of filters for upsampling, multiple sets of filters are devised for the residual upsampling. This facilitates the learning of edge-preserving filters and leads to the improved performance. (3) A warping-based network is used to estimate a motion field of moving objects without using semantic priors. This breaks down the requirement of scene rigidity and allows to use general videos for the unsupervised learning. The motion field is further regularized by an outlier-aware training loss. Despite the depth model just uses a single image in test time and 2.97M parameters, it achieves state-of-the-art results on the KITTI and Cityscapes benchmarks.
-
This paper presents contrastive-tuning, a simple method employing contrastive training to align image and text models while still taking advantage of their pre-training. In our empirical study we find that locked pre-trained image models with unlocked text models work best. We call this instance of contrastive-tuning "Locked-image Tuning" (LiT), which just teaches a text model to read out good representations from a pre-trained image model for new tasks. A LiT model gains the capability of zero-shot transfer to new vision tasks, such as image classification or retrieval. The proposed LiT is widely applicable; it works reliably with multiple pre-training methods (supervised and unsupervised) and across diverse architectures (ResNet, Vision Transformers and MLP-Mixer) using three different image-text datasets. With the transformer-based pre-trained ViT-g/14 model, the LiT model achieves 84.5% zero-shot transfer accuracy on the ImageNet test set, and 81.1% on the challenging out-of-distribution ObjectNet test set.
-
Recently, large-scale synthetic datasets are shown to be very useful for generalizable person re-identification. However, synthesized persons in existing datasets are mostly cartoon-like and in random dress collocation, which limits their performance. To address this, in this work, an automatic approach is proposed to directly clone the whole outfits from real-world person images to virtual 3D characters, such that any virtual person thus created will appear very similar to its real-world counterpart. Specifically, based on UV texture mapping, two cloning methods are designed, namely registered clothes mapping and homogeneous cloth expansion. Given clothes keypoints detected on person images and labeled on regular UV maps with clear clothes structures, registered mapping applies perspective homography to warp real-world clothes to the counterparts on the UV map. As for invisible clothes parts and irregular UV maps, homogeneous expansion segments a homogeneous area on clothes as a realistic cloth pattern or cell, and expand the cell to fill the UV map. Furthermore, a similarity-diversity expansion strategy is proposed, by clustering person images, sampling images per cluster, and cloning outfits for 3D character generation. This way, virtual persons can be scaled up densely in visual similarity to challenge model learning, and diversely in population to enrich sample distribution. Finally, by rendering the cloned characters in Unity3D scenes, a more realistic virtual dataset called ClonedPerson is created, with 5,621 identities and 887,766 images. Experimental results show that the model trained on ClonedPerson has a better generalization performance, superior to that trained on other popular real-world and synthetic person re-identification datasets. The ClonedPerson project is available at https://github.com/Yanan-Wang-cs/ClonedPerson.
-
We present GeoNeRF, a generalizable photorealistic novel view synthesis method based on neural radiance fields. Our approach consists of two main stages: a geometry reasoner and a renderer. To render a novel view, the geometry reasoner first constructs cascaded cost volumes for each nearby source view. Then, using a Transformer-based attention mechanism and the cascaded cost volumes, the renderer infers geometry and appearance, and renders detailed images via classical volume rendering techniques. This architecture, in particular, allows sophisticated occlusion reasoning, gathering information from consistent source views. Moreover, our method can easily be fine-tuned on a single scene, and renders competitive results with per-scene optimized neural rendering methods with a fraction of computational cost. Experiments show that GeoNeRF outperforms state-of-the-art generalizable neural rendering models on various synthetic and real datasets. Lastly, with a slight modification to the geometry reasoner, we also propose an alternative model that adapts to RGBD images. This model directly exploits the depth information often available thanks to depth sensors. The implementation code is available at https://www.idiap.ch/paper/geonerf.
-
Photo retouching finds many applications in various fields. However, most existing methods are designed for global retouching and seldom pay attention to the local region, while the latter is actually much more tedious and time-consuming in photography pipelines. In this paper, we propose a novel adaptive blend pyramid network, which aims to achieve fast local retouching on ultra high-resolution photos. The network is mainly composed of two components: a context-aware local retouching layer (LRL) and an adaptive blend pyramid layer (BPL). The LRL is designed to implement local retouching on low-resolution images, giving full consideration of the global context and local texture information, and the BPL is then developed to progressively expand the low-resolution results to the higher ones, with the help of the proposed adaptive blend module and refining module. Our method outperforms the existing methods by a large margin on two local photo retouching tasks and exhibits excellent performance in terms of running speed, achieving real-time inference on 4K images with a single NVIDIA Tesla P100 GPU. Moreover, we introduce the first high-definition cloth retouching dataset CRHD-3K to promote the research on local photo retouching. The dataset is available at https://github.com/youngLBW/CRHD-3K.
-
Object pose estimation is crucial for robotic applications and augmented reality. Beyond instance level 6D object pose estimation methods, estimating category-level pose and shape has become a promising trend. As such, a new research field needs to be supported by well-designed datasets. To provide a benchmark with high-quality ground truth annotations to the community, we introduce a multimodal dataset for category-level object pose estimation with photometrically challenging objects termed PhoCaL. PhoCaL comprises 60 high quality 3D models of household objects over 8 categories including highly reflective, transparent and symmetric objects. We developed a novel robot-supported multi-modal (RGB, depth, polarisation) data acquisition and annotation process. It ensures sub-millimeter accuracy of the pose for opaque textured, shiny and transparent objects, no motion blur and perfect camera synchronisation. To set a benchmark for our dataset, state-of-the-art RGB-D and monocular RGB methods are evaluated on the challenging scenes of PhoCaL.
-
Most existing deep learning (DL)-based video restoration methods focus on the network structure design to better extract temporal features but ignore how to utilize these extracted temporal features efficiently. The temporal features usually contain various noisy and irrelative information, and they may interfere with the restoration of the current frame. This paper proposes learning noise-robust feature representations to help video restoration. From information theory, we know the noisy data generally has a high degree of uncertainty, thus we design a neural compression module to filter the noise with large uncertainty and refine the features. Our compression module adopts a spatial-channel-wise quantization mechanism to adaptively filter the noise and purify the features with different content characteristics to achieve robustness to noise. The information entropy loss is used to guide the learning of the compression module and helps it preserve the most useful information. Experiments show that our method can significantly boost the performance on video denoising. Under noise level 50, we obtain 0.13 dB improvement over BasicVSR++ with only 0.23x FLOPs. Meanwhile, our method also achieves SOTA results on video deraining and dehazing.
-
Modern object detectors have achieved impressive progress under the close-set setup. However, open-set object detection (OSOD) remains challenging since objects of unknown categories are often misclassified to existing known classes. In this work, we propose to identify unknown objects by separating high/low-density regions in the latent space, based on the consensus that unknown objects are usually distributed in low-density latent regions. As traditional threshold-based methods only maintain limited low-density regions, which cannot cover all unknown objects, we present a novel Open-set Detector (OpenDet) with expanded low-density regions. To this aim, we equip OpenDet with two learners, Contrastive Feature Learner (CFL) and Unknown Probability Learner (UPL). CFL performs instance-level contrastive learning to encourage compact features of known classes, leaving more low-density regions for unknown classes; UPL optimizes unknown probability based on the uncertainty of predictions, which further divides more low-density regions around the cluster of known classes. Thus, unknown objects in low-density regions can be easily identified with the learned unknown probability. Extensive experiments demonstrate that our method can significantly improve the OSOD performance, e.g., OpenDet reduces the Absolute Open-Set Errors by 25%-35% on six OSOD benchmarks. Code is available at: https://github.com/csuhan/opendet2.
-
Image manipulation dates back long before the deep learning era. The classical prevailing approaches were based on maximizing patch similarity between the input and generated output. Recently, single-image GANs were introduced as a superior and more sophisticated solution to image manipulation tasks. Moreover, they offered the opportunity not only to manipulate a given image, but also to generate a large and diverse set of different outputs from a single natural image. This gave rise to new tasks, which are considered "DL-only". However, despite their impressiveness, single-image GANs require long training time (usually hours) for each image and each task and often suffer from visual artifacts. In this paper we revisit the classical patch-based methods, and show that - unlike previously believed -- classical methods can be adapted to tackle these novel "GAN-only" tasks. Moreover, they do so better and faster than single-image GAN-based methods. More specifically, we show that: (i) by introducing slight modifications, classical patch-based methods are able to unconditionally generate diverse images based on a single natural image; (ii) the generated output visual quality exceeds that of single-image GANs by a large margin (confirmed both quantitatively and qualitatively); (iii) they are orders of magnitude faster (runtime reduced from hours to seconds).
-
In this paper, we present Uformer, an effective and efficient Transformer-based architecture for image restoration, in which we build a hierarchical encoder-decoder network using the Transformer block. In Uformer, there are two core designs. First, we introduce a novel locally-enhanced window (LeWin) Transformer block, which performs non-overlapping window-based self-attention instead of global self-attention. It significantly reduces the computational complexity on high resolution feature map while capturing local context. Second, we propose a learnable multi-scale restoration modulator in the form of a multi-scale spatial bias to adjust features in multiple layers of the Uformer decoder. Our modulator demonstrates superior capability for restoring details for various image restoration tasks while introducing marginal extra parameters and computational cost. Powered by these two designs, Uformer enjoys a high capability for capturing both local and global dependencies for image restoration. To evaluate our approach, extensive experiments are conducted on several image restoration tasks, including image denoising, motion deblurring, defocus deblurring and deraining. Without bells and whistles, our Uformer achieves superior or comparable performance compared with the state-of-the-art algorithms. The code and models are available at https://github.com/ZhendongWang6/Uformer.
-
Pose Guided Person Image Generation (PGPIG) is the task of transforming a person image from the source pose to a given target pose. Most of the existing methods only focus on the ill-posed source-to-target task and fail to capture reasonable texture mapping. To address this problem, we propose a novel Dual-task Pose Transformer Network (DPTN), which introduces an auxiliary task (i.e., source-tosource task) and exploits the dual-task correlation to promote the performance of PGPIG. The DPTN is of a Siamese structure, containing a source-to-source self-reconstruction branch, and a transformation branch for source-to-target generation. By sharing partial weights between them, the knowledge learned by the source-to-source task can effectively assist the source-to-target learning. Furthermore, we bridge the two branches with a proposed Pose Transformer Module (PTM) to adaptively explore the correlation between features from dual tasks. Such correlation can establish the fine-grained mapping of all the pixels between the sources and the targets, and promote the source texture transmission to enhance the details of the generated target images. Extensive experiments show that our DPTN outperforms state-of-the-arts in terms of both PSNR and LPIPS. In addition, our DPTN only contains 9.79 million parameters, which is significantly smaller than other approaches. Our code is available at: https://github.com/PangzeCheung/Dual-task-Pose-Transformer-Network.
-
In portraits, eyeglasses may occlude facial regions and generate cast shadows on faces, which degrades the performance of many techniques like face verification and expression recognition. Portrait eyeglasses removal is critical in handling these problems. However, completely removing the eyeglasses is challenging because the lighting effects (e.g., cast shadows) caused by them are often complex. In this paper, we propose a novel framework to remove eyeglasses as well as their cast shadows from face images. The method works in a detect-then-remove manner, in which eyeglasses and cast shadows are both detected and then removed from images. Due to the lack of paired data for supervised training, we present a new synthetic portrait dataset with both intermediate and final supervisions for both the detection and removal tasks. Furthermore, we apply a cross-domain technique to fill the gap between the synthetic and real data. To the best of our knowledge, the proposed technique is the first to remove eyeglasses and their cast shadows simultaneously. The code and synthetic dataset are available at https://github.com/StoryMY/take-off-eyeglasses.
-
We present a new neural representation, called Neural Ray (NeuRay), for the novel view synthesis task. Recent works construct radiance fields from image features of input views to render novel view images, which enables the generalization to new scenes. However, due to occlusions, a 3D point may be invisible to some input views. On such a 3D point, these generalization methods will include inconsistent image features from invisible views, which interfere with the radiance field construction. To solve this problem, we predict the visibility of 3D points to input views within our NeuRay representation. This visibility enables the radiance field construction to focus on visible image features, which significantly improves its rendering quality. Meanwhile, a novel consistency loss is proposed to refine the visibility in NeuRay when finetuning on a specific scene. Experiments demonstrate that our approach achieves state-of-the-art performance on the novel view synthesis task when generalizing to unseen scenes and outperforms per-scene optimization methods after finetuning.
-
Group re-identification (GReID) attempts to correctly associate groups with the same members under different cameras. The main challenge is how to resist the membership and layout variations. Existing works attempt to incorporate layout modeling on the basis of appearance features to achieve robust group representations. However, layout ambiguity is introduced because these methods only consider the 2D layout on the imaging plane. In this paper, we overcome the above limitations by 3D layout modeling. Specifically, we propose a novel 3D transformer (3DT) that reconstructs the relative 3D layout relationship among members, then applies sampling and quantification to preset a series of layout tokens along three dimensions, and selects the corresponding tokens as layout features for each member. Furthermore, we build a synthetic GReID dataset, City1M, including 1.84M images, 45K persons and 11.5K groups with 3D annotations to alleviate data shortages and poor annotations. To the best of our knowledge, 3DT is the first work to address GReID with 3D perspective, and the City1M is the currently largest dataset. Several experiments show the superiority of our 3DT and City1M. Our project has been released on https://github.com/LinlyAC/City1M-dataset.
-
Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely on explicit class semantics obtained from large labeled datasets, and out-of-domain evaluation performance drops significantly. Here we propose a novel approach for mask proposals, Generic Grouping Networks (GGNs), constructed without semantic supervision. Our approach combines a local measure of pixel affinity with instance-level mask supervision, producing a training regimen designed to make the model as generic as the data diversity allows. We introduce a method for predicting Pairwise Affinities (PA), a learned local relationship between pairs of pixels. PA generalizes very well to unseen categories. From PA we construct a large set of pseudo-ground-truth instance masks; combined with human-annotated instance masks we train GGNs and significantly outperform the SOTA on open-world instance segmentation on various benchmarks including COCO, LVIS, ADE20K, and UVO.
-
Object detection under imperfect data receives great attention recently. Weakly supervised object detection (WSOD) suffers from severe localization issues due to the lack of instance-level annotation, while semi-supervised object detection (SSOD) remains challenging led by the inter-image discrepancy between labeled and unlabeled data. In this study, we propose the Single Instance annotated Object Detection (SIOD), requiring only one instance annotation for each existing category in an image. Degraded from inter-task (WSOD) or inter-image (SSOD) discrepancies to the intra-image discrepancy, SIOD provides more reliable and rich prior knowledge for mining the rest of unlabeled instances and trades off the annotation cost and performance. Under the SIOD setting, we propose a simple yet effective framework, termed Dual-Mining (DMiner), which consists of a Similarity-based Pseudo Label Generating module (SPLG) and a Pixel-level Group Contrastive Learning module (PGCL). SPLG firstly mines latent instances from feature representation space to alleviate the annotation missing problem. To avoid being misled by inaccurate pseudo labels, we propose PGCL to boost the tolerance to false pseudo labels. Extensive experiments on MS COCO verify the feasibility of the SIOD setting and the superiority of the proposed method, which obtains consistent and significant improvements compared to baseline methods and achieves comparable results with fully supervised object detection (FSOD) methods with only 40% instances annotated.
-
Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios. In this paper, we develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. To be specific, we establish a cascaded illumination learning process with weight sharing to handle this task. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage, producing the gains that only use the single basic block for inference (yet has not been exploited in previous works), which drastically diminishes computation cost. We then define the unsupervised training loss to elevate the model capability that can adapt general scenes. Further, we make comprehensive explorations to excavate SCI's inherent properties (lacking in existing works) including operation-insensitive adaptability (acquiring stable performance under the settings of different simple operations) and model-irrelevant generality (can be applied to illumination-based existing works to improve performance). Finally, plenty of experiments and ablation studies fully indicate our superiority in both quality and efficiency. Applications on low-light face detection and nighttime semantic segmentation fully reveal the latent practical values for SCI. The source code is available at https://github.com/vis-opt-group/SCI.
-
In this paper, we present a novel approach to incrementally learn an Abstract Model of an unknown environment, and show how an agent can reuse the learned model for tackling the Object Goal Navigation task. The Abstract Model is a finite state machine in which each state is an abstraction of a state of the environment, as perceived by the agent in a certain position and orientation. The perceptions are high-dimensional sensory data (e.g., RGB-D images), and the abstraction is reached by exploiting image segmentation and the Taskonomy model bank. The learning of the Abstract Model is accomplished by executing actions, observing the reached state, and updating the Abstract Model with the acquired information. The learned models are memorized by the agent, and they are reused whenever it recognizes to be in an environment that corresponds to the stored model. We investigate the effectiveness of the proposed approach for the Object Goal Navigation task, relying on public benchmarks. Our results show that the reuse of learned Abstract Models can boost performance on Object Goal Navigation.
-
Action recognition models have shown a promising capability to classify human actions in short video clips. In a real scenario, multiple correlated human actions commonly occur in particular orders, forming semantically meaningful human activities. Conventional action recognition approaches focus on analyzing single actions. However, they fail to fully reason about the contextual relations between adjacent actions, which provide potential temporal logic for understanding long videos. In this paper, we propose a prompt-based framework, Bridge-Prompt (Br-Prompt), to model the semantics across adjacent actions, so that it simultaneously exploits both out-of-context and contextual information from a series of ordinal actions in instructional videos. More specifically, we reformulate the individual action labels as integrated text prompts for supervision, which bridge the gap between individual action semantics. The generated text prompts are paired with corresponding video clips, and together co-train the text encoder and the video encoder via a contrastive approach. The learned vision encoder has a stronger capability for ordinal-action-related downstream tasks, e.g. action segmentation and human activity recognition. We evaluate the performances of our approach on several video datasets: Georgia Tech Egocentric Activities (GTEA), 50Salads, and the Breakfast dataset. Br-Prompt achieves state-of-the-art on multiple benchmarks. Code is available at: https://github.com/ttlmh/Bridge-Prompt.
-
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers semantic similarity and instance similarity. In SimMatch, the consistency regularization will be applied on both semantic-level and instance-level. The different augmented views of the same instance are encouraged to have the same class prediction and similar similarity relationship respected to other instances. Next, we instantiated a labeled memory buffer to fully leverage the ground truth labels on instance-level and bridge the gaps between the semantic and instance similarities. Finally, we proposed the unfolding and aggregation operation which allows these two similarities be isomorphically transformed with each other. In this way, the semantic and instance pseudo-labels can be mutually propagated to generate more high-quality and reliable matching targets. Extensive experimental results demonstrate that SimMatch improves the performance of semi-supervised learning tasks across different benchmark datasets and different settings. Notably, with 400 epochs of training, SimMatch achieves 67.2%, and 74.4% Top-1 Accuracy with 1% and 10% labeled examples on ImageNet, which significantly outperforms the baseline methods and is better than previous semi-supervised learning frameworks.
-
This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors. Specifically, we construct a distinct generative model and design an objective function that encourages the generative model to produce causal, compact, and faithful explanations. This is achieved by isolating the causal factors in the latent space of graphs by maximizing the information flow measurements. We theoretically analyze the cause-effect relationships in the proposed causal graph, identify node attributes as confounders between graphs and GNN predictions, and circumvent such confounder effect by leveraging the backdoor adjustment formula. Our framework is compatible with any GNNs, and it does not require access to the process by which the target GNN produces its predictions. In addition, it does not rely on the linear-independence assumption of the explained features, nor require prior knowledge on the graph learning tasks. We show a proof-of-concept of OrphicX on canonical classification problems on graph data. In particular, we analyze the explanatory subgraphs obtained from explanations for molecular graphs (i.e., Mutag) and quantitatively evaluate the explanation performance with frequently occurring subgraph patterns. Empirically, we show that OrphicX can effectively identify the causal semantics for generating causal explanations, significantly outperforming its alternatives.
-
Hands are often severely occluded by objects, which makes 3D hand mesh estimation challenging. Previous works often have disregarded information at occluded regions. However, we argue that occluded regions have strong correlations with hands so that they can provide highly beneficial information for complete 3D hand mesh estimation. Thus, in this work, we propose a novel 3D hand mesh estimation network HandOccNet, that can fully exploits the information at occluded regions as a secondary means to enhance image features and make it much richer. To this end, we design two successive Transformer-based modules, called feature injecting transformer (FIT) and self-enhancing transformer (SET). FIT injects hand information into occluded region by considering their correlation. SET refines the output of FIT by using a self-attention mechanism. By injecting the hand information to the occluded region, our HandOccNet reaches the state-of-the-art performance on 3D hand mesh benchmarks that contain challenging hand-object occlusions. The codes are available in: https://github.com/namepllet/HandOccNet.
-
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing time. In this paper, we present EfficientNeRF as an efficient NeRF-based method to represent 3D scene and synthesize novel-view images. Although several ways exist to accelerate the training or testing process, it is still difficult to much reduce time for both phases simultaneously. We analyze the density and weight distribution of the sampled points then propose valid and pivotal sampling at the coarse and fine stage, respectively, to significantly improve sampling efficiency. In addition, we design a novel data structure to cache the whole scene during testing to accelerate the testing speed. Overall, our method can reduce over 88% of training time, reach testing speed of around 200 to 500 FPS, while still achieving competitive accuracy. Experiments prove that our method promotes the practicality of NeRF in the real world and enables many applications.
-
We study societal bias amplification in image captioning. Image captioning models have been shown to perpetuate gender and racial biases, however, metrics to measure, quantify, and evaluate the societal bias in captions are not yet standardized. We provide a comprehensive study on the strengths and limitations of each metric, and propose LIC, a metric to study captioning bias amplification. We argue that, for image captioning, it is not enough to focus on the correct prediction of the protected attribute, and the whole context should be taken into account. We conduct extensive evaluation on traditional and state-of-the-art image captioning models, and surprisingly find that, by only focusing on the protected attribute prediction, bias mitigation models are unexpectedly amplifying bias.
-
Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the learning of interaction between agents and objects. We introduce the task of semantic action-conditional video prediction, which uses semantic action labels to describe those interactions and can be regarded as an inverse problem of action recognition. The challenge of this new task primarily lies in how to effectively inform the model of semantic action information. Inspired by the idea of Mixture of Experts, we embody each abstract label by a structured combination of various visual concept learners and propose a novel video prediction model, Modular Action Concept Network (MAC). Our method is evaluated on two newly designed synthetic datasets, CLEVR-Building-Blocks and Sapien-Kitchen, and one real-world dataset called Tower-Creation. Extensive experiments demonstrate that MAC can correctly condition on given instructions and generate corresponding future frames without need of bounding boxes. We further show that the trained model can make out-of-distribution generalization, be quickly adapted to new object categories and exploit its learnt features for object detection, showing the progression towards higher-level cognitive abilities. More visualizations can be found at http://www.pair.toronto.edu/mac/.
-
Despite the tantalizing success in a broad of vision tasks, transformers have not yet demonstrated on-par ability as ConvNets in high-resolution image generative modeling. In this paper, we seek to explore using pure transformers to build a generative adversarial network for high-resolution image synthesis. To this end, we believe that the local attention is crucial to strike the balance between computational efficiency and modeling capacity. Hence, the proposed generator adopts Swin transformer in a style-based architecture. To achieve larger receptive field, we propose double attention which simultaneously leverages the context of the local and the shifted windows, leading to improved generation quality. Moreover, we show that offering the knowledge of the absolute position that has lost in window-based transformers greatly benefits the generation quality. The proposed StyleSwin is scalable to high resolutions, with both the coarse geometry and fine structures benefit from the strong expressivity of transformers. However, blocking artifacts occur during high-resolution synthesis because performing the local attention in a block-wise manner may break the spatial coherency. To solve this, we empirically investigate various solutions, among which we find that employing a wavelet discriminator to examine the spectral discrepancy effectively suppresses the artifacts. Extensive experiments show the superiority over prior transformer-based GANs, especially on high resolutions, e.g., 1024x1024. The StyleSwin, without complex training strategies, excelling over StyleGAN on CelebA-HQ 1024, and achieves on-par performance on FFHQ-1024, proving the promise of using transformers for high-resolution image generation. The code and pretrained models are available at https://github.com/microsoft/StyleSwin.
-
Vision-and-language Navigation (VLN) task requires an embodied agent to navigate to a remote location following a natural language instruction. Previous methods usually adopt a sequence model (e.g., Transformer and LSTM) as the navigator. In such a paradigm, the sequence model predicts action at each step through a maintained navigation state, which is generally represented as a one-dimensional vector. However, the crucial navigation clues (i.e., object-level environment layout) for embodied navigation task is discarded since the maintained vector is essentially unstructured. In this paper, we propose a novel Structured state-Evolution (SEvol) model to effectively maintain the environment layout clues for VLN. Specifically, we utilise the graph-based feature to represent the navigation state instead of the vector-based state. Accordingly, we devise a Reinforced Layout clues Miner (RLM) to mine and detect the most crucial layout graph for long-term navigation via a customised reinforcement learning strategy. Moreover, the Structured Evolving Module (SEM) is proposed to maintain the structured graph-based state during navigation, where the state is gradually evolved to learn the object-level spatial-temporal relationship. The experiments on the R2R and R4R datasets show that the proposed SEvol model improves VLN models' performance by large margins, e.g., +3% absolute SPL accuracy for NvEM and +8% for EnvDrop on the R2R test set.
-
The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos. Most prior works deal with the open-set visual speech recognition problem by adapting existing automatic speech recognition techniques on top of trivially pooled visual features. Instead, in this paper, we focus on the unique challenges encountered in lip reading and propose tailored solutions. To this end, we make the following contributions: (1) we propose an attention-based pooling mechanism to aggregate visual speech representations; (2) we use sub-word units for lip reading for the first time and show that this allows us to better model the ambiguities of the task; (3) we propose a model for Visual Speech Detection (VSD), trained on top of the lip reading network. Following the above, we obtain state-of-the-art results on the challenging LRS2 and LRS3 benchmarks when training on public datasets, and even surpass models trained on large-scale industrial datasets by using an order of magnitude less data. Our best model achieves 22.6% word error rate on the LRS2 dataset, a performance unprecedented for lip reading models, significantly reducing the performance gap between lip reading and automatic speech recognition. Moreover, on the AVA-ActiveSpeaker benchmark, our VSD model surpasses all visual-only baselines and even outperforms several recent audio-visual methods.
-
The development of online economics arouses the demand of generating images of models on product clothes, to display new clothes and promote sales. However, the expensive proprietary model images challenge the existing image virtual try-on methods in this scenario, as most of them need to be trained on considerable amounts of model images accompanied with paired clothes images. In this paper, we propose a cheap yet scalable weakly-supervised method called Deep Generative Projection (DGP) to address this specific scenario. Lying in the heart of the proposed method is to imitate the process of human predicting the wearing effect, which is an unsupervised imagination based on life experience rather than computation rules learned from supervisions. Here a pretrained StyleGAN is used to capture the practical experience of wearing. Experiments show that projecting the rough alignment of clothing and body onto the StyleGAN space can yield photo-realistic wearing results. Experiments on real scene proprietary model images demonstrate the superiority of DGP over several state-of-the-art supervised methods when generating clothing model images.
-
Multi-view clustering has received increasing attention due to its effectiveness in fusing complementary information without manual annotations. Most previous methods hold the assumption that each instance appears in all views. However, it is not uncommon to see that some views may contain some missing instances, which gives rise to incomplete multi-view clustering (IMVC) in literature. Although many IMVC methods have been recently proposed, they always encounter high complexity and expensive time expenditure from being applied into large-scale tasks. In this paper, we present a flexible highly-efficient incomplete large-scale multi-view clustering approach based on bipartite graph framework to solve these issues. Specifically, we formalize multi-view anchor learning and incomplete bipartite graph into a unified framework, which coordinates with each other to boost cluster performance. By introducing the flexible bipartite graph framework to handle IMVC for the first practice, our proposed method enjoys linear complexity respecting to instance numbers, which is more applicable for large-scale IMVC tasks. Comprehensive experimental results on various benchmark datasets demonstrate the effectiveness and efficiency of our proposed algorithm against other IMVC competitors.
-
A fundamental challenge for machine learning models is generalizing to out-of-distribution (OOD) data, in part due to spurious correlations. To tackle this challenge, we first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG). We relax this non-trivial constrained optimization problem to a tractable form with finite-dimensional parameterization and empirical approximation. Then a theoretical analysis of the extent to which the above transformations deviates from the original problem is provided. Based on the transformation, we propose a primal-dual algorithm for joint representation disentanglement and domain generalization. In contrast to traditional approaches based on domain adversarial training and domain labels, DDG jointly learns semantic and variation encoders for disentanglement, enabling flexible manipulation and augmentation on training data. DDG aims to learn intrinsic representations of semantic concepts that are invariant to nuisance factors and generalizable across domains. Comprehensive experiments on popular benchmarks show that DDG can achieve competitive OOD performance and uncover interpretable salient structures within data.
-
Guided depth super-resolution (GDSR) is an essential topic in multi-modal image processing, which reconstructs high-resolution (HR) depth maps from low-resolution ones collected with suboptimal conditions with the help of HR RGB images of the same scene. To solve the challenges in interpreting the working mechanism, extracting cross-modal features and RGB texture over-transferred, we propose a novel Discrete Cosine Transform Network (DCTNet) to alleviate the problems from three aspects. First, the Discrete Cosine Transform (DCT) module reconstructs the multi-channel HR depth features by using DCT to solve the channel-wise optimization problem derived from the image domain. Second, we introduce a semi-coupled feature extraction module that uses shared convolutional kernels to extract common information and private kernels to extract modality-specific information. Third, we employ an edge attention mechanism to highlight the contours informative for guided upsampling. Extensive quantitative and qualitative evaluations demonstrate the effectiveness of our DCTNet, which outperforms previous state-of-the-art methods with a relatively small number of parameters. Codes are available at https://github.com/Zhaozixiang1228/GDSR-DCTNet.
-
Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance. In this paper, we tackle the new problem of joint semantic, affordance and attribute parsing. However, successfully resolving it requires a model to capture long-range dependency, learn from weakly aligned data and properly balance sub-tasks during training. To this end, we propose an attention-based architecture named Cerberus and a tailored training framework. Our method effectively addresses aforementioned challenges and achieves state-of-the-art performance on all three tasks. Moreover, an in-depth analysis shows concept affinity consistent with human cognition, which inspires us to explore the possibility of extremely low-shot learning. Surprisingly, Cerberus achieves strong results using only 0.1%-1% annotation. Visualizations further confirm that this success is credited to common attention maps across tasks. Code and models can be accessed at https://github.com/OPEN-AIR-SUN/Cerberus.
-
Standard semi-supervised learning (SSL) using class-balanced datasets has shown great progress to leverage unlabeled data effectively. However, the more realistic setting of class-imbalanced data - called imbalanced SSL - is largely underexplored and standard SSL tends to underperform. In this paper, we propose a novel co-learning framework (CoSSL), which decouples representation and classifier learning while coupling them closely. To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE) for classifier learning. Furthermore, the current evaluation protocol for imbalanced SSL focuses only on balanced test sets, which has limited practicality in real-world scenarios. Therefore, we further conduct a comprehensive evaluation under various shifted test distributions. In experiments, we show that our approach outperforms other methods over a large range of shifted distributions, achieving state-of-the-art performance on benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our code will be made publicly available.
-
This paper studies the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. However, by relying on appearance alone, these methods fail to separate objects from the background in cluttered scenes. This is a fundamental limitation since the definition of an object is inherently ambiguous and context-dependent. To resolve this ambiguity, we choose to focus on dynamic objects -- entities that can move independently in the world. We then scale the recent auto-encoder based frameworks for unsupervised object discovery from toy synthetic images to complex real-world scenes. To this end, we simplify their architecture, and augment the resulting model with a weak learning signal from general motion segmentation algorithms. Our experiments demonstrate that, despite only capturing a small subset of the objects that move, this signal is enough to generalize to segment both moving and static instances of dynamic objects. We show that our model scales to a newly collected, photo-realistic synthetic dataset with street driving scenarios. Additionally, we leverage ground truth segmentation and flow annotations in this dataset for thorough ablation and evaluation. Finally, our experiments on the real-world KITTI benchmark demonstrate that the proposed approach outperforms both heuristic- and learning-based methods by capitalizing on motion cues.
-
Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be irrelevant when it is not significantly related to objects/scenes. We propose an end-to-end trainable network that mines implicit contextual knowledge behind scene text image and enhance the semantics and correlation to fine-tune the image representation. Unlike the existing methods, our model integrates three modalities: visual feature extraction, text semantics extraction, and correlating background knowledge to fine-grained image classification. Specifically, we employ KnowBert to retrieve relevant knowledge for semantic representation and combine it with image features for fine-grained classification. Experiments on two benchmark datasets, Con-Text, and Drink Bottle, show that our method outperforms the state-of-the-art by 3.72% mAP and 5.39% mAP, respectively. To further validate the effectiveness of the proposed method, we create a new dataset on crowd activity recognition for the evaluation. The source code, new dataset, and pre-trained models of this work will be publicly available.
-
Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from this trend as they require spatially-diverse representations. However, learning dense representations is challenging, as in the unsupervised context it is not clear how to guide the model to learn representations that correspond to various potential object categories. In this paper, we argue that self-supervised learning of object parts is a solution to this issue. Object parts are generalizable: they are a priori independent of an object definition, but can be grouped to form objects a posteriori. To this end, we leverage the recently proposed Vision Transformer's capability of attending to objects and combine it with a spatially dense clustering task for fine-tuning the spatial tokens. Our method surpasses the state-of-the-art on three semantic segmentation benchmarks by 17%-3%, showing that our representations are versatile under various object definitions. Finally, we extend this to fully unsupervised segmentation - which refrains completely from using label information even at test-time - and demonstrate that a simple method for automatically merging discovered object parts based on community detection yields substantial gains.
-
Tracking objects in 3D space and predicting their 6DoF pose is an essential task in computer vision. State-of-the-art approaches often rely on object texture to tackle this problem. However, while they achieve impressive results, many objects do not contain sufficient texture, violating the main underlying assumption. In the following, we thus propose ICG, a novel probabilistic tracker that fuses region and depth information and only requires the object geometry. Our method deploys correspondence lines and points to iteratively refine the pose. We also implement robust occlusion handling to improve performance in real-world settings. Experiments on the YCB-Video, OPT, and Choi datasets demonstrate that, even for textured objects, our approach outperforms the current state of the art with respect to accuracy and robustness. At the same time, ICG shows fast convergence and outstanding efficiency, requiring only 1.3 ms per frame on a single CPU core. Finally, we analyze the influence of individual components and discuss our performance compared to deep learning-based methods. The source code of our tracker is publicly available.
-
We present a novel structured light technique that uses Single Photon Avalanche Diode (SPAD) arrays to enable 3D scanning at high-frame rates and low-light levels. This technique, called "Single-Photon Structured Light", works by sensing binary images that indicates the presence or absence of photon arrivals during each exposure; the SPAD array is used in conjunction with a high-speed binary projector, with both devices operated at speeds as high as 20 kHz. The binary images that we acquire are heavily influenced by photon noise and are easily corrupted by ambient sources of light. To address this, we develop novel temporal sequences using error correction codes that are designed to be robust to short-range effects like projector and camera defocus as well as resolution mismatch between the two devices. Our lab prototype is capable of 3D imaging in challenging scenarios involving objects with extremely low albedo or undergoing fast motion, as well as scenes under strong ambient illumination.
-
Image deblurring is an ill-posed problem with multiple plausible solutions for a given input image. However, most existing methods produce a deterministic estimate of the clean image and are trained to minimize pixel-level distortion. These metrics are known to be poorly correlated with human perception, and often lead to unrealistic reconstructions. We present an alternative framework for blind deblurring based on conditional diffusion models. Unlike existing techniques, we train a stochastic sampler that refines the output of a deterministic predictor and is capable of producing a diverse set of plausible reconstructions for a given input. This leads to a significant improvement in perceptual quality over existing state-of-the-art methods across multiple standard benchmarks. Our predict-and-refine approach also enables much more efficient sampling compared to typical diffusion models. Combined with a carefully tuned network architecture and inference procedure, our method is competitive in terms of distortion metrics such as PSNR. These results show clear benefits of our diffusion-based method for deblurring and challenge the widely used strategy of producing a single, deterministic reconstruction.
-
Observing that the 3D captioning task and the 3D grounding task contain both shared and complementary information in nature, in this work, we propose a unified framework to jointly solve these two distinct but closely related tasks in a synergistic fashion, which consists of both shared task-agnostic modules and lightweight task-specific modules. On one hand, the shared task-agnostic modules aim to learn precise locations of objects, fine-grained attribute features to characterize different objects, and complex relations between objects, which benefit both captioning and visual grounding. On the other hand, by casting each of the two tasks as the proxy task of another one, the lightweight task-specific modules solve the captioning task and the grounding task respectively. Extensive experiments and ablation study on three 3D vision and language datasets demonstrate that our joint training framework achieves significant performance gains for each individual task and finally improves the state-of-the-art performance for both captioning and grounding tasks.
-
The dominant CNN-based methods for cross-view image geo-localization rely on polar transform and fail to model global correlation. We propose a pure transformer-based approach (TransGeo) to address these limitations from a different perspective. TransGeo takes full advantage of the strengths of transformer related to global information modeling and explicit position information encoding. We further leverage the flexibility of transformer input and propose an attention-guided non-uniform cropping method, so that uninformative image patches are removed with negligible drop on performance to reduce computation cost. The saved computation can be reallocated to increase resolution only for informative patches, resulting in performance improvement with no additional computation cost. This "attend and zoom-in" strategy is highly similar to human behavior when observing images. Remarkably, TransGeo achieves state-of-the-art results on both urban and rural datasets, with significantly less computation cost than CNN-based methods. It does not rely on polar transform and infers faster than CNN-based methods. Code is available at https://github.com/Jeff-Zilence/TransGeo2022.
-
In the paradigm of object detection, the decision head is an important part, which affects detection performance significantly. Yet how to design a high-performance decision head remains to be an open issue. In this paper, we propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection. First, we disentangle the decision choices and prediction values by plugging soft decision trees into neural networks. To facilitate the effective learning, we propose the randomized decision routing with node selective and associative losses, which can boost the feature representative learning and network decision simultaneously. Second, we develop the decision head for object detection with narrow branches to generate the routing probabilities and masks, for the purpose of obtaining divergent decisions from different nodes. We name this approach as the randomized decision routing for object detection, abbreviated as R(Det)^2. Experiments on MS-COCO dataset demonstrate that R(Det)^2 is effective to improve the detection performance. Equipped with existing detectors, it achieves 1.4~ 3.6% AP improvement. Code will be released soon.
-
Low-light image enhancement, a pervasive but challenging problem, plays a central role in enhancing the visibility of an image captured in a poor illumination environment. Due to the fact that not all photons can pass the Bayer-Filter on the sensor of the color camera, in this work, we first present a De-Bayer-Filter simulator based on deep neural networks to generate a monochrome raw image from the colored raw image. Next, a fully convolutional network is proposed to achieve the low-light image enhancement by fusing colored raw data with synthesized monochrome data. Channel-wise attention is also introduced to the fusion process to establish a complementary interaction between features from colored and monochrome raw images. To train the convolutional networks, we propose a dataset with monochrome and color raw pairs named Mono-Colored Raw paired dataset (MCR) collected by using a monochrome camera without Bayer-Filter and a color camera with Bayer-Filter. The proposed pipeline take advantages of the fusion of the virtual monochrome and the color raw images and our extensive experiments indicate that significant improvement can be achieved by leveraging raw sensor data and data-driven learning.
-
We propose a learned method for stereo image compression that leverages the similarity of the left and right images in a stereo pair due to overlapping fields of view. The left image is compressed by a learned compression method based on an autoencoder with a hyperprior entropy model. The right image uses this information from the previously encoded left image in both the encoding and decoding stages. In particular, for the right image, we encode only the residual of its latent representation to the optimally shifted latent of the left image. On top of that, we also employ a stereo attention module to connect left and right images during decoding. The performance of the proposed method is evaluated on two benchmark stereo image datasets (Cityscapes and InStereo2K) and outperforms previous stereo image compression methods while being significantly smaller in model size.
-
We consider the object recognition problem in autonomous driving using automotive radar sensors. Comparing to Lidar sensors, radar is cost-effective and robust in all-weather conditions for perception in autonomous driving. However, radar signals suffer from low angular resolution and precision in recognizing surrounding objects. To enhance the capacity of automotive radar, in this work, we exploit the temporal information from successive ego-centric bird-eye-view radar image frames for radar object recognition. We leverage the consistency of an object's existence and attributes (size, orientation, etc.), and propose a temporal relational layer to explicitly model the relations between objects within successive radar images. In both object detection and multiple object tracking, we show the superiority of our method compared to several baseline approaches.
-
We address the problem of estimating the poses of multiple instances of the source point cloud within a target point cloud. Existing solutions require sampling a lot of hypotheses to detect possible instances and reject the outliers, whose robustness and efficiency degrade notably when the number of instances and outliers increase. We propose to directly group the set of noisy correspondences into different clusters based on a distance invariance matrix. The instances and outliers are automatically identified through clustering. Our method is robust and fast. We evaluated our method on both synthetic and real-world datasets. The results show that our approach can correctly register up to 20 instances with an F1 score of 90.46% in the presence of 70% outliers, which performs significantly better and at least 10x faster than existing methods.
-
Point cloud segmentation is fundamental in understanding 3D environments. However, current 3D point cloud segmentation methods usually perform poorly on scene boundaries, which degenerates the overall segmentation performance. In this paper, we focus on the segmentation of scene boundaries. Accordingly, we first explore metrics to evaluate the segmentation performance on scene boundaries. To address the unsatisfactory performance on boundaries, we then propose a novel contrastive boundary learning (CBL) framework for point cloud segmentation. Specifically, the proposed CBL enhances feature discrimination between points across boundaries by contrasting their representations with the assistance of scene contexts at multiple scales. By applying CBL on three different baseline methods, we experimentally show that CBL consistently improves different baselines and assists them to achieve compelling performance on boundaries, as well as the overall performance, e.g. in mIoU. The experimental results demonstrate the effectiveness of our method and the importance of boundaries for 3D point cloud segmentation. Code and model will be made publicly available at https://github.com/LiyaoTang/contrastBoundary.
-
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution
Single image super-resolution (SISR) with generative adversarial networks (GAN) has recently attracted increasing attention due to its potentials to generate rich details. However, the training of GAN is unstable, and it often introduces many perceptually unpleasant artifacts along with the generated details. In this paper, we demonstrate that it is possible to train a GAN-based SISR model which can stably generate perceptually realistic details while inhibiting visual artifacts. Based on the observation that the local statistics (e.g., residual variance) of artifact areas are often different from the areas of perceptually friendly details, we develop a framework to discriminate between GAN-generated artifacts and realistic details, and consequently generate an artifact map to regularize and stabilize the model training process. Our proposed locally discriminative learning (LDL) method is simple yet effective, which can be easily plugged in off-the-shelf SISR methods and boost their performance. Experiments demonstrate that LDL outperforms the state-of-the-art GAN based SISR methods, achieving not only higher reconstruction accuracy but also superior perceptual quality on both synthetic and real-world datasets. Codes and models are available at https://github.com/csjliang/LDL.
-
The classic active contour model raises a great promising solution to polygon-based object extraction with the progress of deep learning recently. Inspired by the physical vibration theory, we propose a contour vibration network (CVNet) for automatic building boundary delineation. Different from the previous contour models, the CVNet originally roots in the force and motion principle of contour string. Through the infinitesimal analysis and Newton's second law, we derive the spatial-temporal contour vibration model of object shapes, which is mathematically reduced to second-order differential equation. To concretize the dynamic model, we transform the vibration model into the space of image features, and reparameterize the equation coefficients as the learnable state from feature domain. The contour changes are finally evolved in a progressive mode through the computation of contour vibration equation. Both the polygon contour evolution and the model optimization are modulated to form a close-looping end-to-end network. Comprehensive experiments on three datasets demonstrate the effectiveness and superiority of our CVNet over other baselines and state-of-the-art methods for the polygon-based building extraction. The code is available at https://github.com/xzq-njust/CVNet.
-
For image segmentation, the current standard is to perform pixel-level optimization and inference in Euclidean output embedding spaces through linear hyperplanes. In this work, we show that hyperbolic manifolds provide a valuable alternative for image segmentation and propose a tractable formulation of hierarchical pixel-level classification in hyperbolic space. Hyperbolic Image Segmentation opens up new possibilities and practical benefits for segmentation, such as uncertainty estimation and boundary information for free, zero-label generalization, and increased performance in low-dimensional output embeddings.
-
In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the idea of backward compatible training (BCT) was proposed. To avoid the cost of backfilling, BCT modifies training of the new model to make its representations compatible with those of the old model. However, BCT can significantly hinder the performance of the new model. In this work, we propose a new learning paradigm for representation learning: forward compatible training (FCT). In FCT, when the old model is trained, we also prepare for a future unknown version of the model. We propose learning side-information, an auxiliary feature for each sample which facilitates future updates of the model. To develop a powerful and flexible framework for model compatibility, we combine side-information with a forward transformation from old to new embeddings. Training of the new model is not modified, hence, its accuracy is not degraded. We demonstrate significant retrieval accuracy improvement compared to BCT for various datasets: ImageNet-1k (+18.1%), Places-365 (+5.4%), and VGG-Face2 (+8.3%). FCT obtains model compatibility when the new and old models are trained across different datasets, losses, and architectures.
-
Multi-modal learning from video data has seen increased attention recently as it allows training of semantically meaningful embeddings without human annotation, enabling tasks like zero-shot retrieval and action localization. In this work, we present a multi-modal, modality agnostic fusion transformer that learns to exchange information between multiple modalities, such as video, audio, and text, and integrate them into a fused representation in a joined multi-modal embedding space. We propose to train the system with a combinatorial loss on everything at once - any combination of input modalities, such as single modalities as well as pairs of modalities, explicitly leaving out any add-ons such as position or modality encoding. At test time, the resulting model can process and fuse any number of input modalities. Moreover, the implicit properties of the transformer allow to process inputs of different lengths. To evaluate the proposed approach, we train the model on the large scale HowTo100M dataset and evaluate the resulting embedding space on four challenging benchmark datasets obtaining state-of-the-art results in zero-shot video retrieval and zero-shot video action localization. Our code for this work is also available.
-
We present techniques for scaling Swin Transformer [??] up to 3 billion parameters and making it capable of training with images of up to 1,536x1,536 resolution. By scaling up capacity and resolution, Swin Transformer sets new records on four representative vision benchmarks: 84.0% top-1 accuracy on ImageNet-V2 image classification, 63.1 / 54.4 box / mask mAP on COCO object detection, 59.9 mIoU on ADE20K semantic segmentation, and 86.8% top-1 accuracy on Kinetics-400 video action classification. We tackle issues of training instability, and study how to effectively transfer models pre-trained at low resolutions to higher resolution ones. To this aim, several novel technologies are proposed: 1) a residual post normalization technique and a scaled cosine attention approach to improve the stability of large vision models; 2) a log-spaced continuous position bias technique to effectively transfer models pre-trained at low-resolution images and windows to their higher-resolution counterparts. In addition, we share our crucial implementation details that lead to significant savings of GPU memory consumption and thus make it feasible to train large vision models with regular GPUs. Using these techniques and self-supervised pre-training, we successfully train a strong 3 billion Swin Transformer model and effectively transfer it to various vision tasks involving high-resolution images or windows, achieving the state-of-the-art accuracy on a variety of benchmarks. Code is available at https://github.com/microsoft/Swin-Transformer.
-
This paper introduces a novel framework called DT-Net for 3D mesh reconstruction and generation via Disentangled Topology. Beyond previous works, we learn a topology-aware neural template specific to each input then deform the template to reconstruct a detailed mesh while preserving the learned topology. One key insight is to decouple the complex mesh reconstruction into two sub-tasks: topology formulation and shape deformation. Thanks to the decoupling, DT-Net implicitly learns a disentangled representation for the topology and shape in the latent space. Hence, it can enable novel disentangled controls for supporting various shape generation applications, eg, remix the topologies of 3D objects, that are not achievable by previous reconstruction works. Extensive experimental results demonstrate that our method is able to produce high-quality meshes, particularly with diverse topologies, as compared with the state-of-the-art methods.
-
Backdoor attack is a type of serious security threat to deep learning models.An adversary can provide users with a model trained on poisoned data to manipulate prediction behavior in test stage using a backdoor. The backdoored models behave normally on clean images, yet can be activated and output incorrect prediction if the input is stamped with a specific trigger pattern.Most existing backdoor attacks focus on manually defining imperceptible triggers in input space without considering the abnormality of triggers' latent representations in the poisoned model.These attacks are susceptible to backdoor detection algorithms and even visual inspection.In this paper, We propose a novel and stealthy backdoor attack - DEFEAT. It poisons the clean data using adaptive imperceptible perturbation and restricts latent representation during training process to strengthen our attack's stealthiness and resistance to defense algorithms.We conduct extensive experiments on multiple image classifiers using real-world datasets to demonstrate that our attack can 1) hold against the state-of-the-art defenses, 2) deceive the victim model with high attack success without jeopardizing model utility, and 3) provide practical stealthiness on image data.
-
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network learning in both forward and backward passes. While several works have proposed different regression-friendly rotation representations, very few works have been devoted to improving the gradient backpropagating in the backward pass. In this paper, we propose a manifold-aware gradient that directly backpropagates into deep network weights. Leveraging Riemannian optimization to construct a novel projective gradient, our proposed regularized projective manifold gradient (RPMG) method helps networks achieve new state-of-the-art performance in a variety of rotation estimation tasks. Our proposed gradient layer can also be applied to other smooth manifolds such as the unit sphere. Our project page is at https://jychen18.github.io/RPMG.
-
It has been widely known that CAM (Class Activation Map) usually only activates discriminative object regions and falsely includes lots of object-related backgrounds. As only a fixed set of image-level object labels are available to the WSSS (weakly supervised semantic segmentation) model, it could be very difficult to suppress those diverse background regions consisting of open set objects. In this paper, we propose a novel Cross Language Image Matching (CLIMS) framework, based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress closely-related open background regions. In particular, we design object, background region and text label matching losses to guide the model to excite more reasonable object regions for CAM of each category. In addition, we design a co-occurring background suppression loss to prevent the model from activating closely-related background regions, with a predefined set of class-related background text descriptions. These designs enable the proposed CLIMS to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC2012 dataset show that our CLIMS significantly outperforms the previous state-of-the-art methods.
-
The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devising advanced action detectors, they still suffer from these co-occurring ingredients which often dominate the actual action content in videos. In this paper, we explore two orthogonal but complementary aspects of a video snippet, i.e., the action features and the co-occurrence features. Especially, we develop a novel auxiliary task by decoupling these two types of features within a video snippet and recombining them to generate a new feature representation with more salient action information for accurate action localization. We term our method RefactorNet, which first explicitly factorizes the action content and regularizes its co-occurrence features, and then synthesizes a new action-dominated video representation. Extensive experimental results and ablation studies on THUMOS14 and ActivityNet v1.3 demonstrate that our new representation, combined with a simple action detector, can significantly improve the action localization performance.
-
We present an approach for recommending a music track for a given video, and vice versa, based on both their temporal alignment and their correspondence at an artistic level. We propose a self-supervised approach that learns this correspondence directly from data, without any need of human annotations. In order to capture the high-level concepts that are required to solve the task, we propose modeling the long-term temporal context of both the video and the music signals, using Transformer networks for each modality. Experiments show that this approach strongly outperforms alternatives that do not exploit the temporal context. The combination of our contributions improve retrieval accuracy up to 10x over prior state of the art. This strong improvement allows us to introduce a wide range of analyses and applications. For instance, we can condition music retrieval based on visually-defined attributes.
-
We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language models on large public datasets has enabled strong differential privacy (DP) guarantees with minor loss of accuracy, a similar practice yields punishing trade-offs in vision tasks. A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset. AdaMix incorporates few-shot training, or cross-modal zero-shot learning, on public data prior to private fine-tuning, to improve the trade-off. AdaMix reduces the error increase from the non-private upper bound from the 167-311% of the baseline, on average across 6 datasets, to 68-92% depending on the desired privacy level selected by the user. AdaMix tackles the trade-off arising in visual classification, whereby the most privacy sensitive data, corresponding to isolated points in representation space, are also critical for high classification accuracy. In addition, AdaMix comes with strong theoretical privacy guarantees and convergence analysis.
-
Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to assign more importance to misclassified (hard) examples. In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality. We argue that the strategy to emphasize misclassified samples should be adjusted according to their image quality. Specifically, the relative importance of easy or hard samples should be based on the sample's image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method achieves this in the form of an adaptive margin function by approximating the image quality with feature norms. Extensive experiments show that our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets (IJB-B, IJB-C, IJB-S and TinyFace). Code and models are released in Supp.
-
Estimating keypoint scale and orientation is crucial to extracting invariant features under significant geometric changes. Recently, the estimators based on self-supervised learning have been designed to adapt to complex imaging conditions. Such learning-based estimators generally predict a single scalar for the keypoint scale or orientation, called hard estimators. However, hard estimators are difficult to handle the local patches containing structures of different objects or multiple edges. In this paper, a Soft Self-Supervised Estimator (S3Esti) is proposed to overcome this problem by learning to predict multiple scales and orientations. S3Esti involves three core factors. First, the estimator is constructed to predict the discrete distributions of scales and orientations. The elements with high confidence will be kept as the final scales and orientations. Second, a probabilistic covariant loss is proposed to improve the consistency of the scale and orientation distributions under different transformations. Third, an optimization algorithm is designed to minimize the loss function, whose convergence is proved in theory. When combined with different keypoint extraction models, S3Esti generally improves over 50% accuracy in image matching tasks under significant viewpoint changes. In the 3D reconstruction task, S3Esti decreases more than 10% reprojection error and improves the number of registered images.
-
We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results from the instability of bipartite graph matching which causes inconsistent optimization goals in early training stages. To address this issue, except for the Hungarian loss, our method additionally feeds ground-truth bounding boxes with noises into Transformer decoder and trains the model to reconstruct the original boxes, which effectively reduces the bipartite graph matching difficulty and leads to a faster convergence. Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement. As a result, our DN-DETR results in a remarkable improvement (+1.9AP) under the same setting and achieves the best result (AP 43.4 and 48.6 with 12 and 50 epochs of training respectively) among DETR-like methods with ResNet-50 backbone. Our code will be released after the blind review.
-
Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such structures with image representations can greatly benefit the semantic understanding on various downstream tasks. Existing contrastive representation learning methods lack such an important model capability. In addition, the negative pairs used in these methods are not guaranteed to be semantically distinct, which could further hamper the structural correctness of learned image representations. To tackle these limitations, we propose a novel contrastive learning framework called Hierarchical Contrastive Selective Coding (HCSC). In this framework, a set of hierarchical prototypes are constructed and also dynamically updated to represent the hierarchical semantic structures underlying the data in the latent space. To make image representations better fit such semantic structures, we employ and further improve conventional instance-wise and prototypical contrastive learning via an elaborate pair selection scheme. This scheme seeks to select more diverse positive pairs with similar semantics and more precise negative pairs with truly distinct semantics. On extensive downstream tasks, we verify the superior performance of HCSC over state-of-the-art contrastive methods, and the effectiveness of major model components is proved by plentiful analytical studies. We are continually building a comprehensive model zoo (see supplementary material). Our source code and model weights are available at https://github.com/gyfastas/HCSC.
-
Recognizing transformation types applied to a video clip (RecogTrans) is a long-established paradigm for self-supervised video representation learning, which achieves much inferior performance compared to instance discrimination approaches (InstDisc) in recent works. However, based on a thorough comparison of representative RecogTrans and InstDisc methods, we observe the great potential of RecogTrans on both semantic-related and temporal-related downstream tasks. Based on hard-label classification, existing RecogTrans approaches suffer from noisy supervision signals in pre-training. To mitigate this problem, we developed TransRank, a unified framework for recognizing Transformations in a Ranking formulation. TransRank provides accurate supervision signals by recognizing transformations relatively, consistently outperforming the classification-based formulation. Meanwhile, the unified framework can be instantiated with an arbitrary set of temporal or spatial transformations, demonstrating good generality. With a ranking-based formulation and several empirical practices, we achieve competitive performance on video retrieval and action recognition.Under the same setting, TransRank surpasses the previous state-of-the-art method by 6.4% on UCF101 and 8.3% on HMDB51 for action recognition (Top1 Acc); improves video retrieval on UCF101 by 20.4% (R@1). The promising results validate that RecogTrans is still a worth exploring paradigm for video self-supervised learning. Codes will be released at https://github.com/kennymckormick/TransRank.
-
We consider the problem of reconstructing the depth of dynamic objects from videos. Recent progress in dynamic video depth prediction has focused on improving the output of monocular depth estimators by means of multi-view constraints while imposing little to no restrictions on the deformation of the dynamic parts of the scene. However, the theory of Non-Rigid Structure from Motion prescribes to constrain the deformations for 3D reconstruction. We thus propose a new model that departs significantly from this prior work. The idea is to fit a dynamic point cloud to the video data using Sinkhorn's algorithm to associate the 3D points to 2D pixels and use a differentiable point renderer to ensure the compatibility of the 3D deformations with the measured optical flow. In this manner, our algorithm, called Keypoint Transporter, models the overall deformation of the object within the entire video, so it can constrain the reconstruction correspondingly. Compared to weaker deformation models, this significantly reduces the reconstruction ambiguity and, for dynamic objects, allows Keypoint Transporter to obtain reconstructions of the quality superior or at least comparable to prior approaches while being much faster and reliant on a pre-trained monocular depth estimator network. To assess the method, we evaluate on new datasets of synthetic videos depicting dynamic humans and animals with ground-truth depth. We also show qualitative results on crowd-sourced real-world videos of pets.
-
Video Question Answering (VideoQA) is the task of answering questions about a video. At its core is understanding the alignments between visual scenes in video and linguistic semantics in question to yield the answer. In leading VideoQA models, the typical learning objective, empirical risk minimization (ERM), latches on superficial correlations between video-question pairs and answers as the alignments. However, ERM can be problematic, because it tends to over-exploit the spurious correlations between question-irrelevant scenes and answers, instead of inspecting the causal effect of question-critical scenes. As a result, the VideoQA models suffer from unreliable reasoning. In this work, we first take a causal look at VideoQA and argue that invariant grounding is the key to ruling out the spurious correlations. Towards this end, we propose a new learning framework, Invariant Grounding for VideoQA (IGV), to ground the question-critical scene, whose causal relations with answers are invariant across different interventions on the complement. With IGV, the VideoQA models are forced to shield the answering process from the negative influence of spurious correlations, which significantly improves the reasoning ability. Experiments on three benchmark datasets validate the superiority of IGV in terms of accuracy, visual explainability, and generalization ability over the leading baselines.
-
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution of diverse prompts to handle the varying visual representations. In this way, we provide high-quality task-related content for facilitating recognition. This prompt distribution learning is realized by an efficient approach that learns the output embeddings of prompts instead of the input embeddings. Thus, we can employ a Gaussian distribution to model them effectively and derive a surrogate loss for efficient training. Extensive experiments on 12 datasets demonstrate that our method consistently and significantly outperforms existing methods. For example, with 1 sample per category, it relatively improves the average result by 9.1% compared to human-crafted prompts.
-
This paper proposes a deep recurrent Rotation Averaging Graph Optimizer (RAGO) for Multiple Rotation Averaging (MRA). Conventional optimization-based methods usually fail to produce accurate results due to corrupted and noisy relative measurements. Recent learning-based approaches regard MRA as a regression problem, while these methods are sensitive to initialization due to the gauge freedom problem. To handle these problems, we propose a learnable iterative graph optimizer minimizing a gauge-invariant cost function with an edge rectification strategy to mitigate the effect of inaccurate measurements. Our graph optimizer iteratively refines the global camera rotations by minimizing each node's single rotation objective function. Besides, our approach iteratively rectifies relative rotations to make them more consistent with the current camera orientations and observed relative rotations. Furthermore, we employ a gated recurrent unit to improve the result by tracing the temporal information of the cost graph. Our framework is a real-time learning-to-optimize rotation averaging graph optimizer with a tiny size deployed for real-world applications. RAGO outperforms previous traditional and deep methods on real-world and synthetic datasets. The code is available at github.com/sfu-gruvi-3dv/RAGO
-
Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search
Neural Architecture Search (NAS) aims to find efficient models for multiple tasks. Beyond seeking solutions for a single task, there are surging interests in transferring network design knowledge across multiple tasks. In this line of research, effectively modeling task correlations is vital yet highly neglected. Therefore, we propose Arch-Graph, a transferable NAS method that predicts task-specific optimal architectures with respect to given task embeddings. It leverages correlations across multiple tasks by using their embeddings as a part of the predictor's input for fast adaptation. We also formulate NAS as an architecture relation graph prediction problem, with the relational graph constructed by treating candidate architectures as nodes and their pairwise relations as edges. To enforce some basic properties such as acyclicity in the relational graph, we add additional constraints to the optimization process, converting NAS into the problem of finding a Maximal Weighted Acyclic Subgraph (MWAS). Our algorithm then strives to eliminate cycles and only establish edges in the graph if the rank results can be trusted. Through MWAS, Arch-Graph can effectively rank candidate models for each task with only a small budget to finetune the predictor. With extensive experiments on TransNAS-Bench-101, we show Arch-Graph's transferability and high sample efficiency across numerous tasks, beating many NAS methods designed for both single-task and multi-task search. It is able to find top 0.16% and 0.29% architectures on average on two search spaces under the budget of only 50 models.
-
Metrics for evaluating generative models aim to measure the discrepancy between real and generated images. The oftenused Frechet Inception Distance (FID) metric, for example, extracts "high-level" features using a deep network from the two sets. However, we find that the differences in "low-level" preprocessing, specifically image resizing and compression, can induce large variations and have unforeseen consequences. For instance, when resizing an image, e.g., with a bilinear or bicubic kernel, signal processing principles mandate adjusting prefilter width depending on the downsampling factor, to antialias to the appropriate bandwidth. However, commonly used implementations use a fixed-width prefilter, resulting in aliasing artifacts. Such aliasing leads to corruptions in the feature extraction downstream. Next, lossy compression, such as JPEG, is commonly used to reduce the file size of an image. Although designed to minimally degrade the perceptual quality of an image, the operation also produces variations downstream. Furthermore, we show that if compression is used on real training images, FID can actually improve if the generated images are also subsequently compressed. This paper shows that choices in low-level image processing have been an under-appreciated aspect of generative modeling. We identify and characterize variations in generative modeling development pipelines, provide recommendations based on signal processing principles, and release a reference implementation to facilitate future comparisons.
-
We present Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes. The key characteristics are the following techniques that exploit 3D positional knowledge for point cloud matching: 1) An architecture that disentangles point cloud representation into feature space and 3D position space. 2) A position encoding method that explicitly reveals 3D relative distance information through the dot product of vectors. 3) A repositioning technique that modifies the crosspoint-cloud relative positions. Ablation studies demonstrate the effectiveness of the above techniques. In rigid cases, Lepard combined with RANSAC and ICP demonstrates state-of-the-art registration recall of 93.9% / 71.3% on the 3DMatch / 3DLoMatch. In deformable cases, Lepard achieves +27.1% / +34.8% higher non-rigid feature matching recall than the prior art on our newly constructed 4DMatch / 4DLoMatch benchmark.
-
We present Virtual Elastic Objects (VEOs): virtual objects that not only look like their real-world counterparts but also behave like them, even when subject to novel interactions. Achieving this presents multiple challenges: not only do objects have to be captured including the physical forces acting on them, then faithfully reconstructed and rendered, but also plausible material parameters found and simulated. To create VEOs, we built a multi-view capture system that captures objects under the influence of a compressed air stream. Building on recent advances in model-free, dynamic Neural Radiance Fields, we reconstruct the objects and corresponding deformation fields. We propose to use a differentiable, particle-based simulator to use these deformation fields to find representative material parameters, which enable us to run new simulations. To render simulated objects, we devise a method for integrating the simulation results with Neural Radiance Fields. The resulting method is applicable to a wide range of scenarios: it can handle objects composed of inhomogeneous material, with very different shapes, and it can simulate interactions with other virtual objects. We present our results using a newly collected dataset of 12 objects under a variety of force fields, which will be made available upon publication.
-
Despite the popularity of Model Compression and Multitask Learning, how to effectively compress a multitask model has been less thoroughly analyzed due to the challenging entanglement of tasks in the parameter space. In this paper, we propose DiSparse, a simple, effective, and first-of-its-kind multitask pruning and sparse training scheme. We consider each task independently by disentangling the importance measurement and take the unanimous decisions among all tasks when performing parameter pruning and selection. Our experimental results demonstrate superior performance on various configurations and settings compared to popular sparse training and pruning methods. Besides the effectiveness in compression, DiSparse also provides a powerful tool to the multitask learning community. Surprisingly, we even observed better performance than some dedicated multitask learning methods in several cases despite the high model sparsity enforced by DiSparse. We analyzed the pruning masks generated with DiSparse and observed strikingly similar sparse network architecture identified by each task even before the training starts. We also observe the existence of a "watershed" layer where the task relatedness sharply drops, implying no benefits in continued parameters sharing. Our code and models will be available at: https://github.com/SHI-Labs/DiSparse-Multitask-Model-Compression.
-
Few-shot learning (FSL) is an important and topical problem in computer vision that has motivated extensive research into numerous methods spanning from sophisticated meta-learning methods to simple transfer learning baselines. We seek to push the limits of a simple-but-effective pipeline for real-world few-shot image classification in practice. To this end, we explore few-shot learning from the perspective of neural architecture, as well as a three stage pipeline of pre-training on external data, meta-training with labelled few-shot tasks, and task-specific fine-tuning on unseen tasks. We investigate questions such as: (1) How pre-training on external data benefits FSL? (2) How state of the art transformer architectures can be exploited? and (3) How to best exploit fine-tuning? Ultimately, we show that a simple transformer-based pipeline yields surprisingly good performance on standard benchmarks such as Mini-ImageNet, CIFAR-FS, CDFSL and Meta-Dataset. Our code is available at https://hushell.github.io/pmf.
-
Tracking and detecting any object, including ones never-seen-before during model training, is a crucial but elusive capability of autonomous systems. An autonomous agent that is blind to never-seen-before objects poses a safety hazard when operating in the real world - and yet this is how almost all current systems work. One of the main obstacles towards advancing tracking any object is that this task is notoriously difficult to evaluate. A benchmark that would allow us to perform an apple-to-apple comparison of existing efforts is a crucial first step towards advancing this important research field. This paper addresses this evaluation deficit and lays out the landscape and evaluation methodology for detecting and tracking both known and unknown objects in the open-world setting. We propose a new benchmark, TAO-OW: Tracking Any Object in an Open World, analyze existing efforts in multi-object tracking, and construct a baseline for this task while highlighting future challenges. We hope to open a new front in multi-object tracking research that will hopefully bring us a step closer to intelligent systems that can operate safely in the real world.
-
Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated a significant performance boost on training large-scale models such as vision transformers. However, the update rule of SAM requires two sequential (non-parallelizable) gradient computations at each step, which can double the computational overhead. In this paper, we propose a novel algorithm LookSAM - that only periodically calculates the inner gradient ascent, to significantly reduce the additional training cost of SAM. The empirical results illustrate that LookSAM achieves similar accuracy gains to SAM while being tremendously faster - it enjoys comparable computational complexity with first-order optimizers such as SGD or Adam. To further evaluate the performance and scalability of LookSAM, we incorporate a layer-wise modification and perform experiments in the large-batch training scenario, which is more prone to converge to sharp local minima. Equipped with the proposed algorithms, we are the first to successfully scale up the batch size when training Vision Transformers (ViTs). With a 64k batch size, we are able to train ViTs from scratch in minutes while maintaining competitive performance. The code is available here: https://github.com/yong-6/LookSAM
-
Detecting objects from LiDAR point clouds is of tremendous significance in autonomous driving. In spite of good progress, accurate and reliable 3D detection is yet to be achieved due to the sparsity and irregularity of LiDAR point clouds. Among existing strategies, multi-view methods have shown great promise by leveraging the more comprehensive information from both bird's eye view (BEV) and range view (RV). These multi-view methods either refine the proposals predicted from single view via fused features, or fuse the features without considering the global spatial context; their performance is limited consequently. In this paper, we propose to adaptively fuse multi-view features in a global spatial context via Dual Cross-VIew SpaTial Attention (VISTA). The proposed VISTA is a novel plug-and-play fusion module, wherein the multi-layer perceptron widely adopted in standard attention modules is replaced with a convolutional one. Thanks to the learned attention mechanism, VISTA can produce fused features of high quality for prediction of proposals. We decouple the classification and regression tasks in VISTA, and an additional constraint of attention variance is applied that enables the attention module to focus on specific targets instead of generic points. We conduct thorough experiments on the benchmarks of nuScenes and Waymo; results confirm the efficacy of our designs. At the time of submission, our method achieves 63.0% in overall mAP and 69.8% in NDS on the nuScenes benchmark, outperforming all published methods by up to 24% in safety-crucial categories such as cyclist.
-
A model that can authentically restore a low-quality face image to a high-quality one can benefit many applications. While existing approaches for face restoration make significant progress in generating high-quality faces, they often fail to preserve facial features and cannot authentically reconstruct the faces. Because the human visual system is very sensitive to faces, even minor facial changes may alter the identity and significantly degrade the perceptual quality. In this work, we argue the problems of existing models can be traced down to the two sub-tasks of the face restoration problem, i.e. face generation and face reconstruction, and the fragile balance between them. Based on the observation, we propose a new face restoration model that improves both generation and reconstruction by learning a stochastic model and enhancing the latent features respectively. Furthermore, we adapt the number of skip connections for a better balance between the two sub-tasks. Besides the model improvement, we also introduce a new evaluation metric for measuring models' ability to preserve the identity in the restored faces. Extensive experiments demonstrate that our model achieves state-of-the-art performance on multiple face restoration benchmarks. The user study shows that our model produces higher quality faces while better preserving the identity 86.4% of the time compared with the best performing baselines.
-
We address the problem of inferring the anatomic skeleton of a person, in an arbitrary pose, from the 3D surface of the body; i.e. we predict the inside (bones) from the outside (skin). This has many applications in medicine and biomechanics. Existing state-of-the-art biomechanical skeletons are detailed but do not easily generalize to new subjects. Additionally, computer vision and graphics methods that predict skeletons are typically heuristic, not learned from data, do not leverage the full 3D body surface, and are not validated against ground truth. To our knowledge, our system, called OSSO (Obtaining Skeletal Shape from Outside), is the first to learn the mapping from the 3D body surface to the internal skeleton from real data. We do so using 1000 male and 1000 female dual-energy X-ray absorptiometry (DXA) scans. To these, we fit a parametric 3D body shape model (STAR) to capture the body surface and a novel part-based 3D skeleton model to capture the bones. This provides inside/outside training pairs. We model the statistical variation of full skeletons using PCA in a pose-normalized space and train a regressor from body shape parameters to skeleton shape parameters. Given an arbitrary 3D body shape and pose, OSSO predicts a realistic skeleton inside. In contrast to previous work, we evaluate the accuracy of the skeleton shape quantitatively on held out DXA scans, outperforming the state-of-the art. We also show 3D skeleton prediction from varied and challenging 3D bodies. The code to infer a skeleton from a body shape is available at https://osso.is.tue.mpg.de, and the dataset of paired outer surface (skin) and skeleton (bone) meshes is available as a Biobank Returned Dataset. This research has been conducted using the UK Biobank Resource.
-
The objective of this paper is a temporal alignment network that ingests long term video sequences, and associated text sentences, in order to: (1) determine if a sentence is alignable with the video; and (2) if it is alignable, then determine its alignment. The challenge is to train such networks from large-scale datasets, such as HowTo100M, where the associated text sentences have significant noise, and are only weakly aligned when relevant. Apart from proposing the alignment network, we also make four contributions: (i) we describe a novel co-training method that enables to denoise and train on raw instructional videos without using manual annotation, despite the considerable noise; (ii) to benchmark the alignment performance, we manually curate a 10-hour subset of HowTo100M, totalling 80 videos, with sparse temporal descriptions. Our proposed model, trained on HowTo100M, outperforms strong baselines (CLIP, MIL-NCE) on this alignment dataset by a significant margin; (iii) we apply the trained model in the zero-shot settings to multiple downstream video understanding tasks and achieve state-of-the-art results, including text-video retrieval on YouCook2, and weakly supervised video action segmentation on Breakfast-Action. (iv) we use the automatically-aligned HowTo100M annotations for end-to-end finetuning of the backbone model, and obtain improved performance on downstream action recognition tasks.
-
The head swapping task aims at flawlessly placing a source head onto a target body, which is of great importance to various entertainment scenarios. While face swapping has drawn much attention in the community, the task of head swapping has rarely been explored, particularly under the few-shot setting. It is inherently challenging due to its unique needs in head modeling and background blending. In this paper, we present the Head Swapper (HeSer), which achieves few-shot head swapping in the wild through two dedicated designed modules. Firstly, a Head2Head Aligner is devised to holistically migrate position and expression information from the target to the source head by examining multi-scale information. Secondly, to tackle the challenges of skin color variations and head-background mismatches, a Head2Scene Blender is introduced to simultaneously modify facial skin color and fill mismatched gaps on the background around the head. Particularly, seamless blending is achieved through a semantic-guided exemplar warping procedure. User studies and experimental results demonstrate that the proposed method produces superior head swapping results on a variety of scenes.
-
Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases, such as ineffective or uneven data sampling, but also ethical concerns, as the social biases are implicitly present--even inadvertently, in the training data or explicitly defined in unfair training schedules. In tasks having impact on human processes, the learning of social biases may produce discriminatory, unethical and untrustworthy consequences. It is often assumed that social biases stem from supervised learning on labelled data, and thus, Self-Supervised Learning (SSL) wrongly appears as an efficient and bias-free solution, as it does not require labelled data. However, it was recently proven that a popular SSL method also incorporates biases. In this paper, we study the biases of a varied set of SSL visual models, trained using ImageNet data, using a method and dataset designed by psychological experts to measure social biases. We show that there is a correlation between the type of the SSL model and the number of biases that it incorporates. Furthermore, the results also suggest that this number does not strictly depend on the model's accuracy and changes throughout the network. Finally, we conclude that a careful SSL model selection process can reduce the number of social biases in the deployed model, whilst keeping high performance. The code is available at https://github.com/vpulab/SB-SSL.
-
Previous super-resolution (SR) approaches often formulate SR as a regression problem and pixel wise restoration, which leads to a blurry and unreal SR output. Recent works combine adversarial loss with pixel-wise loss to train a GAN-based model or introduce normalizing flows into SR problems to generate more realistic images. As another powerful generative approach, autoregressive (AR) model has not been noticed in low level tasks due to its limitation. Based on the fact that given the structural information, the textural details in the natural images are locally related without long term dependency, in this paper we propose a novel autoregressive model-based SR approach, namely LAR-SR, which can efficiently generate realistic SR images using a novel local autoregressive (LAR) module. The proposed LAR module can sample all the patches of textural components in parallel, which greatly reduces the time consumption. In addition to high time efficiency, it is also able to leverage contextual information of pixels and can be optimized with a consistent loss. Experimental results on the widely-used datasets show that the proposed LAR-SR approach achieves superior performance on the visual quality and quantitative metrics compared with other generative models such as GAN, Flow, and is competitive with the mixture generative model.
-
Generalization under distributional shift is an open challenge for machine learning. Invariant Risk Minimization (IRM) is a promising framework to tackle this issue by extracting invariant features. However, despite the potential and popularity of IRM, recent works have reported negative results of it on deep models. We argue that the failure can be primarily attributed to deep models' tendency to overfit the data. Specifically, our theoretical analysis shows that IRM degenerates to empirical risk minimization (ERM) when overfitting occurs. Our empirical evidence also provides supports: IRM methods that work well in typical settings significantly deteriorate even if we slightly enlarge the model size or lessen the training data. To alleviate this issue, we propose Bayesian Invariant Risk Minimization (BIRM) by introducing Bayesian inference into the IRM. The key motivation is to estimate the penalty of IRM based on the posterior distribution of classifiers (as opposed to a single classifier), which is much less prone to overfitting. Extensive experimental results on four datasets demonstrate that BIRM consistently outperforms the existing IRM baselines significantly.
-
Co-salient object detection, with the target of detecting co-existed salient objects among a group of images, is gaining popularity. Recent works use the attention mechanism or extra information to aggregate common co-salient features, leading to incomplete even incorrect responses for target objects. In this paper, we aim to mine comprehensive co-salient features with democracy and reduce background interference without introducing any extra information. To achieve this, we design a democratic prototype generation module to generate democratic response maps, covering sufficient co-salient regions and thereby involving more shared attributes of co-salient objects. Then a comprehensive prototype based on the response maps can be generated as a guide for final prediction. To suppress the noisy background information in the prototype, we propose a self-contrastive learning module, where both positive and negative pairs are formed without relying on additional classification information. Besides, we also design a democratic feature enhancement module to further strengthen the co-salient features by readjusting attention values. Extensive experiments show that our model obtains better performance than previous state-of-the-art methods, especially on challenging real-world cases (e.g., for CoCA, we obtain a gain of 2.0% for MAE, 5.4% for maximum F-measure, 2.3% for maximum E-measure, and 3.7% for S-measure) under the same settings. Code will be released soon.
-
Unsupervised image-to-image (I2I) translation aims to learn a domain mapping function that can preserve the semantics of the input images without paired data. However, because the underlying semantics distributions in the source and target domains are often mismatched, current distribution matching-based methods may distort the semantics when matching distributions, resulting in the inconsistency between the input and translated images, which is known as the semantics distortion problem. In this paper, we focus on the low-level I2I translation, where the structure of images is highly related to their semantics. To alleviate semantic distortions in such translation tasks without paired supervision, we propose a novel I2I translation constraint, called Structure Consistency Constraint (SCC), to promote the consistency of image structures by reducing the randomness of color transformation in the translation process. To facilitate estimation and maximization of SCC, we propose an approximate representation of mutual information called relative Squared-loss Mutual Information (rSMI) that enjoys efficient analytic solutions. Our SCC can be easily incorporated into most existing translation models. Quantitative and qualitative comparisons on a range of low-level I2I translation tasks show that translation models with SCC outperform the original models by a significant margin with little additional computational and memory costs.
-
The human visual system is remarkable in learning new visual concepts from just a few examples. This is precisely the goal behind few-shot class incremental learning (FSCIL), where the emphasis is additionally placed on ensuring the model does not suffer from "forgetting". In this paper, we push the boundary further for FSCIL by addressing two key questions that bottleneck its ubiquitous application (i) can the model learn from diverse modalities other than just photo (as humans do), and (ii) what if photos are not readily accessible (due to ethical and privacy constraints). Our key innovation lies in advocating the use of sketches as a new modality for class support. The product is a "Doodle It Yourself" (DIY) FSCIL framework where the users can freely sketch a few examples of a novel class for the model to learn to recognise photos of that class. For that, we present a framework that infuses (i) gradient consensus for domain invariant learning, (ii) knowledge distillation for preserving old class information, and (iii) graph attention networks for message passing between old and novel classes. We experimentally show that sketches are better class support than text in the context of FSCIL, echoing findings elsewhere in the sketching literature.
-
Current methods for learning realistic and animatable 3D clothed avatars need either posed 3D scans or 2D images with carefully controlled user poses. In contrast, our goal is to learn the avatar from only 2D images of people in unconstrained poses. Given a set of images, our method estimates a detailed 3D surface from each image and then combines these into an animatable avatar. Implicit functions are well suited to the first task, as they can capture details like hair or clothes. Current methods, however, are not robust to varied human poses and often produce 3D surfaces with broken or disembodied limbs, missing details, or non-human shapes. The problem is that these methods use global feature encoders that are sensitive to global pose. To address this, we propose ICON ("Implicit Clothed humans Obtained from Normals"), which uses local features. ICON has two main modules, both of which exploit the SMPL body model. First, ICON infers detailed clothed-human normals(front/back) conditioned on the SMPL normals. Second, a visibility-aware implicit surface regressor produces an iso-surface of the human occupancy field. Importantly, at inference time, a feedback loop alternates between refining the SMPL mesh using the inferred clothed normals and then refining the normals. Given multiple reconstructed frames of a subject in varied poses, we use modified SCANimate to produce an animatable avatar from them. Evaluation on the AGORA and CAPE datasets shows that ICON outperforms the state-of-the-art in reconstruction, even with heavily limited training data. Additionally, it is much more robust to out-of-distribution samples, e.g., in-the-wild poses/images and out-of-frame cropping. ICON takes a step towards pose-robust 3D clothed human reconstruction from in-the-wild images. This enables creating avatars directly from video with personalized and nature pose-dependent cloth deformation. Our models and code will be available for research.
-
Image prediction methods often struggle on tasks that require changing the positions of objects, such as video prediction, producing blurry images that average over the many positions that objects might occupy. In this paper, we propose a simple change to existing image similarity metrics that makes them more robust to positional errors: we match the images using optical flow, then measure the visual similarity of corresponding pixels. This change leads to crisper and more perceptually accurate predictions, and does not require modifications to the image prediction network. We apply our method to a variety of video prediction tasks, where it obtains strong performance with simple network architectures, and to the closely related task of video interpolation. Code and results are available at our webpage: https://dangeng.github.io/CorrWiseLosses
-
Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific paradigm, leading to inefficient collaboration between tasks and high marginal costs of developing perception models for new tasks. In this paper, we present a generic perception architecture named Uni-Perceiver, which processes a variety of modalities and tasks with unified modeling and shared parameters. Specifically, Uni-Perceiver encodes different task inputs and targets from arbitrary modalities into a unified representation space with a modality-agnostic Transformer encoder and lightweight modality-specific tokenizers. Different perception tasks are modeled as the same formulation, that is, finding the maximum likelihood target for each input through the similarity of their representations. The model is pre-trained on several uni-modal and multi-modal tasks, and evaluated on a variety of downstream tasks, including novel tasks that did not appear in the pre-training stage. Results show that our pre-trained model without any tuning can achieve reasonable performance even on novel tasks. The performance can be improved to a level close to state-of-the-art methods by conducting prompt tuning on 1% of downstream task data. Full-data fine-tuning further delivers results on par with or better than state-of-the-art results. Code and pre-trained weights shall be released.
-
Generalization to novel domains is a fundamental challenge for computer vision. Near-perfect accuracy on benchmarks is common, but these models do not work as expected when deployed outside of the training distribution. To build computer vision systems that truly solve real-world problems at global scale, we need benchmarks that fully capture real-world complexity, including geographic domain shift, long-tailed distributions, and data noise. We propose urban forest monitoring as an ideal testbed for studying and improving upon these computer vision challenges, while simultaneously working towards filling a crucial environmental and societal need. Urban forests provide significant benefits to urban societies (e.g., cleaner air and water, carbon sequestration, and energy savings among others). However, planning and maintaining these forests is expensive. One particularly costly aspect of urban forest management is monitoring the existing trees in a city: e.g., tracking tree locations, species, and health. Monitoring efforts are currently based on tree censuses built by human experts, costing cities millions of dollars per census and thus collected infrequently. Previous investigations into automating urban forest monitoring focused on small datasets from single cities, covering only common categories. To address these shortcomings, we introduce a new large-scale dataset that joins public tree censuses from 23 cities with a large collection of street level and aerial imagery. Our Auto Arborist dataset contains over 2.5M trees and 344 genera and is >2 orders of magnitude larger than the closest dataset in the literature. We introduce baseline results on our dataset across modalities as well as metrics for the detailed analysis of generalization with respect to geographic distribution shifts, vital for such a system to be deployed at-scale.
-
Relative pose estimation using the 5-point or 7-point Random Sample Consensus (RANSAC) algorithms can fail even when no outliers are present and there are enough inliers to support a hypothesis. These cases arise due to numerical instability of the 5- and 7-point minimal problems. This paper characterizes these instabilities, both in terms of minimal world scene configurations that lead to infinite condition number in epipolar estimation, and also in terms of the related minimal image feature pair correspondence configurations. The instability is studied in the context of a novel framework for analyzing the conditioning of minimal problems in multiview geometry, based on Riemannian manifolds. Experiments with synthetic and real-world data reveal that RANSAC does not only serve to filter out outliers, but RANSAC also selects for well-conditioned image data, sufficiently separated from the ill-posed locus that our theory predicts. These findings suggest that, in future work, one could try to accelerate and increase the success of RANSAC by testing only well-conditioned image data.
-
We present a new data-driven approach with physics-based priors to scene-level normal estimation from a single polarization image. Existing shape from polarization (SfP) works mainly focus on estimating the normal of a single object rather than complex scenes in the wild. A key barrier to high-quality scene-level SfP is the lack of real-world SfP data in complex scenes. Hence, we contribute the first real-world scene-level SfP dataset with paired input polarization images and ground-truth normal maps. Then we propose a learning-based framework with a multi-head self-attention module and viewing encoding, which is designed to handle increasing polarization ambiguities caused by complex materials and non-orthographic projection in scene-level SfP. Our trained model can be generalized to far-field outdoor scenes as the relationship between polarized light and surface normals is not affected by distance. Experimental results demonstrate that our approach significantly outperforms existing SfP models on two datasets. Our dataset and source code will be publicly available.
-
This demonstration showcases our innovations on efficient, accurate, and temporally consistent video semantic segmentation on mobile device. We employ our test-time unsupervised scheme, AuxAdapt, to enable the segmentation model to adapt to a given video in an online manner. More specifically, we leverage a small auxiliary network to perform weight updates and keep the large, main segmentation network frozen. This significantly reduces the computational cost of adaptation when compared to previous methods (e.g., Tent, DVP), and at the same time, prevents catastrophic forgetting. By running AuxAdapt, we can considerably improve the temporal consistency of video segmentation while maintaining the accuracy. We demonstrate how to efficiently deploy our adaptive video segmentation algorithm on a smartphone powered by a Snapdragon Mobile Platform. Rather than simply running the entire algorithm on the GPU, we adopt a cross-unit deployment strategy. The main network, which will be frozen during test time, will perform inferences on a highly optimized AI accelerator unit, while the small auxiliary network, which will be updated on the fly, will run forward passes and back-propagations on the GPU. Such a deployment scheme best utilizes the available processing power on the smartphone and enables real-time operation of our adaptive video segmentation algorithm. We provide example videos in supplementary material.
-
We present a self-supervised method to learn dynamic 3D deformations of garments worn by parametric human bodies. State-of-the-art data-driven approaches to model 3D garment deformations are trained using supervised strategies that require large datasets, usually obtained by expensive physics-based simulation methods or professional multi-camera capture setups. In contrast, we propose a new training scheme that removes the need for ground-truth samples, enabling self-supervised training of dynamic 3D garment deformations. Our key contribution is to realize that physics-based deformation models, traditionally solved in a frame-by-frame basis by implicit integrators, can be recasted as an optimization problem. We leverage such optimization-based scheme to formulate a set of physics-based loss terms that can be used to train neural networks without precomputing ground-truth data. This allows us to learn models for interactive garments, including dynamic deformations and fine wrinkles, with two orders of magnitude speed up in training time compared to state-of-the-art supervised methods.
-
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo labels are typically biased to the majority classes and basically noisy, leading to an error-prone and suboptimal model. In this paper, we propose a simple region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performance. Our algorithm, Region Impurity and Prediction Uncertainty (RIPU), introduces a new acquisition strategy characterizing the spatial adjacency of image regions along with the prediction confidence. We show that the proposed region-based selection strategy makes more efficient use of a limited budget than image-based or point-based counterparts. Further, we enforce local prediction consistency between a pixel and its nearest neighbors on a source image. Alongside, we develop a negative learning loss to make the features more discriminative. Extensive experiments demonstrate that our method only requires very few annotations to almost reach the supervised performance and substantially outperforms state-of-the-art methods. The code is available at https://github.com/BIT-DA/RIPU.
-
Transparent and semi-transparent materials pose significant challenges for existing scene understanding and segmentation algorithms due to their lack of RGB texture which impedes the extraction of meaningful features. In this work, we exploit that the light-matter interactions on glass materials provide unique intensity-polarization cues for each observed wavelength of light. We present a novel learning-based glass segmentation network that leverages both trichromatic (RGB) intensities as well as trichromatic linear polarization cues from a single photograph captured without making any assumption on the polarization state of the illumination. Our novel network architecture dynamically fuses and weights both the trichromatic color and polarization cues using a novel global-guidance and multi-scale self-attention module, and leverages global cross-domain contextual information to achieve robust segmentation. We train and extensively validate our segmentation method on a new large-scale RGB-Polarization dataset (RGBP-Glass), and demonstrate that our method outperforms state-of-the-art segmentation approaches by a significant margin.
-
Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which operates without any human labeling, is a promising approach to address this issue. We observe in the real world that humans are capable of mapping the visual concepts learnt from 2D images to understand the 3D world. Encouraged by this insight, we propose CrossPoint, a simple cross-modal contrastive learning approach to learn transferable 3D point cloud representations. It enables a 3D-2D correspondence of objects by maximizing agreement between point clouds and the corresponding rendered 2D image in the invariant space, while encouraging invariance to transformations in the point cloud modality. Our joint training objective combines the feature correspondences within and across modalities, thus ensembles a rich learning signal from both 3D point cloud and 2D image modalities in a self-supervised fashion. Experimental results show that our approach outperforms the previous unsupervised learning methods on a diverse range of downstream tasks including 3D object classification and segmentation. Further, the ablation studies validates the potency of our approach for a better point cloud understanding. Code and pretrained models are available at https://github.com/MohamedAfham/CrossPoint.
-
Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption. However, existing methods are prone to model overfitting and collapse in extremely few shot setting (less than 10). To solve this problem, we propose a relaxed spatial structural alignment (RSSA) method to calibrate the target generative models during the adaption. We design a cross-domain spatial structural consistency loss comprising the self-correlation and disturbance correlation consistency loss. It helps align the spatial structural information between the synthesis image pairs of the source and target domains. To relax the cross-domain alignment, we compress the original latent space of generative models to a subspace. Image pairs generated from the subspace are pulled closer. Qualitative and quantitative experiments show that our method consistently surpasses the state-of-the-art methods in few shot setting. Our source code: https://github.com/StevenShaw1999/RSSA.
-
Domain adaptive object detection (DAOD) is a promising way to alleviate performance drop of detectors in new scenes. Albeit great effort made in single source domain adaptation, a more generalized task with multiple source domains remains not being well explored, due to knowledge degradation during their combination. To address this issue, we propose a novel approach, namely target-relevant knowledge preservation (TRKP), to unsupervised multi-source DAOD. Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain. The teacher network is further equipped with an adversarial multi-source disentanglement (AMSD) module to preserve source domain-specific knowledge and simultaneously perform cross-domain alignment. Besides, a holistic target-relevant mining (HTRM) scheme is developed to re-weight the source images according to the source-target relevance. By this means, the teacher network is enforced to capture target-relevant knowledge, thus benefiting decreasing domain shift when mentoring object detection in the target domain. Extensive experiments are conducted on various widely used benchmarks with new state-of-the-art scores reported, highlighting the effectiveness.
-
Recent salient object detection (SOD) methods based on deep neural network have achieved remarkable performance. However, most of existing SOD models designed for low-resolution input perform poorly on high-resolution images due to the contradiction between the sampling depth and the receptive field size. Aiming at resolving this contradiction, we propose a novel one-stage framework called Pyramid Grafting Network (PGNet), using transformer and CNN backbone to extract features from different resolution images independently and then graft the features from transformer branch to CNN branch. An attention-based Cross-Model Grafting Module (CMGM) is proposed to enable CNN branch to combine broken detailed information more holistically, guided by different source feature during decoding process. Moreover, we design an Attention Guided Loss (AGL) to explicitly supervise the attention matrix generated by CMGM to help the network better interact with the attention from different models. We contribute a new Ultra-High-Resolution Saliency Detection dataset UHRSD, containing 5,920 images at 4K-8K resolutions. To our knowledge, it is the largest dataset in both quantity and resolution for high-resolution SOD task, which can be used for training and testing in future research. Sufficient experiments on UHRSD and widely-used SOD datasets demonstrate that our method achieves superior performance compared to the state-of-the-art methods.
-
Current image-to-image translations do not control the output domain beyond the classes used during training, nor do they interpolate between different domains well, leading to implausible results. This limitation largely arises because labels do not consider the semantic distance. To mitigate such problems, we propose a style-aware discriminator that acts as a critic as well as a style encoder to provide conditions. The style-aware discriminator learns a controllable style space using prototype-based self-supervised learning and simultaneously guides the generator. Experiments on multiple datasets verify that the proposed model outperforms current state-of-the-art image-to-image translation methods. In contrast with current methods, the proposed approach supports various applications, including style interpolation, content transplantation, and local image translation. The code is available at github.com/kunheek/style-aware-discriminator.
-
In this paper, we aim to estimate the direction of an underlying signal from its nonlinear observations following the semi-parametric single index model (SIM). Unlike for conventional compressed sensing where the signal is assumed to be sparse, we assume that the signal lies in the range of an L-Lipschitz continuous generative model with bounded k-dimensional inputs. This is mainly motivated by the tremendous success of deep generative models in various real applications. Our reconstruction method is non-iterative (though approximating the projection step may require an iterative procedure) and highly efficient, and it is shown to attain the near-optimal statistical rate of order \sqrt (k \log L)/m , where m is the number of measurements. We consider two specific instances of the SIM, namely noisy 1-bit and cubic measurement models, and perform experiments on image datasets to demonstrate the efficacy of our method. In particular, for the noisy 1-bit measurement model, we show that our non-iterative method significantly outperforms a state-of-the-art iterative method in terms of both accuracy and efficiency.
-
Due to the constraints of the imaging device and high cost in operation time, computer tomography (CT) scans are usually acquired with low within-slice resolution. Improving the inter-slice resolution is beneficial to the disease diagnosis for both human experts and computer-aided systems. To this end, this paper builds a novel medical slice synthesis to increase the inter-slice resolution. Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy to accomplish this task in the self-supervised learning manner. Specifically, we model this problem from three different views: slice-wise interpolation from axial view and pixel-wise interpolation from coronal and sagittal views. Under this circumstance, the models learned from different views can distill valuable knowledge to guide the learning processes of each other. We can repeat this process to make the models synthesize intermediate slice data with increasing between-slice resolution. To demonstrate the effectiveness of the proposed approach, we conduct comprehensive experiments on a large-scale CT dataset. Quantitative and qualitative comparison results show that our method outperforms state-of-the-art algorithms by clear margins.
-
Adversarial training has been shown to be one of the most effective approaches to improve the robustness of deep neural networks. It is formalized as a min-max optimization over model weights and adversarial perturbations, where the weights can be optimized through gradient descent methods like SGD. In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through Second-Order Statistics Optimization (S^2O) with respect to the weights. By relaxing a common (but unrealistic) assumption of previous PAC-Bayesian frameworks that all weights are statistically independent, we derive an improved PAC-Bayesian adversarial generalization bound, which suggests that optimizing second-order statistics of weights can effectively tighten the bound. In addition to this theoretical insight, we conduct an extensive set of experiments, which show that S^2O not only improves the robustness and generalization of the trained neural networks when used in isolation, but also integrates easily in state-of-the-art adversarial training techniques like TRADES, AWP, MART, and AVMixup, leading to a measurable improvement of these techniques. The code is available at https://github.com/Alexkael/S2O.
-
We scrutinise an important observation plaguing scene-level sketch research -- that a significant portion of scene sketches are "partial". A quick pilot study reveals: (i) a scene sketch does not necessarily contain all objects in the corresponding photo, due to the subjective holistic interpretation of scenes, (ii) there exists significant empty (white) regions as a result of object-level abstraction, and as a result, (iii) existing scene-level fine-grained sketch-based image retrieval methods collapse as scene sketches become more partial. To solve this "partial" problem, we advocate for a simple set-based approach using optimal transport (OT) to model cross-modal region associativity in a partially-aware fashion. Importantly, we improve upon OT to further account for holistic partialness by comparing intra-modal adjacency matrices. Our proposed method is not only robust to partial scene-sketches but also yields state-of-the-art performance on existing datasets.
-
Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior because the negative sample size (NSS) is limited by its mini-batch size (MBS). To decouple the NSS from the MBS, a dynamic dictionary has been adopted in a large volume of CL frameworks, among which arguably the most popular one is MoCo family. In essence, MoCo adopts a momentum-based queue dictionary, for which we perform a fine-grained analysis of its size and consistency. We point out that InfoNCE loss used in MoCo implicitly attract anchors to their corresponding positive sample with various strength of penalties and identify such inter-anchor hardness-awareness property as a major reason for the necessity of a large dictionary. Our findings motivate us to simplify MoCo v2 via the removal of its dictionary as well as momentum. Based on an InfoNCE with the proposed dual temperature, our simplified frameworks, SimMoCo and SimCo, outperform MoCo v2 by a visible margin. Moreover, our work bridges the gap between CL and non-CL frameworks, contributing to a more unified understanding of these two mainstream frameworks in SSL. Code is available at: https://bit.ly/3LkQbaT.
-
A novel ordinal regression algorithm, called moving window regression (MWR), is proposed in this paper. First, we propose the notion of relative rank (rho-rank), which is a new order representation scheme for input and reference instances. Second, we develop global and local relative regressors (rho-regressors) to predict rho-ranks within entire and specific rank ranges, respectively. Third, we refine an initial rank estimate iteratively by selecting two reference instances to form a search window and then estimating the rho-rank within the window. Extensive experiments results show that the proposed algorithm achieves the state-of-the-art performances on various benchmark datasets for facial age estimation and historical color image classification. The codes are available at https://github.com/nhshin-mcl/MWR.
-
Conditional image repainting (CIR) is an advanced image editing task, which requires the model to generate visual content in user-specified regions conditioned on multiple cross-modality constraints, and composite the visual content with the provided background seamlessly. Existing methods based on two-phase architecture design assume dependency between phases and cause color-image incongruity. To solve these problems, we propose a novel Unified Conditional image Repainting Network (UniCoRN). We break the two-phase assumption in CIR task by constructing the interaction and dependency relationship between background and other conditions. We further introduce the hierarchical structure into cross-modality similarity model to capture feature patterns at different levels and bridge the gap between visual content and color condition. A new LANDSCAPE-CIR dataset is collected and annotated to expand the application scenarios of the CIR task. Experiments show that UniCoRN achieves higher synthetic quality, better condition consistency, and more realistic compositing effect.
-
We propose the task of forecasting characteristic 3d poses: from a short sequence observation of a person, predict a future 3d pose of that person in a likely action-defining, characteristic pose - for instance, from observing a person picking up an apple, predict the pose of the person eating the apple. Prior work on human motion prediction estimates future poses at fixed time intervals. Although easy to define, this frame-by-frame formulation confounds temporal and intentional aspects of human action. Instead, we define a semantically meaningful pose prediction task that decouples the predicted pose from time, taking inspiration from goal-directed behavior. To predict characteristic poses, we propose a probabilistic approach that models the possible multi-modality in the distribution of likely characteristic poses. We then sample future pose hypotheses from the predicted distribution in an autoregressive fashion to model dependencies between joints. To evaluate our method, we construct a dataset of manually annotated characteristic 3d poses. Our experiments with this dataset suggest that our proposed probabilistic approach outperforms state-of-the-art methods by 26% on average.
-
Effective semi-supervised learning (SSL) in medical image analysis (MIA) must address two challenges: 1) work effectively on both multi-class (e.g., lesion classification) and multi-label (e.g., multiple-disease diagnosis) problems, and 2) handle imbalanced learning (because of the high variance in disease prevalence). One strategy to explore in SSL MIA is based on the pseudo labelling strategy, but it has a few shortcomings. Pseudo-labelling has in general lower accuracy than consistency learning, it is not specifically designed for both multi-class and multi-label problems, and it can be challenged by imbalanced learning. In this paper, unlike traditional methods that select confident pseudo label by threshold, we propose a new SSL algorithm, called anti-curriculum pseudo-labelling (ACPL), which introduces novel techniques to select informative unlabelled samples, improving training balance and allowing the model to work for both multi-label and multi-class problems, and to estimate pseudo labels by an accurate ensemble of classifiers (improving pseudo label accuracy). We run extensive experiments to evaluate ACPL on two public medical image classification benchmarks: Chest X-Ray14 for thorax disease multi-label classification and ISIC2018 for skin lesion multi-class classification. Our method outperforms previous SOTA SSL methods on both datasets
-
Defocus deblurring is a challenging task due to the spatially varying nature of defocus blur. While deep learning approach shows great promise in solving image restoration problems, defocus deblurring demands accurate training data that consists of all-in-focus and defocus image pairs, which is difficult to collect. Naive two-shot capturing cannot achieve pixel-wise correspondence between the defocused and all-in-focus image pairs. Synthetic aperture of light fields is suggested to be a more reliable way to generate accurate image pairs. However, the defocus blur generated from light field data is different from that of the images captured with a traditional digital camera. In this paper, we propose a novel deep defocus deblurring network that leverages the strength and overcomes the shortcoming of light fields. We first train the network on a light field-generated dataset for its highly accurate image correspondence. Then, we fine-tune the network using feature loss on another dataset collected by the two-shot method to alleviate the differences between the defocus blur exists in the two domains. This strategy is proved to be highly effective and able to achieve the state-of-the-art performance both quantitatively and qualitatively on multiple test sets. Extensive ablation studies have been conducted to analyze the effect of each network module to the final performance.
-
Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abnormal test samples. Among the successful approaches for anomaly detection, a distinguished category of methods relies on predicting masked information (e.g. patches, future frames, etc.) and leveraging the reconstruction error with respect to the masked information as an abnormality score. Different from related methods, we propose to integrate the reconstruction-based functionality into a novel self-supervised predictive architectural building block. The proposed self-supervised block is generic and can easily be incorporated into various state-of-the-art anomaly detection methods. Our block starts with a convolutional layer with dilated filters, where the center area of the receptive field is masked. The resulting activation maps are passed through a channel attention module. Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field. We demonstrate the generality of our block by integrating it into several state-of-the-art frameworks for anomaly detection on image and video, providing empirical evidence that shows considerable performance improvements on MVTec AD, Avenue, and ShanghaiTech. We release our code as open source at: https://github.com/ristea/sspcab.
-
Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a large domain gap lies between the source and target domains. In this paper we propose a novel solution named SSRT (Safe Self-Refinement for Transformer-based domain adaptation), which brings improvement from two aspects. First, encouraged by the success of vision transformers in various vision tasks, we arm SSRT with a transformer backbone. We find that the combination of vision transformer with simple adversarial adaptation surpasses best reported Convolutional Neural Network (CNN)-based results on the challenging DomainNet benchmark, showing its strong transferable feature representation. Second, to reduce the risk of model collapse and improve the effectiveness of knowledge transfer between domains with large gaps, we propose a Safe Self-Refinement strategy. Specifically, SSRT utilizes predictions of perturbed target domain data to refine the model. Since the model capacity of vision transformer is large and predictions in such challenging tasks can be noisy, a safe training mechanism is designed to adaptively adjust learning configuration. Extensive evaluations are conducted on several widely tested UDA benchmarks and SSRT achieves consistently the best performances, including 85.43% on Office-Home, 88.76% on VisDA-2017 and 45.2% on DomainNet.
-
Local density of point clouds is crucial for representing local details, but has been overlooked by existing point cloud compression methods. To address this, we propose a novel deep point cloud compression method that preserves local density information. Our method works in an auto-encoder fashion: the encoder downsamples the points and learns point-wise features, while the decoder upsamples the points using these features. Specifically, we propose to encode local geometry and density with three embeddings: density embedding, local position embedding and ancestor embedding. During the decoding, we explicitly predict the upsampling factor for each point, and the directions and scales of the upsampled points. To mitigate the clustered points issue in existing methods, we design a novel sub-point convolution layer, and an upsampling block with adaptive scale. Furthermore, our method can also compress point-wise attributes, such as normal. Extensive qualitative and quantitative results on SemanticKITTI and ShapeNet demonstrate that our method achieves the state-of-the-art rate-distortion trade-off.
-
We apply style transfer on mesh reconstructions of indoor scenes. This enables VR applications like experiencing 3D environments painted in the style of a favorite artist. Style transfer typically operates on 2D images, making stylization of a mesh challenging. When optimized over a variety of poses, stylization patterns become stretched out and inconsistent in size. On the other hand, model-based 3D style transfer methods exist that allow stylization from a sparse set of images, but they require a network at inference time. To this end, we optimize an explicit texture for the reconstructed mesh of a scene and stylize it jointly from all available input images. Our depth- and angle-aware optimization leverages surface normal and depth data of the underlying mesh to create a uniform and consistent stylization for the whole scene. Our experiments show that our method creates sharp and detailed results for the complete scene without view-dependent artifacts. Through extensive ablation studies, we show that the proposed 3D awareness enables style transfer to be applied to the 3D domain of a mesh. Our method can be used to render a stylized mesh in real-time with traditional rendering pipelines.
-
Transfer learning has been recently popularized as a data-efficient alternative to training models from scratch, in particular for computer vision tasks where it provides a remarkably solid baseline. The emergence of rich model repositories, such as TensorFlow Hub, enables the practitioners and researchers to unleash the potential of these models across a wide range of downstream tasks. As these repositories keep growing exponentially, efficiently selecting a good model for the task at hand becomes paramount. We provide a formalization of this problem through a familiar notion of regret and introduce the predominant strategies, namely task-agnostic (e.g. ranking models by their ImageNet performance) and task-aware search strategies (such as linear or kNN evaluation). We conduct a large-scale empirical study and show that both task-agnostic and task-aware methods can yield high regret. We then propose a simple and computationally efficient hybrid search strategy which outperforms the existing approaches. We highlight the practical benefits of the proposed solution on a set of 19 diverse vision tasks.
-
To deal with the great number of untrimmed videos produced every day, we propose an efficient unsupervised action segmentation method by detecting boundaries, named action boundary detection (ABD). In particular, the proposed method has the following advantages: no training stage and low-latency inference. To detect action boundaries, we estimate the similarities across smoothed frames, which inherently have the properties of internal consistency within actions and external discrepancy across actions. Under this circumstance, we successfully transfer the boundary detection task into the change point detection based on the similarity. Then, non-maximum suppression (NMS) is conducted in local windows to select the smallest points as candidate boundaries. In addition, a clustering algorithm is followed to refine the initial proposals. Moreover, we also extend ABD to the online setting, which enables real-time action segmentation in long untrimmed videos. By evaluating on four challenging datasets, our method achieves state-of-the-art performance. Moreover, thanks to the efficiency of ABD, we achieve the best trade-off between the accuracy and the inference time compared with existing unsupervised approaches.
-
Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations. We propose a 2-stage training scheme, i) feature augmentation - cloning part of the backbone and fine-tuning it on the novel data, and ii) fusion - combining the base and novel classifiers into a unified classifier. Experiments show that the proposed method significantly outperforms state-of-the-art CIL methods on the large-scale ImageNet dataset (e.g. +10% overall accuracy than the best). We also propose and analyze understudied practical CIL scenarios, such as base-novel overlap with distribution shift. Our proposed method is robust and generalizes to all analyzed CIL settings.
-
Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). While most existing graph regularizers focus on manipulating graph topological structures by adding/removing edges, we offer a method to augment node features for better performance. We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. By making the model invariant to small fluctuations in input data, our method helps models generalize to out-of-distribution samples and boosts model performance at test time. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks. FLAG is also highly flexible and scalable, and is deployable with arbitrary GNN backbones and large-scale datasets. We demonstrate the efficacy and stability of our method through extensive experiments and ablation studies. We also provide intuitive observations for a deeper understanding of our method. We open source our implementation at https://github.com/devnkong/FLAG.
-
Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn to denoise the (attacked) point clouds by reconstruction, and then feed them to the classifiers as input. In contrast to the literature, we propose a family of robust structured declarative classifiers for point cloud classification, where the internal constrained optimization mechanism can effectively defend adversarial attacks through implicit gradients. Such classifiers can be formulated using a bilevel optimization framework. We further propose an effective and efficient instantiation of our approach, namely, Lattice Point Classifier (LPC), based on structured sparse coding in the permutohedral lattice and 2D convolutional neural networks (CNNs) that is end-to-end trainable. We demonstrate state-of-the-art robust point cloud classification performance on ModelNet40 and ScanNet under seven different attackers. For instance, we achieve 89.51% and 83.16% test accuracy on each dataset under the recent JGBA attacker that outperforms DUP-Net and IF-Defense with PointNet by 70%. Demo code is available at https://zhang-vislab.github.io.
-
Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout. In this work, we go beyond this to propose PhotoScene, a framework that takes input image(s) of a scene along with approximately aligned CAD geometry (either reconstructed automatically or manually specified) and builds a photorealistic digital twin with high-quality materials and similar lighting. We model scene materials using procedural material graphs; such graphs represent photorealistic and resolution-independent materials. We optimize the parameters of these graphs and their texture scale and rotation, as well as the scene lighting to best match the input image via a differentiable rendering layer. We evaluate our technique on objects and layout reconstructions from ScanNet, SUN RGB-D and stock photographs, and demonstrate that our method reconstructs high-quality, fully relightable 3D scenes that can be re-rendered under arbitrary viewpoints, zooms and lighting.
-
The transferability of adversarial examples allows the deception on black-box models, and transfer-based targeted attacks have attracted a lot of interest due to their practical applicability. To maximize the transfer success rate, adversarial examples should avoid overfitting to the source model, and image augmentation is one of the primary approaches for this. However, prior works utilize simple image transformations such as resizing, which limits input diversity. To tackle this limitation, we propose the object-based diverse input (ODI) method that draws an adversarial image on a 3D object and induces the rendered image to be classified as the target class. Our motivation comes from the humans' superior perception of an image printed on a 3D object. If the image is clear enough, humans can recognize the image content in a variety of viewing conditions. Likewise, if an adversarial example looks like the target class to the model, the model should also classify the rendered image of the 3D object as the target class. The ODI method effectively diversifies the input by leveraging an ensemble of multiple source objects and randomizing viewing conditions. In our experimental results on the ImageNet-Compatible dataset, this method boosts the average targeted attack success rate from 28.3% to 47.0% compared to the state-of-the-art methods. We also demonstrate the applicability of the ODI method to adversarial examples on the face verification task and its superior performance improvement. Our code is available at https://github.com/dreamflake/ODI.
-
We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material textures readily deployable in existing graphics pipelines. We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material textures readily deployable in existing graphics pipelines. Our method adopts neural representations for geometry as signed distance fields (SDFs) and materials during optimization to enjoy their flexibility and compactness, and features a hybrid optimization scheme for neural SDFs: first, optimize using a volumetric radiance field approach to recover correct topology, then optimize further using edge-aware physics-based surface rendering for geometry refinement and disentanglement of materials and lighting. In the second stage, we also draw inspiration from mesh-based differentiable rendering, and design a novel edge sampling algorithm for neural SDFs to further improve performance. We show that our IRON achieves significantly better inverse rendering quality compared to prior works.
-
Objects play a crucial role in our everyday activities. Though multisensory object-centric learning has shown great potential lately, the modeling of objects in prior work is rather unrealistic. ObjectFolder 1.0 is a recent dataset that introduces 100 virtualized objects with visual, auditory, and tactile sensory data. However, the dataset is small in scale and the multisensory data is of limited quality, hampering generalization to real-world scenarios. We present ObjectFolder 2.0, a large-scale, multisensory dataset of common household objects in the form of implicit neural representations that significantly enhances ObjectFolder 1.0 in three aspects. First, our dataset is 10 times larger in the amount of objects and orders of magnitude faster in rendering time. Second, we significantly improve the multisensory rendering quality for all three modalities. Third, we show that models learned from virtual objects in our dataset successfully transfer to their real-world counterparts in three challenging tasks: object scale estimation, contact localization, and shape reconstruction. ObjectFolder 2.0 offers a new path and testbed for multisensory learning in computer vision and robotics. The dataset is available at https://github.com/rhgao/ObjectFolder.
-
Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train model that serves as a foundation for data-efficient downstream tasks transfer. To this end, we propose the Human-Centric Multi-Modal Contrastive Learning framework HCMoCo that leverages the multi-modal nature of human data (e.g. RGB, depth, 2D keypoints) for effective representation learning. The objective comes with two main challenges: dense pre-train for multi-modality data, efficient usage of sparse human priors. To tackle the challenges, we design the novel Dense Intra-sample Contrastive Learning and Sparse Structure-aware Contrastive Learning targets by hierarchically learning a modal-invariant latent space featured with continuous and ordinal feature distribution and structure-aware semantic consistency. HCMoCo provides pre-train for different modalities by combining heterogeneous datasets, which allows efficient usage of existing task-specific human data. Extensive experiments on four downstream tasks of different modalities demonstrate the effectiveness of HCMoCo, especially under data-efficient settings (7.16% and 12% improvement on DensePose Estimation and Human Parsing). Moreover, we demonstrate the versatility of HCMoCo by exploring cross-modality supervision and missing-modality inference, validating its strong ability in cross-modal association and reasoning.
-
360deg cameras can capture complete environments in a single shot, which makes 360deg imagery alluring in many computer vision tasks. However, monocular depth estimation remains a challenge for 360deg data, particularly for high resolutions like 2K (2048x1024) and beyond that are important for novel-view synthesis and virtual reality applications. Current CNN-based methods do not support such high resolutions due to limited GPU memory. In this work, we propose a flexible framework for monocular depth estimation from high-resolution 360deg images using tangent images. We project the 360deg input image onto a set of tangent planes that produce perspective views, which are suitable for the latest, most accurate state-of-the-art perspective monocular depth estimators. To achieve globally consistent disparity estimates, we recombine the individual depth estimates using deformable multi-scale alignment followed by gradient-domain blending. The result is a dense, high-resolution 360deg depth map with a high level of detail, also for outdoor scenes which are not supported by existing methods. Our source code and data are available at https://manurare.github.io/360monodepth/.
-
We present a method for semantically transferring the visual appearance of one natural image to another. Specifically, our goal is to generate an image in which objects in a source structure image are "painted" with the visual appearance of their semantically related objects in a target appearance image. Our method works by training a generator given only a single structure/appearance image pair as input. To integrate semantic information into our framework---a pivotal component in tackling this task---our key idea is to leverage a pre-trained and fixed Vision Transformer (ViT) model which serves as an external semantic prior. Specifically, we derive novel representations of structure and appearance extracted from deep ViT features, untwisting them from the learned self-attention modules. We then establish an objective function that splices the desired structure and appearance representations, interweaving them together in the space of ViT features. Our framework, which we term "Splice", does not involve adversarial training, nor does it require any additional input information such as semantic segmentation or correspondences, and can generate high resolution results, e.g., work in HD. We demonstrate high quality results on a variety of in-the-wild image pairs, under significant variations in the number of objects, their pose and appearance.
-
Appearance-based Gaze Estimation leverages deep neural networks to regress the gaze direction from monocular images and achieve impressive performance. However, its success depends on expensive and cumbersome annotation capture. When lacking precise annotation, the large domain gap hinders the performance of trained models on new domains. In this paper, we propose a novel gaze adaptation approach, namely Contrastive Regression Gaze Adaptation (CRGA), for generalizing gaze estimation on the target domain in an unsupervised manner. CRGA leverages the Contrastive Domain Generalization (CDG) module to learn the stable representation from the source domain and leverages the Contrastive Self-training Adaptation (CSA) module to learn from the pseudo labels on the target domain. The core of both CDG and CSA is the Contrastive Regression (CR) loss, a novel contrastive loss for regression by pulling features with closer gaze directions closer together while pushing features with farther gaze directions farther apart. Experimentally, we choose ETH-XGAZE and Gaze-360 as the source domain and test the domain generalization and adaptation performance on MPIIGAZE, RT-GENE, GazeCapture, EyeDiap respectively. The results demonstrate that our CRGA achieves remarkable performance improvement compared with the baseline models and also outperforms the state-of-the-art domain adaptation approaches on gaze adaptation tasks.
-
Accurate long-term trajectory prediction in complex scenes, where multiple agents (e.g., pedestrians or vehicles) interact with each other and the environment while attempting to accomplish diverse and often unknown goals, is a challenging stochastic forecasting problem. In this work, we propose MUSE-VAE, a new probabilistic modeling framework based on a cascade of Conditional VAEs, which tackles the long-term, uncertain trajectory prediction task using a coarse-to-fine multi-factor forecasting architecture. In its Macro stage, the model learns a joint pixel-space representation of two key factors, the underlying environment and the agent movements, to predict the long and short term motion goals. Conditioned on them, the Micro stage learns a fine-grained spatio-temporal representation for the prediction of individual agent trajectories. The VAE backbones across the two stages make it possible to naturally account for the joint uncertainty at both levels of granularity. As a result, MUSE-VAE offers diverse and simultaneously more accurate predictions compared to the current state-of-the-art. We demonstrate these assertions through a comprehensive set of experiments on nuScenes and SDD benchmarks as well as PFSD, a new synthetic dataset, which challenges the forecasting ability of models on complex agent-environment interaction scenarios.
-
3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view consistent images. To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints. By leveraging the underlying 3D geometry information of generated images, i.e., depth and camera transformation matrix, we explicitly establish stereo correspondence between views to perform multi-view joint optimization. In particular, we enforce the photometric consistency between pairs of views and integrate a stereo mixup mechanism into the training process, encouraging the model to reason about the correct 3D shape. Besides, we design a two-stage training strategy with feature-level multi-view joint optimization to improve the image quality. Extensive experiments on three datasets demonstrate that MVCGAN achieves the state-of-the-art performance for 3D-aware image synthesis.
-
Given an image with multiple people, our goal is to directly regress the pose and shape of all the people as well as their relative depth. Inferring the depth of a person in an image, however, is fundamentally ambiguous without knowing their height. This is particularly problematic when the scene contains people of very different sizes, e.g. from infants to adults. To solve this, we need several things. First, we develop a novel method to infer the poses and depth of multiple people in a single image. While previous work that estimates multiple people does so by reasoning in the image plane, our method, called BEV, adds an additional imaginary Bird's-Eye-View representation to explicitly reason about depth. BEV reasons simultaneously about body centers in the image and in depth and, by combing these, estimates 3D body position. Unlike prior work, BEV is a single-shot method that is end-to-end differentiable. Second, height varies with age, making it impossible to resolve depth without also estimating the age of people in the image. To do so, we exploit a 3D body model space that lets BEV infer shapes from infants to adults. Third, to train BEV, we need a new dataset. Specifically, we create a "Relative Human" (RH) dataset that includes age labels and relative depth relationships between the people in the images. Extensive experiments on RH and AGORA demonstrate the effectiveness of the model and training scheme. BEV outperforms existing methods on depth reasoning, child shape estimation, and robustness to occlusion. The code and dataset are released for research purposes.
-
Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector. To overcome this limitation, a few approaches infer latent vectors on a coarse regular 3D grid or on 3D patches, and interpolate them to answer occupancy queries. In doing so, they loose the direct connection with the input points sampled on the surface of objects, and they attach information uniformly in space rather than where it matters the most, i.e., near the surface. Besides, relying on fixed patch sizes may require discretization tuning. To address these issues, we propose to use point cloud convolutions and compute latent vectors at each input point. We then perform a learning-based interpolation on nearest neighbors using inferred weights. Experiments on both object and scene datasets show that our approach significantly outperforms other methods on most classical metrics, producing finer details and better reconstructing thinner volumes. The code is available at https://github.com/valeoai/POCO
-
In this paper, we propose a simple yet effective video super-resolution method that aims at generating high-fidelity high-resolution (HR) videos from low-resolution (LR) ones. Previous methods predominantly leverage temporal neighbor frames to assist the super-resolution of the current frame. Those methods achieve limited performance as they suffer from the challenges in spatial frame alignment and the lack of useful information from similar LR neighbor frames. In contrast, we devise a cross-frame non-local attention mechanism that allows video super-resolution without frame alignment, leading to being more robust to large motions in the video. In addition, to acquire general video prior information beyond neighbor frames, and to compensate for the information loss caused by large motions, we design a novel memory-augmented attention module to memorize general video details during the super-resolution training. We have thoroughly evaluated our work on various challenging datasets. Compared to other recent video super-resolution approaches, our method not only achieves significant performance gains on large motion videos but also shows better generalization. Our source code and the new Parkour benchmark dataset will be released.
-
We deal with the controllable person image synthesis task which aims to re-render a human from a reference image with explicit control over body pose and appearance. Observing that person images are highly structured, we propose to generate desired images by extracting and distributing semantic entities of reference images. To achieve this goal, a neural texture extraction and distribution operation based on double attention is described. This operation first extracts semantic neural textures from reference feature maps. Then, it distributes the extracted neural textures according to the spatial distributions learned from target poses. Our model is trained to predict human images in arbitrary poses, which encourages it to extract disentangled and expressive neural textures representing the appearance of different semantic entities. The disentangled representation further enables explicit appearance control. Neural textures of different reference images can be fused to control the appearance of the interested areas. Experimental comparisons show the superiority of the proposed model. Code is available at https://github.com/RenYurui/Neural-Texture-Extraction-Distribution.
-
Today's VidSGG models are all proposal-based methods, i.e., they first generate numerous paired subject-object snippets as proposals, and then conduct predicate classification for each proposal. In this paper, we argue that this prevalent proposal-based framework has three inherent drawbacks: 1) The ground-truth predicate labels for proposals are partially correct. 2) They break the high-order relations among different predicate instances of a same subject-object pair. 3) VidSGG performance is upper-bounded by the quality of the proposals. To this end, we propose a new classification-then-grounding framework for VidSGG, which can avoid all the three overlooked drawbacks. Meanwhile, under this framework, we reformulate the video scene graphs as temporal bipartite graphs, where the entities and predicates are two types of nodes with time slots, and the edges denote different semantic roles between these nodes. This formulation takes full advantage of our new framework. Accordingly, we further propose a novel BIpartite Graph based SGG model: BIG. It consists of a classification stage and a grounding stage, where the former aims to classify the categories of all the nodes and the edges, and the latter tries to localize the temporal location of each relation instance. Extensive ablations on two VidSGG datasets have attested to the effectiveness of our framework and BIG. Code is available at https://github.com/Dawn-LX/VidSGG-BIG.
-
Magnetic resonance imaging (MRI) can present multi-contrast images of the same anatomical structures, enabling multi-contrast super-resolution (SR) techniques. Compared with SR reconstruction using a single-contrast, multi-contrast SR reconstruction is promising to yield SR images with higher quality by leveraging diverse yet complementary information embedded in different imaging modalities. However, existing methods still have two shortcomings: (1) they neglect that the multi-contrast features at different scales contain different anatomical details and hence lack effective mechanisms to match and fuse these features for better reconstruction; and (2) they are still deficient in capturing long-range dependencies, which are essential for the regions with complicated anatomical structures. We propose a novel network to comprehensively address these problems by developing a set of innovative Transformer-empowered multi-scale contextual matching and aggregation techniques; we call it McMRSR. Firstly, we tame transformers to model long-range dependencies in both reference and target images. Then, a new multi-scale contextual matching method is proposed to capture corresponding contexts from reference features at different scales. Furthermore, we introduce a multi-scale aggregation mechanism to gradually and interactively aggregate multi-scale matched features for reconstructing the target SR MR image. Extensive experiments demonstrate that our network outperforms state-of-the-art approaches and has great potential to be applied in clinical practice.
-
Appearance-based gaze estimation aims to predict the 3D eye gaze direction from a single image. While recent deep learning-based approaches have demonstrated excellent performance, they usually assume one calibrated face in each input image and cannot output multi-person gaze in real time. However, simultaneous gaze estimation for multiple people in the wild is necessary for real-world applications. In this paper, we propose the first one-stage end-to-end gaze estimation method, GazeOnce, which is capable of simultaneously predicting gaze directions for multiple faces (>10) in an image. In addition, we design a sophisticated data generation pipeline and propose a new dataset, MPSGaze, which contains full images of multiple people with 3D gaze ground truth. Experimental results demonstrate that our unified framework not only offers a faster speed, but also provides a lower gaze estimation error compared with state-of-the-art methods. This technique can be useful in real-time applications with multiple users.
-
Online action detection is the task of predicting the action as soon as it happens in a streaming video. A major challenge is that the model does not have access to the future and has to solely rely on the history, i.e., the frames observed so far, to make predictions. It is therefore important to accentuate parts of the history that are more informative to the prediction of the current frame. We present GateHUB, Gated History Unit with Background Suppression, that comprises a novel position-guided gated cross-attention mechanism to enhance or suppress parts of the history as per how informative they are for current frame prediction. GateHUB further proposes Future-augmented History (FaH) to make history features more informative by using subsequently observed frames when available. In a single unified framework, GateHUB integrates the transformer's ability of long-range temporal modeling and the recurrent model's capacity to selectively encode relevant information. GateHUB also introduces a background suppression objective to further mitigate false positive background frames that closely resemble the action frames. Extensive validation on three benchmark datasets, THUMOS, TVSeries, and HDD, demonstrates that GateHUB significantly outperforms all existing methods and is also more efficient than the existing best work. Furthermore, a flow-free version of GateHUB is able to achieve higher or close accuracy at 2.8x higher frame rate compared to all existing methods that require both RGB and optical flow information for prediction.
-
Few-shot font generation (FFG), which aims to generate a new font with a few examples, is gaining increasing attention due to the significant reduction in labor cost. A typical FFG pipeline considers characters in a standard font library as content glyphs and transfers them to a new target font by extracting style information from the reference glyphs. Most existing solutions explicitly disentangle content and style of reference glyphs globally or component-wisely. However, the style of glyphs mainly lies in the local details, i.e. the styles of radicals, components, and strokes together depict the style of a glyph. Therefore, even a single character can contain different styles distributed over spatial locations. In this paper, we propose a new font generation approach by learning 1) the fine-grained local styles from references, and 2) the spatial correspondence between the content and reference glyphs. Therefore each spatial location in the content glyph can be assigned with the right fine-grained style. To this end, we adopt cross-attention over the representation of the content glyphs as the queries and the representations of the reference glyphs as the keys and values. Instead of explicitly disentangling global or component-wise modeling, the cross attention mechanism can attend to the right local styles in the reference glyphs and aggregates the reference styles into a fine-grained style representation for the given content glyphs. The experiments show that the proposed method outperforms the state-of-the-art methods in FFG. In particular, the user studies also demonstrate the style consistency of our approach is significantly outperforms previous methods.
-
Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local associations between videos and texts. Another line of research uses a joint encoder to interact video with texts, but results in low efficiency since each text-video pair needs to be fed into the model. In this work, we enable fine-grained video-text interactions while maintaining high efficiency for retrieval via a novel pretext task, dubbed as Multiple Choice Questions (MCQ), where a parametric module BridgeFormer is trained to answer the "questions" constructed by the text features via resorting to the video features. Specifically, we exploit the rich semantics of text (i.e., nouns and verbs) to build questions, with which the video encoder can be trained to capture more regional content and temporal dynamics. In the form of questions and answers, the semantic associations between local video-text features can be properly established. BridgeFormer is able to be removed for downstream retrieval, rendering an efficient and flexible model with only two encoders. Our method outperforms state-of-the-art methods on the popular text-to-video retrieval task in five datasets with different experimental setups (i.e., zero-shot and fine-tune), including HowTo100M (one million videos). We further conduct zero-shot action recognition, which can be cast as video-to-text retrieval, and our approach also significantly surpasses its counterparts. As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e.g., action recognition with linear evaluation.
-
Talking head video generation aims to produce a synthetic human face video that contains the identity and pose information respectively from a given source image and a driving video. Existing works for this task heavily rely on 2D representations (e.g. appearance and motion) learned from the input images. However, dense 3D facial geometry (e.g. pixel-wise depth) is extremely important for this task as it is particularly beneficial for us to essentially generate accurate 3D face structures and distinguish noisy information from the possibly cluttered background. Nevertheless, dense 3D geometry annotations are prohibitively costly for videos and are typically not available for this video generation task. In this paper, we introduce a self-supervised face-depth learning method to automatically recover dense 3D facial geometry (i.e. depth) from the face videos without the requirement of any expensive 3D annotation data. Based on the learned dense depth maps, we further propose to leverage them to estimate sparse facial keypoints that capture the critical movement of the human head. In a more dense way, the depth is also utilized to learn 3D-aware cross-modal (i.e. appearance and depth) attention to guide the generation of motion fields for warping source image representations. All these contributions compose a novel depth-aware generative adversarial network (DaGAN) for talking head generation. Extensive experiments conducted demonstrate that our proposed method can generate highly realistic faces, and achieve significant results on the unseen human faces.
-
Deep image inpainting can inpaint a corrupted image using a feed-forward inference, but still fails to handle large missing area or complex semantics. Recently, GAN inversion based inpainting methods propose to leverage semantic information in pretrained generator (e.g., StyleGAN) to solve the above issues. Different from feed-forward methods, they seek for a closest latent code to the corrupted image and feed it to a pretrained generator. However, inferring the latent code is either time-consuming or inaccurate. In this paper, we develop a dual-path inpainting network with inversion path and feed-forward path, in which inversion path provides auxiliary information to help feed-forward path. We also design a novel deformable fusion module to align the feature maps in two paths. Experiments on FFHQ and LSUN demonstrate that our method is effective in solving the aforementioned problems while producing more realistic results than state-of-the-art methods.
-
Synthesizing high-quality realistic images from text descriptions is a challenging task. Existing text-to-image Generative Adversarial Networks generally employ a stacked architecture as the backbone yet still remain three flaws. First, the stacked architecture introduces the entanglements between generators of different image scales. Second, existing studies prefer to apply and fix extra networks in adversarial learning for text-image semantic consistency, which limits the supervision capability of these networks. Third, the cross-modal attention-based text-image fusion that widely adopted by previous works is limited on several special image scales because of the computational cost. To these ends, we propose a simpler but more effective Deep Fusion Generative Adversarial Networks (DF-GAN). To be specific, we propose: (i) a novel one-stage text-to-image backbone that directly synthesizes high-resolution images without entanglements between different generators, (ii) a novel Target-Aware Discriminator composed of Matching-Aware Gradient Penalty and One-Way Output, which enhances the text-image semantic consistency without introducing extra networks, (iii) a novel deep text-image fusion block, which deepens the fusion process to make a full fusion between text and visual features. Compared with current state-of-the-art methods, our proposed DF-GAN is simpler but more efficient to synthesize realistic and text-matching images and achieves better performance on widely used datasets. Code is available at https://github.com/tobran/DF-GAN.
-
Flow-based generative models have shown an excellent ability to explicitly learn the probability density function of data via a sequence of invertible transformations. Yet, learning attentions in generative flows remains understudied, while it has made breakthroughs in other domains. To fill the gap, this paper introduces two types of invertible attention mechanisms, i.e., map-based and transformer-based attentions, for both unconditional and conditional generative flows. The key idea is to exploit a masked scheme of these two attentions to learn long-range data dependencies in the context of generative flows. The masked scheme allows for invertible attention modules with tractable Jacobian determinants, enabling its seamless integration at any positions of the flow-based models. The proposed attention mechanisms lead to more efficient generative flows, due to their capability of modeling the long-term data dependencies. Evaluation on multiple image synthesis tasks shows that the proposed attention flows result in efficient models and compare favorably against the state-of-the-art unconditional and conditional generative flows.
-
Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic Neural Networks (HNNs) exploit such representational power by lifting Euclidean features into hyperbolic space for classification, outperforming Euclidean neural networks (ENNs) on datasets with known semantic hierarchies. However, HNNs underperform ENNs on standard benchmarks without clear hierarchies, greatly restricting HNNs' applicability in practice. Our key insight is that HNNs' poorer general classification performance results from vanishing gradients during backpropagation, caused by their hybrid architecture connecting Euclidean features to a hyperbolic classifier. We propose an effective solution by simply clipping the Euclidean feature magnitude while training HNNs. Our experiments demonstrate that clipped HNNs become super-hyperbolic classifiers: They are not only consistently better than HNNs which already outperform ENNs on hierarchical data, but also on-par with ENNs on MNIST, CIFAR10, CIFAR100 and ImageNet benchmarks, with better adversarial robustness and out-of-distribution detection.
-
Image denoising has achieved unprecedented progress as great efforts have been made to exploit effective deep denoisers. To improve the denoising performance in real-world, two typical solutions are used in recent trends: devising better noise models for the synthesis of more realistic training data, and estimating noise level function to guide non-blind denoisers. In this work, we combine both noise modeling and estimation, and propose an innovative noise model estimation and noise synthesis pipeline for realistic noisy image generation. Specifically, our model learns a noise estimation model with fine-grained statistical noise model in a contrastive manner. Then, we use the estimated noise parameters to model camera-specific noise distribution, and synthesize realistic noisy training data. The most striking thing for our work is that by calibrating noise models of several sensors, our model can be extended to predict other cameras. In other words, we can estimate camera-specific noise models for unknown sensors with only testing images, without any laborious calibration frames or paired noisy/clean data. The proposed pipeline endows deep denoisers with competitive performances with state-of-the-art real noise modeling methods.
-
Current deep neural network approaches for camera pose estimation rely on scene structure for 3D motion estimation, but this decreases the robustness and thereby makes cross-dataset generalization difficult. In contrast, classical approaches to structure from motion estimate 3D motion utilizing optical flow and then compute depth. Their accuracy, however, depends strongly on the quality of the optical flow. To avoid this issue, direct methods have been proposed, which separate 3D motion from depth estimation but compute 3D motion using only image gradients in the form of normal flow. In this paper, we introduce a network NFlowNet, for normal flow estimation which is used to enforce robust and direct constraints. In particular, normal flow is used to estimate relative camera pose based on the cheirality (depth positivity) constraint. We achieve this by formulating the optimization problem as a differentiable cheirality layer, which allows for end-to-end learning of camera pose. We perform extensive qualitative and quantitative evaluation of the proposed DiffPoseNet's sensitivity to noise and its generalization across datasets. We compare our approach to existing state-of-the-art methods on KITTI, TartanAir, and TUM-RGBD datasets
-
Finding prototypes (e.g., mean and median) for a dataset is central to a number of common machine learning algorithms. Subspaces have been shown to provide useful, robust representations for datasets of images, videos and more. Since subspaces correspond to points on a Grassmann manifold, one is led to consider the idea of a subspace prototype for a Grassmann-valued dataset. While a number of different subspace prototypes have been described, the calculation of some of these prototypes has proven to be computationally expensive while other prototypes are affected by outliers and produce highly imperfect clustering on noisy data. This work proposes a new subspace prototype, the flag median, and introduces the FlagIRLS algorithm for its calculation. We provide evidence that the flag median is robust to outliers and can be used effectively in algorithms like Linde-Buzo-Grey (LBG) to produce improved clusterings on Grassmannians. Numerical experiments include a synthetic dataset, the MNIST handwritten digits dataset, the Mind's Eye video dataset and the UCF YouTube action dataset. The flag median is compared the other leading algorithms for computing prototypes on the Grassmannian, namely, the l_2-median and to the flag mean. We find that using FlagIRLS to compute the flag median converges in 4 iterations on a synthetic dataset. We also see that Grassmannian LBG with a codebook size of 20 and using the flag median produces at least a 10% improvement in cluster purity over Grassmannian LBG using the flag mean or l_2-median on the Mind's Eye dataset.
-
Quantization has been applied to multiple domains in Deep Neural Networks (DNNs). We propose Depthwise Quantization (DQ) where quantization is applied to a decomposed sub-tensor along the feature axis of weak statistical dependence. The feature decomposition leads to an exponential increase in representation capacity with a linear increase in memory and parameter cost. In addition, DQ can be directly applied to existing encoder-decoder frameworks without modification of the DNN architecture. We use DQ in the context of Hierarchical Auto-Encoders and train end-to-end on an image feature representation. We provide an analysis of the cross-correlation between spatial and channel features and propose a decomposition of the image feature representation along the channel axis. The improved performance of the depthwise operator is due to the increased representation capacity from implicit feature decoupling. We evaluate DQ on the likelihood estimation task, where it outperforms the previous state-of-the-art on CIFAR-10, ImageNet-32 and ImageNet-64. We progressively train with increasing image size a single hierarchical model that uses 69% fewer parameters and has faster convergence than the previous work.
-
Deep learning for graph matching has received growing interest and developed rapidly in the past decade. Although recent deep graph matching methods have shown excellent performance on matching between graphs of equal size in the computer vision area, the size-varied graph matching problem, where the number of keypoints in the images of the same category may vary due to occlusion, is still an open and challenging problem. To tackle this, we firstly propose to formulate the combinatorial problem of graph matching as an Integer Linear Programming (ILP) problem, which is more flexible and efficient to facilitate comparing graphs of varied sizes. A novel Graph-context Attention Network (GCAN), which jointly capture intrinsic graph structure and cross-graph information for improving the discrimination of node features, is then proposed and trained to resolve this ILP problem with node correspondence supervision. We further show that the proposed GCAN model is efficient to resolve the graph-level matching problem and is able to automatically learn node-to-node similarity via graph-level matching. The proposed approach is evaluated on three public keypoint-matching datasets and one graph-matching dataset for blood vessel patterns, with experimental results showing its superior performance over existing state-of-the-art algorithms on the keypoint and graph-level matching tasks.
-
Previous portrait image generation methods roughly fall into two categories: 2D GANs and 3D-aware GANs. 2D GANs can generate high fidelity portraits but with low view consistency. 3D-aware GAN methods can maintain view consistency but their generated images are not locally editable. To overcome these limitations, we propose FENeRF, a 3D-aware generator that can produce view-consistent and locally-editable portrait images. Our method uses two decoupled latent codes to generate corresponding facial semantics and texture in a spatial-aligned 3D volume with shared geometry. Benefiting from such underlying 3D representation, FENeRF can jointly render the boundary-aligned image and semantic mask and use the semantic mask to edit the 3D volume via GAN inversion. We further show such 3D representation can be learned from widely available monocular image and semantic mask pairs. Moreover, we reveal that joint learning semantics and texture helps to generate finer geometry. Our experiments demonstrate that FENeRF outperforms state-of-the-art methods in various face editing tasks.
-
We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i.e. camera control). We allow the user to annotate which part of the scene one wishes to control with just a small number of mask annotations in the training images. Our key idea is to treat the attributes as latent variables that are regressed by the neural network given the scene encoding. This leads to a few-shot learning framework, where attributes are discovered automatically by the framework when annotations are not provided. We apply our method to various scenes with different types of controllable attributes (e.g. expression control on human faces, or state control in the movement of inanimate objects). Overall, we demonstrate, to the best of our knowledge, for the first time novel view and novel attribute re-rendering of scenes from a single video.
-
Image noise modeling is a long-standing problem with many applications in computer vision. Early attempts that propose simple models, such as signal-independent additive white Gaussian noise or the heteroscedastic Gaussian noise model (a.k.a., camera noise level function) are not sufficient to learn the complex behavior of the camera sensor noise. Recently, more complex learning-based models have been proposed that yield better results in noise synthesis and downstream tasks, such as denoising. However, their dependence on supervised data (i.e., paired clean images) is a limiting factor given the challenges in producing ground-truth images. This paper proposes a framework for training a noise model and a denoiser simultaneously while relying only on pairs of noisy images rather than noisy/clean paired image data. We apply this framework to the training of the Noise Flow architecture. The noise synthesis and density estimation results show that our framework outperforms previous signal-processing-based noise models and is on par with its supervised counterpart. The trained denoiser is also shown to significantly improve upon both supervised and weakly supervised baseline denoising approaches. The results indicate that the joint training of a denoiser and a noise model yields significant improvements in the denoiser.
-
Less than 35% of recyclable waste is being actually recycled in the US, which leads to increased soil and sea pollution and is one of the major concerns of environmental researchers as well as the common public. At the heart of the problem are the inefficiencies of the waste sorting process (separating paper, plastic, metal, glass, etc.) due to the extremely complex and cluttered nature of the waste stream. Recyclable waste detection poses a unique computer vision challenge as it requires detection of highly deformable and often translucent objects in cluttered scenes without the kind of context information usually present in human-centric datasets. This challenging computer vision task currently lacks suitable datasets or methods in the available literature. In this paper, we take a step towards computer-aided waste detection and present the first in-the-wild industrial-grade waste detection and segmentation dataset, ZeroWaste. We believe that ZeroWaste will catalyze research in object detection and semantic segmentation in extreme clutter as well as applications in the recycling domain. Our project page can be found at http://ai.bu.edu/zerowaste/.
-
To realize trajectory prediction, most previous methods adopt the parameter-based approach, which encodes all the seen past-future instance pairs into model parameters. However, in this way, the model parameters come from all seen instances, which means a huge amount of irrelevant seen instances might also involve in predicting the current situation, disturbing the performance. To provide a more explicit link between the current situation and the seen instances, we imitate the mechanism of retrospective memory in neuropsychology and propose MemoNet, an instance-based approach that predicts the movement intentions of agents by looking for similar scenarios in the training data. In MemoNet, we design a pair of memory banks to explicitly store representative instances in the training set, acting as prefrontal cortex in the neural system, and a trainable memory addresser to adaptively search a current situation with similar instances in the memory bank, acting like basal ganglia. During prediction, MemoNet recalls previous memory by using the memory addresser to index related instances in the memory bank. We further propose a two-step trajectory prediction system, where the first step is to leverage MemoNet to predict the destination and the second step is to fulfill the whole trajectory according to the predicted destinations. Experiments show that the proposed MemoNet improves the FDE by 20.3%/10.2%/28.3% from the previous best method on SDD/ETH-UCY/NBA datasets. Experiments also show that our MemoNet has the ability to trace back to specific instances during prediction, promoting more interpretability.
-
Recent video question answering benchmarks indicate that state-of-the-art models struggle to answer compositional questions. However, it remains unclear which types of compositional reasoning cause models to mispredict. Furthermore, it is difficult to discern whether models arrive at answers using compositional reasoning or by leveraging data biases. In this paper, we develop a question decomposition engine that programmatically deconstructs a compositional question into a directed acyclic graph of sub-questions. The graph is designed such that each parent question is a composition of its children. We present AGQA-Decomp, a benchmark containing 2.3M question graphs, with an average of 11.49 sub-questions per graph, and 4.55M total new sub-questions. Using question graphs, we evaluate three state-of-the-art models with a suite of novel compositional consistency metrics. We find that models either cannot reason correctly through most compositions or are reliant on incorrect reasoning to reach answers, frequently contradicting themselves or achieving high accuracies when failing at intermediate reasoning steps.
-
Instance contrast for unsupervised representation learning has achieved great success in recent years. In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks. By considering instance contrastive learning as a dictionary look-up operation, we construct a semantics-aware dictionary with samples from both source and target domains where each target sample is assigned a (pseudo) category label based on the category priors of source samples. This allows category contrastive learning (between target queries and the category-level dictionary) for category-discriminative yet domain-invariant feature representations: samples of the same category (from either source or target domain) are pulled closer while those of different categories are pushed apart simultaneously. Extensive UDA experiments in multiple visual tasks (e.g., segmentation, classification and detection) show that CaCo achieves superior performance as compared with state-of-the-art methods. The experiments also demonstrate that CaCo is complementary to existing UDA methods and generalizable to other learning setups such as unsupervised model adaptation, open-/partial-set adaptation etc.
-
While Visual Question Answering (VQA) has progressed rapidly, previous works raise concerns about robustness of current VQA models. In this work, we study the robustness of VQA models from a novel perspective: visual context. We suggest that the models over-rely on the visual context, i.e., irrelevant objects in the image, to make predictions. To diagnose the models' reliance on visual context and measure their robustness, we propose a simple yet effective perturbation technique, SwapMix. SwapMix perturbs the visual context by swapping features of irrelevant context objects with features from other objects in the dataset. Using SwapMix we are able to change answers to more than 45% of the questions for a representative VQA model. Additionally, we train the models with perfect sight and find that the context over-reliance highly depends on the quality of visual representations. In addition to diagnosing, SwapMix can also be applied as a data augmentation strategy during training in order to regularize the context over-reliance. By swapping the context object features, the model reliance on context can be suppressed effectively. Two representative VQA models are studied using SwapMix: a co-attention model MCAN and a large-scale pretrained model LXMERT. Our experiments on the popular GQA dataset show the effectiveness of SwapMix for both diagnosing model robustness, and regularizing the over-reliance on visual context.
-
We introduce UNIST, the first deep neural implicit model for general-purpose, unpaired shape-to-shape translation, in both 2D and 3D domains. Our model is built on autoencoding implicit fields, rather than point clouds which represents the state of the art. Furthermore, our translation network is trained to perform the task over a latent grid representation which combines the merits of both latent-space processing and position awareness, to not only enable drastic shape transforms but also well preserve spatial features and fine local details for natural shape translations. With the same network architecture and only dictated by the input domain pairs, our model can learn both style-preserving content alteration and content-preserving style transfer. We demonstrate the generality and quality of the translation results, and compare them to well-known baselines. Code is available at https://qiminchen.github.io/unist/.
-
Due to the rising concern of data privacy, it's reasonable to assume the local client data can't be transferred to a centralized server, nor their associated identity label is provided. To support continuous learning and fill the last-mile quality gap, we introduce a new problem setup called Local-Adaptive Face Recognition (LaFR). Leveraging the environment-specific local data after the deployment of the initial global model, LaFR aims at getting optimal performance by training local-adapted models automatically and un-supervisely, as opposed to fixing their initial global model. We achieve this by a newly proposed embedding cluster model based on Graph Convolution Network (GCN), which is trained via meta-optimization procedure. Compared with previous works, our meta-clustering model can generalize well in unseen local environments. With the pseudo identity labels from the clustering results, we further introduce novel regularization techniques to improve the model adaptation performance. Extensive experiments on racial and internal sensor adaptation demonstrate that our proposed solution is more effective for adapting face recognition models in each specific environment. Meanwhile, we show that LaFR can further improve the global model by a simple federated aggregation over the updated local models.
-
Quantitative evaluation has increased dramatically among recent video inpainting work, but the video and mask content used to gauge performance has received relatively little attention. Although attributes such as camera and background scene motion inherently change the difficulty of the task and affect methods differently, existing evaluation schemes fail to control for them, thereby providing minimal insight into inpainting failure modes. To address this gap, we propose the Diagnostic Evaluation of Video Inpainting on Landscapes (DEVIL) benchmark, which consists of two contributions: (i) a novel dataset of videos and masks labeled according to several key inpainting failure modes, and (ii) an evaluation scheme that samples slices of the dataset characterized by a fixed content attribute, and scores performance on each slice according to reconstruction, realism, and temporal consistency quality. By revealing systematic changes in performance induced by particular characteristics of the input content, our challenging benchmark enables more insightful analysis into video inpainting methods and serves as an invaluable diagnostic tool for the field. Our code and data are available at github.com/MichiganCOG/devil.
-
Pan-sharpening aims to integrate the complementary information of texture-rich PAN images and multi-spectral (MS) images to produce the texture-rich MS images. Despite the remarkable progress, existing state-of-the-art Pan-sharpening methods don't explicitly enforce the complementary information learning between two modalities of PAN and MS images. This leads to information redundancy not being handled well, which further limits the performance of these methods. To address the above issue, we propose a novel mutual information-driven Pan-sharpening framework in this paper. To be specific, we first project the PAN and MS image into modality-aware feature space independently, and then impose the mutual information minimization over them to explicitly encourage the complementary information learning. Such operation is capable of reducing the information redundancy and improving the model performance. Extensive experimental results over multiple satellite datasets demonstrate that the proposed algorithm outperforms other state-of-the-art methods qualitatively and quantitatively with great generalization ability to real-world scenes.
-
Visual grounding focuses on establishing fine-grained alignment between vision and natural language, which has essential applications in multimodal reasoning systems. Existing methods use pre-trained query-agnostic visual backbones to extract visual feature maps independently without considering the query information. We argue that the visual features extracted from the visual backbones and the features really needed for multimodal reasoning are inconsistent. One reason is that there are differences between pre-training tasks and visual grounding. Moreover, since the backbones are query-agnostic, it is difficult to completely avoid the inconsistency issue by training the visual backbone end-to-end in the visual grounding framework. In this paper, we propose a Query-modulated Refinement Network (QRNet) to address the inconsistent issue by adjusting intermediate features in the visual backbone with a novel Query-aware Dynamic Attention (QD-ATT) mechanism and query-aware multiscale fusion. The QD-ATT can dynamically compute query-dependent visual attention at the spatial and channel level of the feature maps produced by the visual backbone. We apply the QRNet to an end-to-end visual grounding framework. Extensive experiments show that the proposed method outperforms state-of-the-art methods on five widely used datasets.
-
Self-explaining deep models are designed to learn the latent concept-based explanations implicitly during training, which eliminates the requirement of any post-hoc explanation generation technique. In this work, we propose one such model that appends an explanation generation module on top of any basic network and jointly trains the whole module that shows high predictive performance and generates meaningful explanations in terms of concepts. Our training strategy is suitable for unsupervised concept learning with much lesser parameter space requirements compared to baseline methods. Our proposed model also has provision for leveraging self-supervision on concepts to extract better explanations. However, with full concept supervision, we achieve the best predictive performance compared to recently proposed concept-based explainable models. We report both qualitative and quantitative results with our method, which shows better performance than recently proposed concept-based explainability methods. We reported exhaustive results with two datasets without ground truth concepts, i.e., CIFAR10, ImageNet, and two datasets with ground truth concepts, i.e., AwA2, CUB-200, to show the effectiveness of our method for both cases. To the best of our knowledge, we are the first ante-hoc explanation generation method to show results with a large-scale dataset such as ImageNet.
-
Evaluating and improving planning for autonomous vehicles requires scalable generation of long-tail traffic scenarios. To be useful, these scenarios must be realistic and challenging, but not impossible to drive through safely. In this work, we introduce STRIVE, a method to automatically generate challenging scenarios that cause a given planner to produce undesirable behavior, like collisions. To maintain scenario plausibility, the key idea is to leverage a learned model of traffic motion in the form of a graph-based conditional VAE. Scenario generation is formulated as an optimization in the latent space of this traffic model, perturbing an initial real-world scene to produce trajectories that collide with a given planner. A subsequent optimization is used to find a "solution" to the scenario, ensuring it is useful to improve the given planner. Further analysis clusters generated scenarios based on collision type. We attack two planners and show that STRIVE successfully generates realistic, challenging scenarios in both cases. We additionally "close the loop" and use these scenarios to optimize hyperparameters of a rule-based planner.
-
Multi-object multi-part scene parsing is a challenging task which requires detecting multiple object classes in a scene and segmenting the semantic parts within each object. In this paper, we propose FLOAT, a factorized label space framework for scalable multi-object multi-part parsing. Our framework involves independent dense prediction of object category and part attributes which increases scalability and reduces task complexity compared to the monolithic label space counterpart. In addition, we propose an inference-time 'zoom' refinement technique which significantly improves segmentation quality, especially for smaller objects/parts. Compared to state of the art, FLOAT obtains an absolute improvement of 2.0% for mean IOU (mIOU) and 4.8% for segmentation quality IOU (sqIOU) on the Pascal-Part-58 dataset. For the larger Pascal-Part-108 dataset, the improvements are 2.1% for mIOU and 3.9% for sqIOU. We incorporate previously excluded part attributes and other minor parts of the Pascal-Part dataset to create the most comprehensive and challenging version which we dub Pascal-Part-201. FLOAT obtains improvements of 8.6% for mIOU and 7.5% for sqIOU on the new dataset, demonstrating its parsing effectiveness across a challenging diversity of objects and parts. The code and datasets are available at floatseg.github.io.
-
Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations that are not 3D-consistent; the former limits quality and resolution of the generated images and the latter adversely affects multi-view consistency and shape quality. In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations. We introduce an expressive hybrid explicit-implicit network architecture that, together with other design choices, synthesizes not only high-resolution multi-view-consistent images in real time but also produces high-quality 3D geometry. By decoupling feature generation and neural rendering, our framework is able to leverage state-of-the-art 2D CNN generators, such as StyleGAN2, and inherit their efficiency and expressiveness. We demonstrate state-of-the-art 3D-aware synthesis with FFHQ and AFHQ Cats, among other experiments.
-
In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. Training GANs is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as GANs have a large-scale strategy space. In DO-GAN, we extend the double oracle framework to GANs. We first generalize the players' strategies as the trained models of generator and discriminator from the best response oracles. We then compute the meta-strategies using a linear program. For scalability of the framework where multiple generators and discriminator best responses are stored in the memory, we propose two solutions: 1) pruning the weakly-dominated players' strategies to keep the oracles from becoming intractable; 2) applying continual learning to retain the previous knowledge of the networks. We apply our framework to established GAN architectures such as vanilla GAN, Deep Convolutional GAN, Spectral Normalization GAN and Stacked GAN. Finally, we conduct experiments on MNIST, CIFAR-10 and CelebA datasets and show that DO-GAN variants have significant improvements in both subjective qualitative evaluation and quantitative metrics, compared with their respective GAN architectures.
-
Imaging in low light is extremely challenging due to low photon counts. Using sensitive CMOS cameras, it is currently possible to take videos at night under moonlight (0.05-0.3 lux illumination). In this paper, we demonstrate photorealistic video under starlight (no moon present, <0.001 lux) for the first time. To enable this, we develop a GAN-tuned physics-based noise model to more accurately represent camera noise at the lowest light levels. Using this noise model, we train a video denoiser using a combination of simulated noisy video clips and real noisy still images. We capture a 5-10 fps video dataset with significant motion at approximately 0.6-0.7 millilux with no active illumination. Comparing against alternative methods, we achieve improved video quality at the lowest light levels, demonstrating photorealistic video denoising in starlight for the first time.
-
Interactive image segmentation is an essential tool in pixel-level annotation and image editing. To obtain a high-precision binary segmentation mask, users tend to add interaction clicks around the object details, such as edges and holes, for efficient refinement. Current methods regard these repair clicks as the guidance to jointly determine the global prediction. However, the global view makes the model lose focus from later clicks, and is not in line with user intentions. In this paper, we dive into the view of clicks' eyes to endow them with the decisive role in object details again. To verify the necessity of focus view, we design a simple yet effective pipeline, named FocusCut, which integrates the functions of object segmentation and local refinement. After obtaining the global prediction, it crops click-centered patches from the original image with adaptive scopes to refine the local predictions progressively. Without user perception and parameters increase, our method has achieved state-of-the-art results. Extensive experiments and visualized results demonstrate that FocusCut makes hyper-fine segmentation possible for interactive image segmentation.
-
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects represented by surface meshes, their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral coordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to isometric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
-
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes suboptimal for learning spatio-temporally fine-grained features in videos, where scenes and instances evolve through space and time. In this paper, we present Contextualized Spatio-Temporal Contrastive Learning (ConST-CL) to effectively learn spatio-temporally fine-grained video representations via self-supervision. We first design a region-based pretext task which requires the model to transform instance representations from one view to another, guided by context features. Further, we introduce a simple network design that successfully reconciles the simultaneous learning process of both holistic and local representations. We evaluate our learned representations on a variety of downstream tasks and show that ConST-CL achieves competitive results on 6 datasets, including Kinetics, UCF, HMDB, AVAKinetics, AVA and OTB. Our code and models will be available.
-
Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental challenges such as the lack of convergence and the potential for catastrophic forgetting across real-world heterogeneous devices. In this paper, we demonstrate that self-attention-based architectures (e.g., Transformers) are more robust to distribution shifts and hence improve federated learning over heterogeneous data. Concretely, we conduct the first rigorous empirical investigation of different neural architectures across a range of federated algorithms, real-world benchmarks, and heterogeneous data splits. Our experiments show that simply replacing convolutional networks with Transformers can greatly reduce catastrophic forgetting of previous devices, accelerate convergence, and reach a better global model, especially when dealing with heterogeneous data. We will release our code and pretrained models to encourage future exploration in robust architectures as an alternative to current research efforts on the optimization front.
-
Rigged puppets are one of the most prevalent representations to create 2D character animations. Creating these puppets requires partitioning characters into independently moving parts. In this work, we present a method to automatically identify such articulated parts from a small set of character poses shown in a sprite sheet, which is an illustration of the character that artists often draw before puppet creation. Our method is trained to infer articulated parts, e.g. head, torso and limbs, that can be re-assembled to best reconstruct the given poses. Our results demonstrate significantly better performance than alternatives qualitatively and quantitatively. Our project page https://zhan-xu.github.io/parts/ includes our code and data.
-
While significant progress has been made in garment transfer, one of the most applicable directions of human-centric image generation, existing works overlook the in-the-wild imagery, presenting severe garment-person misalignment as well as noticeable degradation in fine texture details. This paper, therefore, attends to virtual try-on in real-world scenes and brings essential improvements in authenticity and naturalness especially for loose garment (e.g., skirts, formal dresses), challenging poses (e.g., cross arms, bent legs), and cluttered backgrounds. Specifically, we find that the pixel flow excels at handling loose garments whereas the vertex flow is preferred for hard poses, and by combining their advantages we propose a novel generative network called wFlow that can effectively push up garment transfer to in-the-wild context. Moreover, former approaches require paired images for training. Instead, we cut down the laboriousness by working on a newly constructed large-scale video dataset named Dance50k with self-supervised cross-frame training and an online cycle optimization. The proposed Dance50k can boost real-world virtual dressing by covering a wide variety of garments under dancing poses. Extensive experiments demonstrate the superiority of our wFlow in generating realistic garment transfer results for in-the-wild images without resorting to expensive paired datasets.
-
Visual private information leakage is an emerging key issue for the fast growing applications of video understanding like activity recognition. Existing approaches for mitigating privacy leakage in action recognition require privacy labels along with the action labels from the video dataset. However, annotating frames of video dataset for privacy labels is not feasible. Recent developments of self-supervised learning (SSL) have unleashed the untapped potential of the unlabeled data. For the first time, we present a novel training framework which removes privacy information from input video in a self-supervised manner without requiring privacy labels. Our training framework consists of three main components: anonymization function, self-supervised privacy removal branch, and action recognition branch. We train our framework using a minimax optimization strategy to minimize the action recognition cost function and maximize the privacy cost function through a contrastive self-supervised loss. Employing existing protocols of known-action and privacy attributes, our framework achieves a competitive action-privacy trade-off to the existing state-of-the-art supervised methods. In addition, we introduce a new protocol to evaluate the generalization of learned the anonymization function to novel-action and privacy attributes and show that our self-supervised framework outperforms existing supervised methods. Code available at: https://github.com/DAVEISHAN/SPAct
-
As RGB-D sensors become more affordable, using RGB-D images to obtain high-accuracy 6D pose estimation results becomes a better option. State-of-the-art approaches typically use different backbones to extract features for RGB and depth images. They use a 2D CNN for RGB images and a per-pixel point cloud network for depth data, as well as a fusion network for feature fusion. We find that the essential reason for using two independent backbones is the "projection breakdown" problem. In the depth image plane, the projected 3D structure of the physical world is preserved by the 1D depth value and its built-in 2D pixel coordinate (UV). Any spatial transformation that modifies UV, such as resize, flip, crop, or pooling operations in the CNN pipeline, breaks the binding between the pixel value and UV coordinate. As a consequence, the 3D structure is no longer preserved by a modified depth image or feature. To address this issue, we propose a simple yet effective method denoted as Uni6D that explicitly takes the extra UV data along with RGB-D images as input. Our method has a Unified CNN framework for 6D pose estimation with a single CNN backbone. In particular, the architecture of our method is based on Mask R-CNN with two extra heads, one named RT head for directly predicting 6D pose and the other named abc head for guiding the network to map the visible points to their coordinates in the 3D model as an auxiliary module. This end-to-end approach balances simplicity and accuracy, achieving comparable accuracy with state of the arts and 7.2x faster inference speed on the YCB-Video dataset.
-
With increasing focus on augmented and virtual reality applications (XR) comes the demand for algorithms that can lift objects from images and videos into representations that are suitable for a wide variety of related 3D tasks. Large-scale deployment of XR devices and applications means that we cannot solely rely on supervised learning, as collecting and annotating data for the unlimited variety of objects in the real world is infeasible. We present a weakly supervised method that is able to decompose a single image of an object into shape (depth and normals), material (albedo, reflectivity and shininess) and global lighting parameters. For training, the method only relies on a rough initial shape estimate of the training objects to bootstrap the learning process. This shape supervision can come for example from a pretrained depth network or - more generically - from a traditional structure-from-motion pipeline. In our experiments, we show that the method can successfully de-render 2D images into a decomposed 3D representation and generalizes to unseen object categories. Since in-the-wild evaluation is difficult due to the lack of ground truth data, we also introduce a photo-realistic synthetic test set that allows for quantitative evaluation. Please find our project page at: https://github.com/Brummi/derender3d
-
Parametric 3D models have formed a fundamental role in modeling deformable objects, such as human bodies, faces, and hands; however, the construction of such parametric models requires significant manual intervention and domain expertise. Recently, neural implicit 3D representations have shown great expressibility in capturing 3D shape geometry. We observe that deformable object motion is often semantically structured, and thus propose to learn Structured-implicit PArametric Models (SPAMs) as a deformable object representation that structurally decomposes non-rigid object motion into part-based disentangled representations of shape and pose, with each being represented by deep implicit functions. This enables a structured characterization of object movement, with part decomposition characterizing a lower-dimensional space in which we can establish coarse motion correspondence. In particular, we can leverage the part decompositions at test time to fit to new depth sequences of unobserved shapes, by establishing part correspondences between the input observation and our learned part spaces; this guides a robust joint optimization between the shape and pose of all parts, even under dramatic motion sequences. Experiments demonstrate that our part-aware shape and pose understanding lead to state-of-the-art performance in reconstruction and tracking of depth sequences of complex deforming object motion.
-
Recently, deep network-based image compressed sensing methods achieved high reconstruction quality and reduced computational overhead compared with traditional methods. However, existing methods obtain measurements only from partial features in the network and use it only once for image reconstruction. They ignore there are low, mid, and high-level features in the network and all of them are essential for high-quality reconstruction. Moreover, using measurements only once may not be enough for extracting richer information from measurements. To address these issues, we propose a novel Measurements Reuse Convolutional Compressed Sensing Network (MR-CCSNet) which employs Global Sensing Module (GSM) to collect all level features for achieving an efficient sensing and Measurements Reuse Block (MRB) to reuse measurements multiple times on multi-scale. Finally, we conduct a series of experiments on three benchmark datasets to show that our model can significantly outperform state-of-the-art methods. Code is available at https://github.com/fze0012/MR-CCSNet.
-
Auxiliary loss is additional loss besides the main branch loss to help optimize the learning process of neural networks. In order to calculate the auxiliary loss between the feature maps of intermediate layers and the ground truth in the field of semantic segmentation, the size of each feature map must match the ground truth. In all studies using the auxiliary losses with the segmentation models, from what we have investigated, they either use a down-sampling function to reduce the size of the ground truth or use an up-sampling function to increase the size of the feature map in order to match the resolution between the feature map and the ground truth. However, in the process of selecting representative values through down-sampling and up-sampling, information loss is inevitable. In this paper, we introduce Class Probability Preserving (CPP) pooling to alleviate information loss in down-sampling the ground truth in semantic segmentation tasks. We demonstrated the superiority of the proposed method on Cityscapes, Pascal VOC, Pascal Context, and NYU-Depth-v2 datasets by using CPP pooling with auxiliary losses based on seven popular segmentation models. In addition, we propose See-Through Network (SeeThroughNet) that adopts an improved multi-scale attention-coupled decoder structure to maximize the effect of CPP pooling. SeeThroughNet shows cutting-edge results in the field of semantic understanding of urban street scenes, which ranked #1 on the Cityscapes benchmark.
-
Differentiable rendering is an essential operation in modern vision, allowing inverse graphics approaches to 3D understanding to be utilized in modern machine learning frameworks. Yet, explicit shape representations (e.g., voxels, point clouds, meshes), while relatively easily rendered, often suffer from limited geometric fidelity or topological constraints. On the other hand, implicit representations (e.g., occupancy, distance, or radiance fields) preserve greater fidelity, but suffer from complex or inefficient rendering processes, limiting scalability. In this work, we endeavour to address both shortcomings with a novel shape representation that allows fast differentiable rendering within an implicit architecture. Building on implicit distance representations, we define Directed Distance Fields (DDFs), which map an oriented point (position and direction) to surface visibility and depth. Such a field can render a depth map with a single forward pass per pixel, enable differential surface geometry extraction (e.g., surface normals and curvatures) via network derivatives, can be easily composed, and permit extraction of classical unsigned distance fields. Using probabilistic DDFs (PDDFs), we show how to model inherent discontinuities in the underlying field. Finally, we apply our method to fitting single shapes, unpaired 3D-aware generative image modelling, and single-image 3D reconstruction tasks, showcasing strong performance with simple architectural components via the versatility of our representation.
-
Representational learning forms the backbone of most deep learning applications, and the value of a learned representation is intimately tied to its information content regarding different factors of variation. Finding good representations depends on the nature of supervision and the learning algorithm. We propose a novel algorithm that utilizes a weak form of supervision where the data is partitioned into sets according to certain inactive (common) factors of variation which are invariant across elements of each set. Our key insight is that by seeking correspondence between elements of different sets, we learn strong representations that exclude the inactive factors of variation and isolate the active factors that vary within all sets. As a consequence of focusing on the active factors, our method can leverage a mix of set-supervised and wholly unsupervised data, which can even belong to a different domain. We tackle the challenging problem of synthetic-to-real object pose transfer, without pose annotations on anything, by isolating pose information which generalizes to the category level and across the synthetic/real domain gap. The method can also boost performance in supervised settings, by strengthening intermediate representations, as well as operate in practically attainable scenarios with set-supervised natural images, where quantity is limited and nuisance factors of variation are more plentiful.
-
We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects. We derive challenging benchmarks that exploit the unique properties of ABO and measure the current limits of the state-of-the-art on three open problems for real-world 3D object understanding: single-view 3D reconstruction, material estimation, and cross-domain multi-view object retrieval.
-
Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method that pretrains the entire object detection network, including the object localization and embedding components. During pretraining, DETReg predicts object localizations to match the localizations from an unsupervised region proposal generator and simultaneously aligns the corresponding feature embeddings with embeddings from a self-supervised image encoder. We implement DETReg using the DETR family of detectors and show that it improves over competitive baselines when finetuned on COCO, PASCAL VOC, and Airbus Ship benchmarks. In low-data regimes, including semi-supervised and few-shot learning settings, DETReg establishes many state-of-the-art results, e.g., on COCO we see a +6.0 AP improvement for 10-shot detection and +3.5 AP improvement when training with only 1% of the labels.
-
In-the-wild 3D face modelling is a challenging problem as the predicted facial geometry and texture suffer from a lack of reliable clues or priors, when the input images are degraded. To address such a problem, in this paper we propose a novel Learning to Restore (L2R) 3D face framework for unsupervised high-quality face reconstruction from low-resolution images. Rather than directly refining 2D image appearance, L2R learns to recover fine-grained 3D details on the proxy against degradation via extracting generative facial priors. Concretely, L2R proposes a novel albedo restoration network to model high-quality 3D facial texture, in which the diverse guidance from the pre-trained Generative Adversarial Networks (GANs) is leveraged to complement the lack of input facial clues. With the finer details of the restored 3D texture, L2R then learns displacement maps from scratch to enhance the significant facial structure and geometry. Both of the procedures are mutually optimized with a novel 3D-aware adversarial loss, which further improves the modelling performance and suppresses the potential uncertainty. Extensive experiments on benchmarks show that L2R outperforms state-of-the-art methods under the condition of low-quality inputs, and obtains superior performances than 2D pre-processed modelling approaches with limited 3D proxy.
-
Defense models against adversarial attacks have grown significantly, but the lack of practical evaluation methods has hindered progress. Evaluation can be defined as looking for defense models' lower bound of robustness given a budget number of iterations and a test dataset. A practical evaluation method should be convenient (i.e., parameter-free), efficient (i.e., fewer iterations) and reliable (i.e., approaching the lower bound of robustness). Towards this target, we propose a parameter-free Adaptive Auto Attack (A3) evaluation method which addresses the efficiency and reliability in a test-time-training fashion. Specifically, by observing that adversarial examples to a specific defense model follow some regularities in their starting points, we design an Adaptive Direction Initialization strategy to speed up the evaluation. Furthermore, to approach the lower bound of robustness under the budget number of iterations, we propose an online statistics-based discarding strategy that automatically identifies and abandons hard-to-attack images. Extensive experiments on nearly 50 widely-used defense models demonstrate the effectiveness of our A3.By consuming much fewer iterations than existing methods, i.e., 1/10 on average (10x speed up), we achieve lower robust accuracy in all cases. Notably, we won first place out of 1681 teams in CVPR 2021 White-box Adversarial Attacks on Defense Models competitions with this method. Code is available at: https://github.com/liuye6666/adaptive_auto_attack
-
In many different fields interactions between objects play a critical role in determining their behavior. Graph neural networks (GNNs) have emerged as a powerful tool for modeling interactions, although often at the cost of adding considerable complexity and latency. In this paper, we consider the problem of spatial interaction modeling in the context of predicting the motion of actors around autonomous vehicles, and investigate alternatives to GNNs. We revisit 2D convolutions and show that they can demonstrate comparable performance to graph networks in modeling spatial interactions with lower latency, thus providing an effective and efficient alternative in time-critical systems. Moreover, we propose a novel interaction loss to further improve the interaction modeling of the considered methods.
-
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. The temporal relation is complex in those datasets, including challenges like composite action, and co-occurring action. For detecting actions in those complex videos, efficiently capturing both short-term and long-term temporal information in the video is critical. To this end, we propose a novel ConvTransformer network for action detection. This network comprises three main components: (1) Temporal Encoder module extensively explores global and local temporal relations at multiple temporal resolutions. (2) Temporal Scale Mixer module effectively fuses the multi-scale features to have a unified feature representation. (3) Classification module is used to learn the instance center-relative position and predict the frame-level classification scores. The extensive experiments on multiple datasets, including Charades, TSU and MultiTHUMOS, confirm the effectiveness of our proposed method. Our network outperforms the state-of-the-art methods on all the three datasets.
-
Weakly supervised object detection (WSOD) has recently attracted much attention. However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD. To bridge the performance and technical gaps between WSOD and FSOD, this paper proposes a new framework, Salvage of Supervision (SoS), with the key idea being to harness every potentially useful supervisory signal in WSOD: the weak image-level labels, the pseudo-labels, and the power of semi-supervised object detection. This paper shows that each type of supervisory signal brings in notable improvements, outperforms existing WSOD methods (which mainly use only the weak labels) by large margins. The proposed SoS-WSOD method also have the ability to freely use modern FSOD techniques. SoS-WSOD achieves 64.4 mAP50 on VOC2007, 61.9 mAP50 on VOC2012 and 16.6 mAP50:95 on MS-COCO, and also has fast inference speed. Ablations and visualization further verify the effectiveness of SoS.
-
We present cross-view transformers, an efficient attention-based model for map-view semantic segmentation from multiple cameras. Our architecture implicitly learns a mapping from individual camera views into a canonical map-view representation using a camera-aware cross-view attention mechanism. Each camera uses positional embeddings that depend on its intrinsic and extrinsic calibration. These embeddings allow a transformer to learn the mapping across different views without ever explicitly modeling it geometrically. The architecture consists of a convolutional image encoder for each view and cross-view transformer layers to infer a map-view semantic segmentation. Our model is simple, easily parallelizable, and runs in real-time. The presented architecture performs at state-of-the-art on the nuScenes dataset, with 4x faster inference speeds. Code is available at https://github.com/bradyz/cross_view_transformers.
-
Generalized zero-shot learning (GZSL) aims to recognize samples whose categories may not have been seen at training. Recognizing unseen classes as seen ones or vice versa often leads to poor performance in GZSL. Therefore, distinguishing seen and unseen domains is naturally an effective yet challenging solution for GZSL. In this paper, we present a novel method which leverages both visual and semantic modalities to distinguish seen and unseen categories. Specifically, our method deploys two variational autoencoders to generate latent representations for visual and semantic modalities in a shared latent space, in which we align latent representations of both modalities by Wasserstein distance and reconstruct two modalities with the representations of each other. In order to learn a clearer boundary between seen and unseen classes, we propose a two-stage training strategy which takes advantage of seen and unseen semantic descriptions and searches a threshold to separate seen and unseen visual samples. At last, a seen expert and an unseen expert are used for final classification. Extensive experiments on five widely used benchmarks verify that the proposed method can significantly improve the results of GZSL. For instance, our method correctly recognizes more than 99% samples when separating domains and improves the final classification accuracy from 72.6% to 82.9% on AWA1.
-
Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. Large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning scenarios under noisy data streams are yet underexplored. We consider a more practical CL setup of an online learning from blurry data stream with corrupted noise, where existing CL methods struggle. To address the task, we first argue the importance of both diversity and purity of examples in the episodic memory of continual learning models. To balance diversity and purity in the episodic memory, we propose a novel strategy to manage and use the memory by a unified approach of label noise aware diverse sampling and robust learning with semi-supervised learning. Our empirical validations on four real-world or synthetic benchmark datasets (CIFAR10 and 100, mini-WebVision, and Food-101N) show that our method significantly outperforms prior arts in this realistic and challenging continual learning scenario.
-
Multi-task learning commonly encounters competition for resources among tasks, specifically when model capacity is limited. This challenge motivates models which allow control over the relative importance of tasks and total compute cost during inference time. In this work, we propose such a controllable multi-task network that dynamically adjusts its architecture and weights to match the desired task preference as well as the resource constraints. In contrast to the existing dynamic multi-task approaches that adjust only the weights within a fixed architecture, our approach affords the flexibility to dynamically control the total computational cost and match the user-preferred task importance better. We propose a disentangled training of two hypernetworks, by exploiting task affinity and a novel branching regularized loss, to take input preferences and accordingly predict tree-structured models with adapted weights. Experiments on three multi-task benchmarks, namely PASCAL-Context, NYU-v2, and CIFAR-100, show the efficacy of our approach. Project page is available at https://www.nec-labs.com/ mas/DYMU.
-
Deep neural network (DNN) suffers from catastrophic forgetting when learning incrementally, which greatly limits its applications. Although maintaining a handful of samples (called "exemplars") of each task could alleviate forgetting to some extent, existing methods are still limited by the small number of exemplars since these exemplars are too few to carry enough task-specific knowledge, and therefore the forgetting remains. To overcome this problem, we propose to "imagine" diverse counterparts of given exemplars referring to the abundant semantic-irrelevant information from unlabeled data. Specifically, we develop a learnable feature generator to diversify exemplars by adaptively generating diverse counterparts of exemplars based on semantic information from exemplars and semantically-irrelevant information from unlabeled data. We introduce semantic contrastive learning to enforce the generated samples to be semantic consistent with exemplars and perform semanticdecoupling contrastive learning to encourage diversity of generated samples. The diverse generated samples could effectively prevent DNN from forgetting when learning new tasks. Our method does not bring any extra inference cost and outperforms state-of-the-art methods on two benchmarks CIFAR-100 and ImageNet-Subset by a clear margin.
-
Several recent works seek to create lightweight deep networks for video object detection on mobiles. We observe that many existing detectors, previously deemed computationally costly for mobiles, intrinsically support adaptive inference, and offer a multi-branch object detection framework (MBODF). Here, an MBODF is referred to as a solution that has many execution branches and one can dynamically choose from among them at inference time to satisfy varying latency requirements (e.g. by varying resolution of an input frame). In this paper, we ask, and answer, the wide-ranging question across all MBODFs: How to expose the right set of execution branches and then how to schedule the optimal one at inference time? In addition, we uncover the importance of making a content-aware decision on which branch to run, as the optimal one is conditioned on the video content. Finally, we explore a content-aware scheduler, an Oracle one, and then a practical one, leveraging various lightweight feature extractors. Our evaluation shows that layered on Faster R-CNN-based MBODF, compared to 7 baselines, our SMARTADAPT achieves a higher Pareto optimal curve in the accuracy-vs-latency space for the ILSVRC VID dataset.
-
Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. However, fine-tuning the entire parameter set of pre-trained models becomes impractical since the model size is growing rapidly. Hence, in this paper, we introduce adapter-based parameter-efficient transfer learning techniques to V&L models such as VL-BART and VL-T5. We evaluate our methods in a unified multi-task setup on both image-text and video-text benchmarks. For the image-text tasks, we use four diverse V&L datasets: VQAv2, GQA, NLVR2, and MSCOCO image captioning. For video-text tasks, we use TVQA, How2QA, TVC, and YC2C. With careful training and thorough experiments, we benchmark three popular adapter-based methods (Adapter, Hyperformer, Compacter) against the standard full fine-tuning and the recently proposed prompt-tuning approach. We also enhance the efficiency and performance of adapters by sharing their weights to attain knowledge across tasks. Our results demonstrate that training the adapter with the weight-sharing technique (4.18% of total parameters for image-text tasks and 3.39% for video-text tasks) can match the performance of fine-tuning the entire model. Lastly, we present a comprehensive analysis including the combination of adapter and task-specific prompts and the impact of V&L pre-training on adapters.
-
We propose a principled and practical method for out-of-distribution (OoD) detection with deep hybrid models (DHMs), which model the joint density p(x,y) of features and labels with a single forward pass. By factorizing the joint density p(x,y) into three sources of uncertainty, we show that our approach has the ability to identify samples semantically different from the training data. To ensure computational scalability, we add a weight normalization step during training, which enables us to plug in state-of-the-art (SoTA) deep neural network (DNN) architectures for approximately modeling and inferring expressive probability distributions. Our method provides an efficient, general, and flexible framework for predictive uncertainty estimation with promising results and theoretical support. To our knowledge, this is the first work to reach 100% in OoD detection tasks on both vision and language datasets, especially on notably difficult dataset pairs such as CIFAR-10 vs. SVHN and CIFAR-100 vs. CIFAR-10. This work is a step towards enabling DNNs in real-world deployment for safety-critical applications.
-
We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream. Specifically, we propose a motion vector-based warping method for propagating segmentation masks from keyframes to other frames in a bi-directional and multi-hop manner. Additionally, we introduce a residual-based correction module that can fix wrongly propagated segmentation masks from noisy or erroneous motion vectors. Our approach is flexible and can be added on top of several existing video object segmentation algorithms. We achieved highly competitive results on DAVIS17 and YouTube-VOS on various base models with substantial speed-ups of up to 3.5X with minor drops in accuracy.
-
Source-free domain adaptation (SFDA) newly emerges to transfer the relevant knowledge of a well-trained source model to an unlabeled target domain, which is critical in various privacy-preserving scenarios. Most existing methods focus on learning the domain-invariant representations depending solely on the target data, leading to the obtained representations are target-specific. In this way, they cannot fully address the distribution shift problem across domains. In contrast, we provide a fascinating insight: rather than attempting to learn domain-invariant representations, it is better to explore the domain-invariant parameters of the source model. The motivation behind this insight is clear: the domain-invariant representations are dominated by only partial parameters of an available deep source model. We devise the Domain-Invariant Parameter Exploring (DIPE) approach to capture such domain-invariant parameters in the source model to generate domain-invariant representations. A distinguishing method is developed correspondingly for two types of parameters, i.e., domain-invariant and domain-specific parameters, as well as an effective update strategy based on the clustering correction technique and a target hypothesis is proposed. Extensive experiments verify that DIPE successfully exceeds the current state-of-the-art models on many domain adaptation datasets.
-
We present a massively parallel Lagrange decomposition method for solving 0--1 integer linear programs occurring in structured prediction. We propose a new iterative update scheme for solving the Lagrangean dual and a perturbation technique for decoding primal solutions. For representing subproblems we follow Lange et al. (2021) and use binary decision diagrams (BDDs). Our primal and dual algorithms require little synchronization between subproblems and optimization over BDDs needs only elementary operations without complicated control flow. This allows us to exploit the parallelism offered by GPUs for all components of our method. We present experimental results on combinatorial problems from MAP inference for Markov Random Fields, quadratic assignment and cell tracking for developmental biology. Our highly parallel GPU implementation improves upon the running times of the algorithms from Lange et al. (2021) by up to an order of magnitude. In particular, we come close to or outperform some state-of-the-art specialized heuristics while being problem agnostic. Our implementation is available at https://github.com/LPMP/BDD.
-
Dynamic model pruning is a recent direction that allows for the inference of a different sub-network for each input sample during deployment. However, current dynamic methods rely on learning a continuous channel gating through regularization by inducing sparsity loss. This formulation introduces complexity in balancing different losses (e.g task loss, regularization loss). In addition, regularization based methods lack transparent tradeoff hyperparameter selection to realize computational budget. Our contribution is two-fold: 1) decoupled task and pruning training. 2) Simple hyperparameter selection that enables FLOPs reduction estimation before training. Inspired by the Hebbian theory in Neuroscience: "neurons that fire together wire together", we propose to predict a mask to process k filters in a layer based on the activation of its previous layer. We pose the problem as a self-supervised binary classification problem. Each mask predictor module is trained to predict if the log-likelihood for each filter in the current layer belongs to the top-k activated filters. The value k is dynamically estimated for each input based on a novel criterion using the mass of heatmaps. We show experiments on several neural architectures, such as VGG, ResNet and MobileNet on CIFAR and ImageNet datasets. On CIFAR, we reach similar accuracy to SOTA methods with 15% and 24% higher FLOPs reduction. Similarly in ImageNet, we achieve lower drop in accuracy with up to 13% improvement in FLOPs reduction.
-
Deep learning-based image salient object detection (SOD) heavily relies on large-scale training data with pixel-wise labeling. High-quality labels involve intensive labor and are expensive to acquire. In this paper, we propose a novel multi-source uncertainty mining method to facilitate unsupervised deep learning from multiple noisy labels generated by traditional handcrafted SOD methods. We design an Uncertainty Mining Network (UMNet) which consists of multiple Merge-and-Split (MS) modules to recursively analyze the commonality and difference among multiple noisy labels and infer pixel-wise uncertainty map for each label. Meanwhile, we model the noisy labels using Gibbs distribution and propose a weighted uncertainty loss to jointly train the UMNet with the SOD network. As a consequence, our UMNet can adaptively select reliable labels for SOD network learning. Extensive experiments on benchmark datasets demonstrate that our method not only outperforms existing unsupervised methods, but also is on par with fully-supervised state-of-the-art models.
-
Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based methods for keypoint detection rely on standard translation-equivariant CNNs but often fail to detect reliable keypoints against geometric variations. To learn to detect robust oriented keypoints, we introduce a self-supervised learning framework using rotation-equivariant CNNs. We propose a dense orientation alignment loss by an image pair generated by synthetic transformations for training a histogram-based orientation map. Our method outperforms the previous methods on an image matching benchmark and a camera pose estimation benchmark.
-
Remarkable achievements have been attained with Generative Adversarial Networks (GANs) in image-to-image translation. However, due to a tremendous amount of parameters, state-of-the-art GANs usually suffer from low efficiency and bulky memory usage. To tackle this challenge, firstly, this paper investigates GANs performance from a frequency perspective. The results show that GANs, especially small GANs lack the ability to generate high-quality high frequency information. To address this problem, we propose a novel knowledge distillation method referred to as wavelet knowledge distillation. Instead of directly distilling the generated images of teachers, wavelet knowledge distillation first decomposes the images into different frequency bands with discrete wavelet transformation and then only distills the high frequency bands. As a result, the student GAN can pay more attention to its learning on high frequency bands. Experiments demonstrate that our method leads to 7.08X compression and 6.80X acceleration on CycleGAN with almost no performance drop. Additionally, we have studied the relation between discriminators and generators which shows that the compression of discriminators can promote the performance of compressed generators.
-
Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object detection, the features of the teacher and student vary greatly in different areas, especially in the foreground and background. If we distill them equally, the uneven differences between feature maps will negatively affect the distillation. Thus, we propose Focal and Global Distillation (FGD). Focal distillation separates the foreground and background, forcing the student to focus on the teacher's critical pixels and channels. Global distillation rebuilds the relation between different pixels and transfers it from teachers to students, compensating for missing global information in focal distillation. As our method only needs to calculate the loss on the feature map, FGD can be applied to various detectors. We experiment on various detectors with different backbones and the results show that the student detector achieves excellent mAP improvement. For example, ResNet-50 based RetinaNet, Faster RCNN, RepPoints and Mask RCNN with our distillation method achieve 40.7%, 42.0%, 42.0% and 42.1% mAP on COCO2017, which are 3.3, 3.6, 3.4 and 2.9 higher than the baseline, respectively. Our codes are available at https://github.com/yzd-v/FGD.
-
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task identity at test time to retrieve learned knowledge and address forgetting, while this work presents a new paradigm for continual learning that aims to train a more succinct memory system without accessing task identity at test time. Our method learns to dynamically prompt (L2P) a pre-trained model to learn tasks sequentially under different task transitions. In our proposed framework, prompts are small learnable parameters, which are maintained in a memory space. The objective is to optimize prompts to instruct the model prediction and explicitly manage task-invariant and task-specific knowledge while maintaining model plasticity. We conduct comprehensive experiments under popular image classification benchmarks with different challenging continual learning settings, where L2P consistently outperforms prior state-of-the-art methods. Surprisingly, L2P achieves competitive results against rehearsal-based methods even without a rehearsal buffer and is directly applicable to challenging task-agnostic continual learning. Source code is available at https://github.com/google-research/l2p.
-
Videos from edited media like movies are a useful, yet under-explored source of information, with rich variety of appearance and interactions between humans depicted over a large temporal context. However, the richness of data comes at the expense of fundamental challenges such as abrupt shot changes and close up shots of actors with heavy truncation, which limits the applicability of existing 3D human understanding methods. In this paper, we address these limitations with the insight that while shot changes of the same scene incur a discontinuity between frames, the 3D structure of the scene still changes smoothly. This allows us to handle frames before and after the shot change as multi-view signal that provide strong cues to recover the 3D state of the actors. We propose a multi-shot optimization framework that realizes this insight, leading to improved 3D reconstruction and mining of sequences with pseudo-ground truth 3D human mesh. We treat this data as valuable supervision for models that enable human mesh recovery from movies; both from single image and from video, where we propose a transformer-based temporal encoder that can naturally handle missing observations due to shot changes in the input frames. We demonstrate the importance of our insight and proposed models through extensive experiments. The tools we develop open the door to processing and analyzing in 3D content from a large library of edited media, which could be helpful for many downstream applications. Code, models and data are available at: https://geopavlakos.github.io/multishot/
-
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. It is thus imperative to devise effective attack algorithms to identify the deficiencies of DNNs beforehand in security-sensitive applications. To efficiently tackle the black-box setting where the target model's particulars are unknown, feature-level transfer-based attacks propose to contaminate the intermediate feature outputs of local models, and then directly employ the crafted adversarial samples to attack the target model. Due to the transferability of features, feature-level attacks have shown promise in synthesizing more transferable adversarial samples. However, existing feature-level attacks generally employ inaccurate neuron importance estimations, which deteriorates their transferability. To overcome such pitfalls, in this paper, we propose the Neuron Attribution-based Attack (NAA), which conducts feature-level attacks with more accurate neuron importance estimations. Specifically, we first completely attribute a model's output to each neuron in a middle layer. We then derive an approximation scheme of neuron attribution to tremendously reduce the computation overhead. Finally, we weight neurons based on their attribution results and launch feature-level attacks. Extensive experiments confirm the superiority of our approach to the state-of-the-art benchmarks.
-
Backdoor attacks aim to cause misclassification of a subject model by stamping a trigger to inputs. Backdoors could be injected through malicious training and naturally exist. Deriving backdoor trigger for a subject model is critical to both attack and defense. A popular trigger inversion method is by optimization. Existing methods are based on finding a smallest trigger that can uniformly flip a set of input samples by minimizing a mask. The mask defines the set of pixels that ought to be perturbed. We develop a new optimization method that directly minimizes individual pixel changes, without using a mask. Our experiments show that compared to existing methods, the new one can generate triggers that require a smaller number of input pixels to be perturbed, have a higher attack success rate, and are more robust. They are hence more desirable when used in real-world attacks and more effective when used in defense. Our method is also more cost-effective.
-
Segmenting an image into its parts is a frequent preprocess for high-level vision tasks such as image editing. However, annotating masks for supervised training is expensive. Weakly-supervised and unsupervised methods exist, but they depend on the comparison of pairs of images, such as from multi-views, frames of videos, and image augmentation, which limits their applicability. To address this, we propose a GAN-based approach that generates images conditioned on latent masks, thereby alleviating full or weak annotations required in previous approaches. We show that such mask-conditioned image generation can be learned faithfully when conditioning the masks in a hierarchical manner on latent keypoints that define the position of parts explicitly. Without requiring supervision of masks or points, this strategy increases robustness to viewpoint and object positions changes. It also lets us generate image-mask pairs for training a segmentation network, which outperforms the state-of-the-art unsupervised segmentation methods on established benchmarks.
-
The ultimate goal of semi-supervised object detection (SSOD) is to facilitate the utilization and deployment of detectors in actual applications with the help of a large amount of unlabeled data. Although a few works have proposed various self-training-based methods or consistency-regularization-based methods, they all target anchor-based detectors, while ignoring the dependency on anchor-free detectors of the actual industrial deployment. To this end, in this paper, we intend to bridge the gap on anchor-free SSOD algorithm by proposing a DenSe Learning (DSL) based algorithm for SSOD. It is mainly achieved by introducing several novel techniques, including (1) Adaptive Ignoring strategy with MetaNet for assigning multi-level and accurate dense pixel-wise pseudo-labels, (2) Aggregated Teacher for producing stable and precise pseudo-labels, and (3) uncertainty consistency regularization among scales and shuffled patches for improving the generalization of the detector. In order to verify the effectiveness of our proposed method, extensive experiments have been conducted over the popular datasets MS-COCO [??] and PASCAL-VOC [??], achieving state-of-the-art performances. Codes will be available at \textcolor[rgb] 1,0,0 xxxxxxxxx .
-
This paper studies the problem of fixing malfunctional 3D objects. While previous works focus on building passive perception models to learn the functionality from static 3D objects, we argue that functionality is reckoned with respect to the physical interactions between the object and the user. Given a malfunctional object, humans can perform mental simulations to reason about its functionality and figure out how to fix it. Inspired by this, we propose FixIt, a dataset that contains around 5k poorly-designed 3D physical objects paired with choices to fix them. To mimic humans' mental simulation process, we present FixNet, a novel framework that seamlessly incorporates perception and physical dynamics. Specifically, FixNet consists of a perception module to extract the structured representation from the 3D point cloud, a physical dynamics prediction module to simulate the results of interactions on 3D objects, and a functionality prediction module to evaluate the functionality and choose the correct fix. Experimental results show that our framework outperforms baseline models by a large margin, and can generalize well to objects with similar interaction types. We will release our code and dataset.
-
In the biological visual pathway, especially the retina, neurons are tiled along spatial dimensions with the electrical coupling as their local association, while in a convolution layer, kernels are placed along the channel dimension singly. We propose Convolution of Convolution, associating kernels in a layer and letting them collaborate spatially. With this method, a layer can provide feature maps with extra transformations and learn its kernels together instead of isolatedly. It is only used during training, bringing in negligible extra costs; and can be re-parameterized to common convolution before testing, boosting performance gratuitously in tasks like classification, detection and segmentation. Our method works even better when large receptive fields are demanded. The code is available on site: https://github.com/Genera1Z/ConvolutionOfConvolution.
-
Generating controllable videos conforming to user intentions is an appealing yet challenging topic in computer vision. To enable maneuverable control in line with user intentions, a novel video generation task, named Text-Image-to-Video generation (TI2V), is proposed. With both controllable appearance and motion, TI2V aims at generating videos from a static image and a text description. The key challenges of TI2V task lie both in aligning appearance and motion from different modalities, and in handling uncertainty in text descriptions. To address these challenges, we propose a Motion Anchor-based video GEnerator (MAGE) with an innovative motion anchor (MA) structure to store appearance-motion aligned representation. To model the uncertainty and increase the diversity, it further allows the injection of explicit condition and implicit randomness. Through three-dimensional axial transformers, MA is interacted with given image to generate next frames recursively with satisfying controllability and diversity. Accompanying the new task, we build two new video-text paired datasets based on MNIST and CATER for evaluation. Experiments conducted on these datasets verify the effectiveness of MAGE and show appealing potentials of TI2V task. Code and datasets are released at https://github.com/Youncy-Hu/MAGE.
-
Long-tail object detection suffers from poor performance on tail categories. We reveal that the real culprit lies in the extremely imbalanced distribution of the classifier's weight norm. For conventional softmax cross-entropy loss, such imbalanced weight norm distribution yields ill conditioned decision boundary for categories which have small weight norms. To get rid of this situation, we choose to maximize the cosine similarity between the learned feature and the weight vector of target category rather than the inner-product of them. The decision boundary between any two categories is the angular bisector of their weight vectors. Whereas, the absolutely equal decision boundary is suboptimal because it reduces the model's sensitivity to various categories. Intuitively, categories with rich data diversity should occupy a larger area in the classification space while categories with limited data diversity should occupy a slightly small space. Hence, we devise a Category-Aware Angular Margin Loss (C2AM Loss) to introduce an adaptive angular margin between any two categories. Specifically, the margin between two categories is proportional to the ratio of their classifiers' weight norms. As a result, the decision boundary is slightly pushed towards the category which has a smaller weight norm. We conduct comprehensive experiments on LVIS dataset. C2AM Loss brings 4.9 5.2 AP improvements on different detectors and backbones compared with baseline.
-
In this paper, we propose Neural Points, a novel point cloud representation and apply it to the arbitrary-factored upsampling task. Different from traditional point cloud representation where each point only represents a position or a local plane in the 3D space, each point in Neural Points represents a local continuous geometric shape via neural fields. Therefore, Neural Points contain more shape information and thus have a stronger representation ability. Neural Points is trained with surface containing rich geometric details, such that the trained model has enough expression ability for various shapes. Specifically, we extract deep local features on the points and construct neural fields through the local isomorphism between the 2D parametric domain and the 3D local patch. In the final, local neural fields are integrated together to form the global surface. Experimental results show that Neural Points has powerful representation ability and demonstrate excellent robustness and generalization ability. With Neural Points, we can resample point cloud with arbitrary resolutions, and it outperforms the state-of-the-art point cloud upsampling methods. Code is available at https://github.com/WanquanF/NeuralPoints.
-
Recent progress on neural architecture search (NAS) has demonstrated exciting results on automating deep network architecture designs. In order to overcome the unaffordable complexity of training each candidate architecture from scratch, the state-of-the-art one-shot NAS approaches adopt a weight-sharing strategy to improve training efficiency. Although the computational cost is greatly reduced, such one-shot process introduces a severe weight coupling problem that largely degrades the evaluation accuracy of each candidate. The existing approaches often address the problem by shrinking the search space, model distillation, or few-shot training. Instead, in this paper, we propose a novel distribution consistent one-shot neural architecture search algorithm. We first theoretically investigate how the weight coupling problem affects the network searching performance from a parameter distribution perspective, and then propose a novel supernet training strategy with a Distribution Consistent Constraint that can provide a good measurement for the extent to which two architectures can share weights. Our strategy optimizes the supernet through iteratively inferring network weights and corresponding local sharing states. Such joint optimization of supernet's weights and topologies can diminish the discrepancy between the weights inherited from the supernet and the ones that are trained with a stand-alone model. As a result, it enables a more accurate model evaluation phase and leads to a better searching performance. We conduct extensive experiments on benchmark datasets with multiple searching spaces. The resulting architecture achieves superior performance over the current state-of-the-art NAS algorithms with comparable search costs, which demonstrates the efficacy of our approach.
-
Learning generic joint representations for video and text by a supervised method requires a prohibitively substantial amount of manually annotated video datasets. As a practical alternative, a large-scale but uncurated and narrated video dataset, HowTo100M, has recently been introduced. But it is still challenging to learn joint embeddings of video and text in a self-supervised manner, due to its ambiguity and non-sequential alignment. In this paper, we propose a novel multi-modal self-supervised framework Video-Text Temporally Weak Alignment-based Contrastive Learning (VT-TWINS) to capture significant information from noisy and weakly correlated data using a variant of Dynamic Time Warping (DTW). We observe that the standard DTW inherently cannot handle weakly correlated data and only considers the globally optimal alignment path. To address these problems, we develop a differentiable DTW which also reflects local information with weak temporal alignment. Moreover, our proposed model applies a contrastive learning scheme to learn feature representations on weakly correlated data. Our extensive experiments demonstrate that VT-TWINS attains significant improvements in multi-modal representation learning and outperforms various challenging downstream tasks. Code is available at https://github.com/mlvlab/VT-TWINS.
-
The saliency ranking task is recently proposed to study the visual behavior that humans would typically shift their attention over different objects of a scene based on their degrees of saliency. Existing approaches focus on learning either object-object or object-scene relations. Such a strategy follows the idea of object-based attention in Psychology, but it tends to favor those objects with strong semantics (e.g., humans), resulting in unrealistic saliency ranking. We observe that spatial attention works concurrently with object-based attention in the human visual recognition system. During the recognition process, the human spatial attention mechanism would move, engage, and disengage from region to region (i.e., context to context). This inspires us to model the region-level interactions, in addition to the object-level reasoning, for saliency ranking. To this end, we propose a novel bi-directional method to unify spatial attention and object-based attention for saliency ranking. Our model includes two novel modules: (1) a selective object saliency (SOS) module that models object-based attention via inferring the semantic representation of the salient object, and (2) an object-context-object relation (OCOR) module that allocates saliency ranks to objects by jointly modeling the object-context and context-object interactions of the salient objects. Extensive experiments show that our approach outperforms existing state-of-the-art methods. Code and pretrained model are available at https://github.com/GrassBro/OCOR.
-
Instance segmentation is a fundamental vision task that aims to recognize and segment each object in an image. However, it requires costly annotations such as bounding boxes and segmentation masks for learning. In this work, we propose a fully unsupervised learning method that learns class-agnostic instance segmentation without any annotations. We present FreeSOLO, a self-supervised instance segmentation framework built on top of the simple instance segmentation method SOLO. Our method also presents a novel localization-aware pre-training framework, where objects can be discovered from complicated scenes in an unsupervised manner. FreeSOLO achieves 9.8% AP50 on the challenging COCO dataset, which even outperforms several segmentation proposal methods that use manual annotations. For the first time, we demonstrate unsupervised class-agnostic instance segmentation successfully. FreeSOLO's box localization significantly outperforms state-of-the-art unsupervised object detection/discovery methods, with about 100% relative improvements in COCO AP. FreeSOLO further demonstrates superiority as a strong pre-training method, outperforming state-of-the-art self-supervised pre-training methods by +9.8% AP when fine-tuning instance segmentation with only 5% COCO masks.
-
Today's state of the art visual navigation agents typically consist of large deep learning architectures trained end to end. Such models offer little to no interpretability about the skills learned by the agent or the actions taken by it in response to its environment. While past works have explored interpreting deep learning models, little attention has been devoted to interpreting embodied AI systems, which often involve reasoning about the structure of the environment, target characteristics and the outcome of one's actions. In this paper, we introduce the Interpretability System for Embodied agEnts (iSEE) for Point Goal (PointNav) and Object Goal (ObjectNav) navigation models. We use iSEE to probe the dynamic representations produced by PointNav and ObjectNav agents for the presence of information about their agents location and actions, as well as the environment. We demonstrate interesting insights about navigation agents using iSEE, including the ability to encode reachable locations (to avoid obstacles), visibility of the target, progress from the initial spawn location as well as the dramatic effect on the behaviors of agents when we mask out critical individual neurons.
-
We propose Path-CNN, a method for the segmentation of centerlines of tubular structures by embedding convolutional neural networks (CNNs) into the progressive minimal path method. Minimal path methods are widely used for topology-aware centerline segmentation, but usually these methods rely on weak, hand-tuned image features. In contrast, CNNs use strong image features which are learned automatically from images. But CNNs usually do not take the topology of the results into account, and often require a large amount of annotations for training. We integrate CNNs into the minimal path method, so that both techniques benefit from each other: CNNs employ learned image features to improve the determination of minimal paths, while the minimal path method ensures the correct topology of the segmented centerlines, provides strong geometric priors to increase the performance of CNNs, and reduces the amount of annotations for the training of CNNs significantly. Our method has lower hardware requirements than many recent methods. Qualitative and quantitative comparison with other methods shows that Path-CNN achieves better performance, especially when dealing with tubular structures with complex shapes in challenging environments.
-
Robust visual recognition under adverse weather conditions is of great importance in real-world applications. In this context, we propose a new method for learning semantic segmentation models robust against fog. Its key idea is to consider the fog condition of an image as its style and close the gap between images with different fog conditions in neural style spaces of a segmentation model. In particular, since the neural style of an image is in general affected by other factors as well as fog, we introduce a fog-pass filter module that learns to extract a fog-relevant factor from the style. Optimizing the fog-pass filter and the segmentation model alternately gradually closes the style gap between different fog conditions and allows to learn fog-invariant features in consequence. Our method substantially outperforms previous work on three real foggy image datasets. Moreover, it improves performance on both foggy and clear weather images, while existing methods often degrade performance on clear scenes.
-
3D face reconstruction from a single image is a task that has garnered increased interest in the Computer Vision community, especially due to its broad use in a number of applications such as realistic 3D avatar creation, pose invariant face recognition and face hallucination. Since the introduction of the 3D Morphable Model in the late 90's, we witnessed an explosion of research aiming at particularly tackling this task. Nevertheless, despite the increasing level of detail in the 3D face reconstructions from single images mainly attributed to deep learning advances, finer and highly deformable components of the face such as the tongue are still absent from all 3D face models in the literature, although being very important for the realness of the 3D avatar representations. In this work we present the first, to the best of our knowledge, end-to-end trainable pipeline that accurately reconstructs the 3D face together with the tongue. Moreover, we make this pipeline robust in "in-the-wild" images by introducing a novel GAN method tailored for 3D tongue surface generation. Finally, we make publicly available to the community the first diverse tongue dataset, consisting of 1,800 raw scans of 700 individuals varying in gender, age, and ethnicity backgrounds. As we demonstrate in an extensive series of quantitative as well as qualitative experiments, our model proves to be robust and realistically captures the 3D tongue structure, even in adverse "in-the-wild" conditions.
-
Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the min-max adversarial training, but instead learn from a weak adversary inefficiently. Conversely, we propose Hardness Manipulation to efficiently perturb the training triplet till a specified level of hardness for adversarial training, according to a harder benign triplet or a pseudo-hardness function. It is flexible since regular training and min-max adversarial training are its boundary cases. Besides, Gradual Adversary, a family of pseudo-hardness functions is proposed to gradually increase the specified hardness level during training for a better balance between performance and robustness. Additionally, an Intra-Class Structure loss term among benign and adversarial examples further improves model robustness and efficiency. Comprehensive experimental results suggest that the proposed method, although simple in its form, overwhelmingly outperforms the state-of-the-art defenses in terms of robustness, training efficiency, as well as performance on benign examples.
-
Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale low-resolution representations, which makes dense prediction tasks such as semantic segmentation challenging for ViTs. Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs. We balance the model performance and efficiency of HRViT by various branch-block co-optimization techniques. Specifically, we explore heterogeneous branch designs, reduce the redundancy in linear layers, and augment the attention block with enhanced expressiveness. Those approaches enabled \ours to push the Pareto frontier of performance and efficiency on semantic segmentation to a new level, as our evaluation results on ADE20K and Cityscapes show. HRViT achieves 50.20% mIoU on ADE20K and 83.16% mIoU on Cityscapes for semantic segmentation tasks, surpassing state-of-the-art MiT and CSWin backbones with an average of +1.78 mIoU improvement, 28% parameter reduction, and 21% FLOPs reduction, demonstrating the potential of HRViT as a strong vision backbone for semantic segmentation.
-
Recent multi-modal detectors based on transformers and modality encoders have successfully achieved impressive results on end-to-end visual object detection conditioned on a raw text query. However, they require a large model size and an enormous amount of computations to achieve high performance, which makes it difficult to deploy mobile applications that are limited by tight hardware resources. In this paper, we present a Lightweight modulated detector, Lite-MDETR, to facilitate efficient end-to-end multi-modal understanding on mobile devices. The key primitive is that Dictionary-Lookup-Transformormations (DLT) is proposed to replace Linear Transformation (LT) in multi-modal detectors where each weight in Linear Transformation (LT) is approximately factorized into a smaller dictionary, index, and coefficient. This way, the enormous linear projection with weights is converted into lite linear projection with dictionaries, a few lookups and scalings with indices and coefficients. DLT can be directly applied to pre-trained detectors, removing the need to perform expensive training from scratch. To tackle the challenging training of DLT due to the non-differentiable index, we convert the index and coefficient into a sparse matrix, train this sparse matrix during the fine-tuning phase, and recover it back to index and coefficient during the inference phase. Extensive experiments on several tasks such as phrase grounding, referring expression comprehension and segmentation show that our Lite-MDETR achieves similar detection accuracy to the prior multi-modal detectors with ~ 4.1xmodel size reduction.
-
Recent advances show that Generative Adversarial Networks (GANs) can synthesize images with smooth variations along semantically meaningful latent directions, such as pose, expression, layout, etc. While this indicates that GANs implicitly learn pixel-level correspondences across images, few studies explored how to extract them explicitly. In this work, we introduce Coordinate GAN (CoordGAN), a structure-texture disentangled GAN that learns a dense correspondence map for each generated image. We represent the correspondence maps of different images as warped coordinate frames transformed from a canonical coordinate frame, i.e., the correspondence map, which describes the structure (e.g., the shape of a face), is controlled via a transformation. Hence, finding correspondences boils down to locating the same coordinate in different correspondence maps. In CoordGAN, we sample a transformation to represent the structure of a synthesized instance, while an independent texture branch is responsible for rendering appearance details orthogonal to the structure. Our approach can also extract dense correspondence maps for real images by adding an encoder on top of the generator. We quantitatively demonstrate the quality of the learned dense correspondences through segmentation mask transfer on multiple datasets. We also show that the proposed generator achieves better structure and texture disentanglement compared to existing approaches.
-
This paper proposes a simple transfer learning baseline for sign language translation. Existing sign language datasets (e.g. PHOENIX-2014T, CSL-Daily) contain only about 10K-20K pairs of sign videos, gloss annotations and texts, which are an order of magnitude smaller than typical parallel data for training spoken language translation models. Data is thus a bottleneck for training effective sign language translation models. To mitigate this problem, we propose to progressively pretrain the model from general-domain datasets that include a large amount of external supervision to within-domain datasets. Concretely, we pretrain the sign-to-gloss visual network on the general domain of human actions and the within-domain of a sign-to-gloss dataset, and pretrain the gloss-to-text translation network on the general domain of a multilingual corpus and the within-domain of a gloss-to-text corpus. The joint model is fine-tuned with an additional module named the visual-language mapper that connects the two networks. This simple baseline surpasses the previous state-of-the-art results on two sign language translation benchmarks, demonstrating the effectiveness of transfer learning. With its simplicity and strong performance, this approach can serve as a solid baseline for future research.
-
Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination. The main challenge resides in clustering since prevalent clustering methods (e.g., k-means) have to run in a batch mode. Besides, there can be a trivial solution consisting of a dominating cluster. To address these challenges, we first investigate the objective of clustering-based representation learning. Based on this, we propose a novel clustering-based pretext task with online Constrained K-means (CoKe). Compared with the balanced clustering that each cluster has exactly the same size, we only constrain the minimal size of each cluster to flexibly capture the inherent data structure. More importantly, our online assignment method has a theoretical guarantee to approach the global optimum. By decoupling clustering and discrimination, CoKe can achieve competitive performance when optimizing with only a single view from each instance. Extensive experiments on ImageNet and other benchmark data sets verify both the efficacy and efficiency of our proposal.
-
We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud. Combining differentiable volume rendering with learned implicit density representations has made it possible to synthesize photo-realistic images for novel views of small scenes. As neural volumetric rendering methods require dense sampling of the underlying functional scene representation, at hundreds of samples along a ray cast through the volume, they are fundamentally limited to small scenes with the same objects projected to hundreds of training views. Promoting sparse point clouds to neural implicit light fields allows us to represent large scenes effectively with only a single radiance evaluation per ray. These point light fields are as a function of the ray direction, and local point feature neighborhood, allowing us to interpolate the light field conditioned training images without dense object coverage and parallax. We assess the proposed method for novel view synthesis on large driving scenarios, where we synthesize realistic unseen views that existing implicit approaches fail to represent. We validate that Neural Point Light Fields make it possible to predict videos along unseen trajectories previously only feasible to generate by explicitly modeling the scene.
-
Vehicle trajectory prediction is nowadays a fundamental pillar of self-driving cars. Both the industry and research communities have acknowledged the need for such a pillar by providing public benchmarks. While state-of-the-art methods are impressive, i.e., they have no off-road prediction, their generalization to cities outside of the benchmark remains unexplored. In this work, we show that those methods do not generalize to new scenes. We present a novel method that automatically generates realistic scenes causing state-of-the-art models to go off-road. We frame the problem through the lens of adversarial scene generation. The method is a simple yet effective generative model based on atomic scene generation functions along with physical constraints. Our experiments show that more than 60% of existing scenes from the current benchmarks can be modified in a way to make prediction methods fail (i.e., predicting off-road). We further show that the generated scenes (i) are realistic since they do exist in the real world, and (ii) can be used to make existing models more robust, yielding 30-40% reductions in the off-road rate. The code is available online: https://s-attack.github.io/
-
In this paper, we propose a new deep learning-based method for estimating room layout given a pair of 360 panoramas. Our system, called Position-aware Stereo Merging Network or PSMNet, is an end-to-end joint layout-pose estimator. PSMNet consists of a Stereo Pano Pose (SP^2) transformer and a novel Cross-Perspective Projection (CP^2) layer. The stereo-view SP^2 transformer is used to implicitly infer correspondences between views, and can handle noisy poses. The pose-aware CP^2layer is designed to render features from the adjacent view to the anchor (reference) view, in order to perform view fusion and estimate the visible layout. Our experiments and analysis validate our method, which significantly outperforms the state-of-the-art layout estimators, especially for large and complex room spaces.
-
Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to assist 3D detection, but suffer from the additional computational burden and achieve limited performance caused by inaccurate depth priors. To alleviate this, we propose MonoDTR, a novel end-to-end depth-aware transformer network for monocular 3D object detection. It mainly consists of two components: (1) the Depth-Aware Feature Enhancement (DFE) module that implicitly learns depth-aware features with auxiliary supervision without requiring extra computation, and (2) the Depth-Aware Transformer (DTR) module that globally integrates context- and depth-aware features. Moreover, different from conventional pixel-wise positional encodings, we introduce a novel depth positional encoding (DPE) to inject depth positional hints into transformers. Our proposed depth-aware modules can be easily plugged into existing image-only monocular 3D object detectors to improve the performance. Extensive experiments on the KITTI dataset demonstrate that our approach outperforms previous state-of-the-art monocular-based methods and achieves real-time detection. Code is available at https://github.com/kuanchihhuang/MonoDTR.
-
We introduce a novel formulation for guided super-resolution. Its core is a differentiable optimisation layer that operates on a learned affinity graph. The learned graph potentials make it possible to leverage rich contextual information from the guide image, while the explicit graph optimisation within the architecture guarantees rigorous fidelity of the high-resolution target to the low-resolution source. With the decision to employ the source as a constraint rather than only as an input to the prediction, our method differs from state-of-the-art deep architectures for guided super-resolution, which produce targets that, when downsampled, will only approximately reproduce the source. This is not only theoretically appealing, but also produces crisper, more natural-looking images. A key property of our method is that, although the graph connectivity is restricted to the pixel lattice, the associated edge potentials are learned with a deep feature extractor and can encode rich context information over large receptive fields. By taking advantage of the sparse graph connectivity, it becomes possible to propagate gradients through the optimisation layer and learn the edge potentials from data. We extensively evaluate our method on several datasets, and consistently outperform recent baselines in terms of quantitative reconstruction errors, while also delivering visually sharper outputs. Moreover, we demonstrate that our method generalises particularly well to new datasets not seen during training.
-
In this paper, we introduce a new dataset, named InstaOrder, that can be used to understand the spatial relationships of instances in a 3D space. The dataset consists of 2.9M annotations of geometric orderings for class-labeled instances in 101K natural scenes. The scenes were annotated by 3,659 crowd-workers regarding (1) occlusion order that identifies occluder/occludee and (2) depth order that describes ordinal relations that consider relative distance from the camera. The dataset provides joint annotation of two kinds of orderings for the same instances, and we discover that the occlusion order and depth order are complementary. We also introduce a geometric order prediction network called InstaOrderNet, which is superior to state-of-the-art approaches. Moreover, we propose a dense depth prediction network called InstaDepthNet that uses auxiliary geometric order loss to boost the accuracy of the state-of-the-art depth prediction approach, MiDaS [54].
-
Human actions often induce changes of object states such as "cutting an apple", "cleaning shoes" or "pouring coffee". In this paper, we seek to temporally localize object states (e.g. "empty" and "full" cup) together with the corresponding state-modifying actions ("pouring coffee") in long uncurated videos with minimal supervision. The contributions of this work are threefold. First, we develop a self-supervised model for jointly learning state-modifying actions together with the corresponding object states from an uncurated set of videos from the Internet. The model is self-supervised by the causal ordering signal, i.e. initial object state -> manipulating action -> end state. Second, to cope with noisy uncurated training data, our model incorporates a noise adaptive weighting module supervised by a small number of annotated still images, that allows to efficiently filter out irrelevant videos during training. Third, we collect a new dataset with more than 2600 hours of video and 34 thousand changes of object states, and manually annotate a part of this data to validate our approach. Our results demonstrate substantial improvements over prior work in both action and object state-recognition in video.
-
This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a promising alternative to convolutional neural networks for visual recognition. But when there is no sufficient data, it gets stuck in overfitting and shows inferior performance. To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attribute surrogates. The intrinsic image structure is utilized to reduce the ambiguity between foreground content and background noise by spectral tokens pooling. And the attribute surrogate learning scheme is designed to benefit from the rich visual information in image-label pairs instead of simple visual concepts assigned by their labels. Our Hierarchically Cascaded Transformers, called HCTransformers, is built upon a self-supervised learning framework DINO and is tested on several popular few-shot learning benchmarks. In the inductive setting, HCTransformers surpass the DINO baseline by a large margin of 9.7% 5-way 1-shot accuracy and 9.17% 5-way 5-shot accuracy on mini-ImageNet, which demonstrates HCTransformers are efficient to extract discriminative features. Also, HCTransformers show clear advantages over SOTA few-shot classification methods in both 5-way 1-shot and 5-way 5-shot settings on four popular benchmark datasets, including mini-ImageNet, tiered-ImageNet, FC100, and CIFAR-FS. The trained weights and codes are available at https://github.com/StomachCold/HCTransformers.
-
In this paper, we consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set. Here, the unlabelled images may come from labelled classes or from novel ones. Existing recognition methods are not able to deal with this setting, because they make several restrictive assumptions, such as the unlabelled instances only coming from known -- or unknown -- classes, and the number of unknown classes being known a-priori. We address the more unconstrained setting, naming it 'Generalized Category Discovery', and challenge all these assumptions. We first establish strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task. Next, we propose the use of vision transformers with contrastive representation learning for this open-world setting. We then introduce a simple yet effective semi-supervised k-means method to cluster the unlabelled data into seen and unseen classes automatically, substantially outperforming the baselines. Finally, we also propose a new approach to estimate the number of classes in the unlabelled data. We thoroughly evaluate our approach on public datasets for generic object classification and on fine-grained datasets, leveraging the recent Semantic Shift Benchmark suite. Code: https://www.robots.ox.ac.uk/~vgg/research/gcd
-
Maximisation of Consensus (MaxCon) is one of the most widely used robust criteria in computer vision. Tennakoon et al. (CVPR2021), made a connection between MaxCon and estimation of influences of a Monotone Boolean function. In such, there are two distributions involved: the distribution defining the influence measure; and the distribution used for sampling to estimate the influence measure. This paper studies the concept of weighted influences for solving MaxCon. In particular, we study the Bernoulli measures. Theoretically, we prove the weighted influences, under this measure, of points belonging to larger structures are smaller than those of points belonging to smaller structures in general. We also consider another "natural" family of weighting strategies: sampling with uniform measure concentrated on a particular (Hamming) level of the cube. One can choose to have matching distributions: the same for defining the measure as for implementing the sampling. This has the advantage that the sampler is an unbiased estimator of the measure. Based on weighted sampling, we modify the algorithm of Tennakoon et al., and test on both synthetic and real datasets. We show some modest gains of Bernoulli sampling, and we illuminate some of the interactions between structure in data and weighted measures and weighted sampling.
-
Establishing correspondences between images remains a challenging task, especially under large appearance changes due to different viewpoints or intra-class variations. In this work, we introduce a strong semantic image matching learner, dubbed TransforMatcher, which builds on the success of transformer networks in vision domains. Unlike existing convolution- or attention-based schemes for correspondence, TransforMatcher performs global match-to-match attention for precise match localization and dynamic refinement. To handle a large number of matches in a dense correlation map, we develop a light-weight attention architecture to consider the global match-to-match interactions. We also propose to utilize a multi-channel correlation map for refinement, treating the multi-level scores as features instead of a single score to fully exploit the richer layer-wise semantics. In experiments, TransforMatcher sets a new state of the art on SPair-71k while performing on par with existing SOTA methods on the PF-PASCAL dataset.
-
Deep networks often make confident, yet, incorrect, predictions when tested with outlier data that is far removed from their training distributions. Likelihoods computed by deep generative models (DGMs) are a candidate metric for outlier detection with unlabeled data. Yet, previous studies have shown that DGM likelihoods are unreliable and can be easily biased by simple transformations to input data. Here, we examine outlier detection with variational autoencoders (VAEs), among the simplest of DGMs. We propose novel analytical and algorithmic approaches to ameliorate key biases with VAE likelihoods. Our bias corrections are sample-specific, computationally inexpensive, and readily computed for various decoder visible distributions. Next, we show that a well-known image pre-processing technique -- contrast stretching -- extends the effectiveness of bias correction to further improve outlier detection. Our approach achieves state-of-the-art accuracies with nine grayscale and natural image datasets, and demonstrates significant advantages -- both with speed and performance -- over four recent, competing approaches. In summary, lightweight remedies suffice to achieve robust outlier detection with VAEs.
-
We propose an effective and easy-to-implement method for simultaneously performing landmark detection in images and obtaining an ingenious uncertainty measurement for each landmark. Uncertainty measurements for landmarks are particularly useful in medical imaging applications: rather than giving an erroneous reading, a landmark detection system is more useful when it flags its level of confidence in its prediction. When an automated system is unsure of its predictions, the accuracy of the results can be further improved manually by a human. In the medical domain, being able to review an automated system's level of certainty significantly improves a clinician's trust in it. This paper obtains landmark predictions with uncertainty measurements using a three stage method: 1) We train our network on one-hot heatmap images, 2) We calibrate the uncertainty of the network using temperature scaling, 3) We calculate a novel statistic called 'Expected Radial Error' to obtain uncertainty measurements. We find that this method not only achieves localisation results on par with other state-of-the-art methods but also an uncertainty score which correlates with the true error for each landmark thereby bringing an overall step change in what a generic computer vision method for landmark detection should be capable of. In addition, we show that our uncertainty measurement can be used to classify, with good accuracy, what landmark predictions are likely to be inaccurate. Code available at: https://github.com/jfm15/ContourHuggingHeatmaps.git
-
In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion. The proposed approach aims to maintain cross-modality consistency by representing and fusing augmented image features as a ray in the voxel field. To this end, the learnable sampler is first designed to sample vital features from the image plane that are projected to the voxel grid in a point-to-ray manner, which maintains the consistency in feature representation with spatial context. In addition, ray-wise fusion is conducted to fuse features with the supplemental context in the constructed voxel field. We further develop mixed augmentor to align feature-variant transformations, which bridges the modality gap in data augmentation. The proposed framework is demonstrated to achieve consistent gains in various benchmarks and outperforms previous fusion-based methods on KITTI and nuScenes datasets. Code is made available at https://github.com/dvlab-research/VFF.
-
In response to the explosively-increasing requirement of annotated data, Novel Class Discovery (NCD) has emerged as a promising alternative to automatically recognize unknown classes without any annotation. To this end, a model makes use of a base set to learn basic semantic discriminability that can be transferred to recognize novel classes. Most existing works handle the base and novel sets using separate objectives within a two-stage training paradigm. Despite showing competitive performance on novel classes, they fail to generalize to recognizing samples from both base and novel sets. In this paper, we focus on this generalized setting of NCD (GNCD), and propose to divide and conquer it with two groups of Compositional Experts (ComEx). Each group of experts is designed to characterize the whole dataset in a comprehensive yet complementary fashion. With their union, we can solve GNCD in an efficient end-to-end manner. We further look into the drawback in current NCD methods, and propose to strengthen ComEx with global-to-local and local-to-local regularization. ComEx is evaluated on four popular benchmarks, showing clear superiority towards the goal of GNCD.
-
We introduce Programmatic Motion Concepts, a hierarchical motion representation for human actions that captures both low level motion and high level description as motion concepts. This representation enables human motion description, interactive editing, and controlled synthesis of novel video sequences within a single framework. We present an architecture that learns this concept representation from paired video and action sequences in a semi-supervised manner. The compactness of our representation also allows us to present a low-resource training recipe for data-efficient learning. By outperforming established baselines, especially in small data regime, we demonstrate the efficiency and effectiveness of our framework for multiple applications.
-
Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network response to a given input. This is directly related to the huge number of variables and the associated non-linearities of neural models, which are often used as black boxes. When it comes to critical applications as autonomous driving, security and safety, medicine and health, the lack of interpretability of the network behavior tends to induce skepticism and limited trustworthiness, despite the accurate performance of such systems in the given task. Furthermore, a single metric, such as the classification accuracy, provides a non-exhaustive evaluation of most real-world scenarios. In this paper, we want to make a step forward towards interpretability in neural networks, providing new tools to interpret their behavior. We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues and organizing the input distribution matching the conceptual-semantic hierarchical structure between classes. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, providing a more interpretable model than other state-of-the-art approaches.
-
Tensor completion using multiway delay-embedding transform (MDT) (or Hankelization) suffers from the large memory requirement and high computational cost in spite of its high potentiality for the image modeling. Recent studies have shown high completion performance with a relatively small window size, but experiments with large window sizes require huge amount of memory and cannot be easily calculated. In this study, we address this serious computational issue, and propose its fast and efficient algorithm. Key techniques of the proposed method are based on two properties: (1) the signal after MDT can be diagonalized by Fourier transform, (2) an inverse MDT can be represented as a convolutional form. To use the properties, we modify MDT-Tucker, a method using Tucker decomposition with MDT, and introducing the fast and efficient algorithm. Our experiments show more than 100 times acceleration while maintaining high accuracy, and to realize the computation with large window size.
-
This paper presents a novel framework to integrate both semantic and instance contexts for panoptic segmentation. In existing works, it is common to use a shared backbone to extract features for both things (countable classes such as vehicles) and stuff (uncountable classes such as roads). This, however, fails to capture the rich relations among them, which can be utilized to enhance visual understanding and segmentation performance. To address this shortcoming, we propose a novel Panoptic, Instance, and Semantic Relations (PISR) module to exploit such contexts. First, we generate panoptic encodings to summarize key features of the semantic classes and predicted instances. A Panoptic Relational Attention (PRA) module is then applied to the encodings and the global feature map from the backbone. It produces a feature map that captures 1) the relations across semantic classes and instances and 2) the relations between these panoptic categories and spatial features. PISR also automatically learns to focus on the more important instances, making it robust to the number of instances used in the relational attention module. Moreover, PISR is a general module that can be applied to any existing panoptic segmentation architecture. Through extensive evaluations on panoptic segmentation benchmarks like Cityscapes, COCO, and ADE20K, we show that PISR attains considerable improvements over existing approaches.
-
We present a simple and effective framework, named Point2Seq, for 3D object detection from point clouds. In contrast to previous methods that normally predict attributes of 3D objects all at once, we expressively model the interdependencies between attributes of 3D objects, which in turn enables a better detection accuracy. Specifically, we view each 3D object as a sequence of words and reformulate the 3D object detection task as decoding words from 3D scenes in an auto-regressive manner. We further propose a lightweight scene-to-sequence decoder that can auto-regressively generate words conditioned on features from a 3D scene as well as cues from the preceding words. The predicted words eventually constitute a set of sequences that completely describe the 3D objects in the scene, and all the predicted sequences are then automatically assigned to the respective ground truths through similarity-based sequence matching. Our approach is conceptually intuitive and can be readily plugged upon most existing 3D-detection backbones without adding too much computational overhead; the sequential decoding paradigm we proposed, on the other hand, can better exploit information from complex 3D scenes with the aid of preceding predicted words. Without bells and whistles, our method significantly outperforms the previous anchor- and center-based 3D object detection frameworks, yielding the new state-of-the-art on the challenging ONCE dataset as well as the Waymo Open Dataset. Code will be made publicly available.
-
We study the automatic generation of navigation instructions from 360-degree images captured on indoor routes. Existing generators suffer from poor visual grounding, causing them to rely on language priors and hallucinate objects. Our MARKY-MT5 system addresses this by focusing on visual landmarks; it comprises a first stage landmark detector and a second stage generator--a multimodal, multilingual, multitask encoder-decoder. To train it, we bootstrap grounded landmark annotations on top of the Room-across-Room (RxR) dataset. Using text parsers, weak supervision from RxR's pose traces, and a multilingual image-text encoder trained on 1.8b images, we identify 1.1m English, Hindi and Telugu landmark descriptions and ground them to specific regions in panoramas. On Room-to-Room, human wayfinders obtain success rates (SR) of 73% following MARKY-MT5's instructions, just shy of their 76% SR following human instructions---and well above SRs with other generators. Evaluations on RxR's longer, diverse paths obtain 62-64% SRs on three languages. Generating such high-quality navigation instructions in novel environments is a step towards conversational navigation tools and could facilitate larger-scale training of instruction-following agents.
-
We study the problem of few-shot open-set recognition (FSOR), which learns a recognition system capable of both fast adaptation to new classes with limited labeled examples and rejection of unknown negative samples. Traditional large-scale open-set methods have been shown ineffective for FSOR problem due to data limitation. Current FSOR methods typically calibrate few-shot closed-set classifiers to be sensitive to negative samples so that they can be rejected via thresholding. However, threshold tuning is a challenging process as different FSOR tasks may require different rejection powers. In this paper, we instead propose task-adaptive negative class envision for FSOR to integrate threshold tuning into the learning process. Specifically, we augment the few-shot closed-set classifier with additional negative prototypes generated from few-shot examples. By incorporating few-shot class correlations in the negative generation process, we are able to learn dynamic rejection boundaries for FSOR tasks. Besides, we extend our method to generalized few-shot open-set recognition (GFSOR), which requires classification on both many-shot and few-shot classes as well as rejection of negative samples. Extensive experiments on public benchmarks validate our methods on both problems.
-
We introduce Displacement Aware Relation Module (DisARM), a novel neural network module for enhancing the performance of 3D object detection in point cloud scenes. The core idea is extracting the most principal contextual information is critical for detection while the target is incomplete or featureless. We find that relations between proposals provide a good representation to describe the context. However, adopting relations between all the object or patch proposals for detection is inefficient, and an imbalanced combination of local and global relations brings extra noise that could mislead the training. Rather than working with all relations, we find that training with relations only between the most representative ones, or anchors, can significantly boost the detection performance. Good anchors should be semantic-aware with no ambiguity and able to describe the whole layout of a scene with no redundancy. To find the anchors, we first perform a preliminary relation anchor module with an objectness-aware sampling approach and then devise a displacement based module for weighing the relation importance for better utilization of contextual information. This light-weight relation module leads to significantly higher accuracy of object instance detection when being plugged into the state-of- the-art detectors. Evaluations on the public benchmarks of real-world scenes show that our method achieves the state-of-the-art performance on both SUN RGB-D and ScanNet V2. The code and models are publicly available at https://github.com/YaraDuan/DisARM.
-
Waste inspection for packaged waste is an important step in the pipeline of waste disposal. Previous methods either rely on manual visual checking or RGB image-based inspection algorithm, requiring costly preparation procedures (e.g., open the bag and spread the waste items). Moreover, occluded items are very likely to be left out. Inspired by the fact that X-ray has a strong penetrating power to see through the bag and overlapping objects, we propose to perform waste inspection efficiently using X-ray images without the need to open the bag. We introduce a novel problem of instance-level waste segmentation in X-ray image for intelligent waste inspection, and contribute a real dataset consisting of 5,038 X-ray images (totally 30,881 waste items) with high-quality annotations (i.e., waste categories, object boxes, and instance-level masks) as a benchmark for this problem. As existing segmentation methods are mainly designed for natural images and cannot take advantage of the characteristics of X-ray waste images (e.g., heavy occlusions and penetration effect), we propose a new instance segmentation method to explicitly take these image characteristics into account. Specifically, our method adopts an easy-to-hard disassembling strategy to use high confidence predictions to guide the segmentation of highly overlapped objects, and a global structure guidance module to better capture the complex contour information caused by the penetration effect. Extensive experiments demonstrate the effectiveness of the proposed method. Our dataset is released at WIXRayNet.
-
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We propose MixFormer to find a solution. First, we combine local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields. Second, we propose bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions. These two designs are integrated to achieve efficient feature mixing among windows and dimensions. Our MixFormer provides competitive results on image classification with EfficientNet and shows better results than RegNet and Swin Transformer. Performance in downstream tasks outperforms its alternatives by significant margins with less computational costs in 5 dense prediction tasks on MS COCO, ADE20k, and LVIS. Code is available at https://github.com/PaddlePaddle/PaddleClas.
-
Learning discriminative deep feature embeddings by using million-scale in-the-wild datasets and margin-based softmax loss is the current state-of-the-art approach for face recognition. However, the memory and computing cost of the Fully Connected (FC) layer linearly scales up to the number of identities in the training set. Besides, the large-scale training data inevitably suffers from inter-class conflict and long-tailed distribution. In this paper, we propose a sparsely updating variant of the FC layer, named Partial FC (PFC). In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss. All class centers are still maintained throughout the whole training process, but only a subset is selected and updated in each iteration. Therefore, the computing requirement, the probability of inter-class conflict, and the frequency of passive update on tail class centers, are dramatically reduced. Extensive experiments across different training data and backbones (e.g. CNN and ViT) confirm the effectiveness, robustness and efficiency of the proposed PFC.
-
Implicit neural rendering, especially Neural Radiance Field (NeRF), has shown great potential in novel view synthesis of a scene. However, current NeRF-based methods cannot enable users to perform user-controlled shape deformation in the scene. While existing works have proposed some approaches to modify the radiance field according to the user's constraints, the modification is limited to color editing or object translation and rotation. In this paper, we propose a method that allows users to perform controllable shape deformation on the implicit representation of the scene, and synthesizes the novel view images of the edited scene without re-training the network. Specifically, we establish a correspondence between the extracted explicit mesh representation and the implicit neural representation of the target scene. Users can first utilize well-developed mesh-based deformation methods to deform the mesh representation of the scene. Our method then utilizes user edits from the mesh representation to bend the camera rays by introducing a tetrahedra mesh as a proxy, obtaining the rendering results of the edited scene. Extensive experiments demonstrate that our framework can achieve ideal editing results not only on synthetic data, but also on real scenes captured by users.
-
Mean Average Precision (mAP) is the primary evaluation measure for object detection. Although object detection has a broad range of applications, mAP evaluates detectors in terms of the performance of ranked instance retrieval. Such the assumption for the evaluation task does not suit some downstream tasks. To alleviate the gap between downstream tasks and the evaluation scenario, we propose Optimal Correction Cost (OC-cost), which assesses detection accuracy at image level. OC-cost computes the cost of correcting detections to ground truths as a measure of accuracy. The cost is obtained by solving an optimal transportation problem between the detections and the ground truths. Unlike mAP, OC-cost is designed to penalize false positive and false negative detections properly, and every image in a dataset is treated equally. Our experimental result validates that OC-cost has better agreement with human preference than a ranking-based measure, i.e., mAP for a single image. We also show that detectors' rankings by OC-cost are more consistent on different data splits than mAP. Our goal is not to replace mAP with OC-cost but provide an additional tool to evaluate detectors from another aspect. To help future researchers and developers choose a target measure, we provide a series of experiments to clarify how mAP and OC-cost differ.
-
Asymmetric image retrieval, which typically uses small model for query side and large model for database server, is an effective solution for resource-constrained scenarios. However, existing approaches either fail to achieve feature coherence or make strong assumptions, e.g., requiring labeled datasets or classifiers from large model, etc., which limits their practical application. To this end, we propose a flexible contextual similarity distillation framework to enhance the small query model and keep its output feature compatible with that of large gallery model, which is crucial with asymmetric retrieval. In our approach, we learn the small model with a new contextual similarity consistency constraint without any data label. During the small model learning, it preserves the contextual similarity among each training image and its neighbors with the features extracted by the large model. Note that this simple constraint is consistent with simultaneous first-order feature vector preserving and second-order ranking list preserving. Extensive experiments show that the proposed method outperforms the state-of-the-art methods on the Revisited Oxford and Paris datasets.
-
Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability. We argue that understanding both high-level semantics and internal temporal structures of actions in competitive sports videos is the key to making predictions accurate and interpretable. Towards this goal, we construct a new fine-grained dataset, called FineDiving, developed on diverse diving events with detailed annotations on action procedures. We also propose a procedure-aware approach for action quality assessment, learned by a new Temporal Segmentation Attention module. Specifically, we propose to parse pairwise query and exemplar action instances into consecutive steps with diverse semantic and temporal correspondences. The procedure-aware cross-attention is proposed to learn embeddings between query and exemplar steps to discover their semantic, spatial, and temporal correspondences, and further serve for fine-grained contrastive regression to derive a reliable scoring mechanism. Extensive experiments demonstrate that our approach achieves substantial improvements over the state-of-the-art methods with better interpretability. The dataset and code are available at https://github.com/xujinglin/FineDiving.
-
Style transfer has been well studied in recent years with excellent performance processed. While existing methods usually choose CNNs as the powerful tool to accomplish superb stylization, less attention was paid to the latent style space. Rare exploration of underlying dimensions results in the poor style controllability and the limited practical application. In this work, we rethink the internal meaning of style features, further proposing a novel unsupervised algorithm for style discovery and achieving personalized manipulation. In particular, we take a closer look into the mechanism of style transfer and obtain different artistic style components from the latent space consisting of different style features. Then fresh styles can be generated by linear combination according to various style components. Experimental results have shown that our approach is superb in 1) restylizing the original output with the diverse artistic styles discovered from the latent space while keeping the content unchanged, and 2) being generic and compatible for various style transfer methods.
-
This paper presents a novel attention-based neural network for structured reconstruction, which takes a 2D raster image as an input and reconstructs a planar graph depicting an underlying geometric structure. The approach detects corners and classifies edge candidates between corners in an end-to-end manner. Our contribution is a holistic edge classification architecture, which 1) initializes the feature of an edge candidate by a trigonometric positional encoding of its end-points; 2) fuses image feature to each edge candidate by deformable attention; 3) employs two weight-sharing Transformer decoders to learn holistic structural patterns over the graph edge candidates; and 4) is trained with a masked learning strategy. The corner detector is a variant of the edge classification architecture, adapted to operate on pixels as corner candidates. We conduct experiments on two structured reconstruction tasks: outdoor building architecture and indoor floorplan planar graph reconstruction. Extensive qualitative and quantitative evaluations demonstrate the superiority of our approach over the state of the art. Code and pre-trained models are available at https://heat-structured-reconstruction.github.io
-
The inversion of real images into StyleGAN's latent space is a well-studied problem. Nevertheless, applying existing approaches to real-world scenarios remains an open challenge, due to an inherent trade-off between reconstruction and editability: latent space regions which can accurately represent real images typically suffer from degraded semantic control. Recent work proposes to mitigate this trade-off by fine-tuning the generator to add the target image to well-behaved, editable regions of the latent space. While promising, this fine-tuning scheme is impractical for prevalent use as it requires a lengthy training phase for each new image. In this work, we introduce this approach into the realm of encoder-based inversion. We propose HyperStyle, a hypernetwork that learns to modulate StyleGAN's weights to faithfully express a given image in editable regions of the latent space. A naive modulation approach would require training a hypernetwork with over three billion parameters. Through careful network design, we reduce this to be in line with existing encoders. HyperStyle yields reconstructions comparable to those of optimization techniques with the near real-time inference capabilities of encoders. Lastly, we demonstrate HyperStyle's effectiveness on several applications beyond the inversion task, including the editing of out-of-domain images which were never seen during training.
-
The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms of bias. We further introduce a novel semantic alignment loss to establish balanced feature representation to reduce the biased predictions from the classifier. We term the whole framework as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label. We conduct extensive experiments in a wide range of imbalanced benchmarks: CIFAR10/100-LT, STL10-LT, and large-scale long-tailed Semi-Aves with open-set class, and demonstrate that, the proposed DASO framework reliably improves SSL learners with unlabeled data especially when both (1) class imbalance and (2) distribution mismatch dominate.
-
We present Mobile-Former, a parallel design of MobileNet and transformer with a two-way bridge in between. This structure leverages the advantages of MobileNet at local processing and transformer at global interaction. And the bridge enables bidirectional fusion of local and global features. Different from recent works on vision transformer, the transformer in Mobile-Former contains very few tokens (e.g. 6 or fewer tokens) that are randomly initialized to learn global priors, resulting in low computational cost. Combining with the proposed light-weight cross attention to model the bridge, Mobile-Former is not only computationally efficient, but also has more representation power. It outperforms MobileNetV3 at low FLOP regime from 25M to 500M FLOPs on ImageNet classification. For instance, Mobile-Former achieves 77.9% top-1 accuracy at 294M FLOPs, gaining 1.3% over MobileNetV3 but saving 17% of computations. When transferring to object detection, Mobile-Former outperforms MobileNetV3 by 8.6 AP in RetinaNet framework. Furthermore, we build an efficient end-to-end detector by replacing backbone, encoder and decoder in DETR with Mobile-Former, which outperforms DETR by 1.3 AP but saves 52% of computational cost and 36% of parameters. Code will be released at https://github.com/aaboys/mobileformer.
-
We present a novel self-distillation based self-supervised monocular depth estimation (SD-SSMDE) learning framework. In the first step, our network is trained in a self-supervised regime on high-resolution images with the photometric loss. The network is further used to generate pseudo depth labels for all the images in the training set. To improve the performance of our estimates, in the second step, we re-train the network with the scale invariant logarithmic loss supervised by pseudo labels. We resolve scale ambiguity and inter-frame scale consistency by introducing an automatically computed scale in our depth labels. To filter out noisy depth values, we devise a filtering scheme based on the 3D consistency between consecutive views. Extensive experiments demonstrate that each proposed component and the self-supervised learning framework improve the quality of the depth estimation over the baseline and achieve state-of-the-art results on the KITTI and Cityscapes datasets.
-
Self- and cross-attention in Transformers provide for high model capacity, making them viable models for object detection. However, Transformers still lag in performance behind CNN-based detectors. This is, we believe, because: (a) Cross-attention is used for both classification and bounding-box regression tasks; (b) Transformer's decoder poorly initializes content queries; and (c) Self-attention poorly accounts for certain prior knowledge which could help improve inductive bias. These limitations are addressed with the corresponding three contributions. First, we propose a new Detection Split Transformer (DESTR) that separates estimation of cross-attention into two independent branches -- one tailored for classification and the other for box regression. Second, we use a mini-detector to initialize the content queries in the decoder with classification and regression embeddings of the respective heads in the mini-detector. Third, we augment self-attention in the decoder to additionally account for pairs of adjacent object queries. Our experiments on the MS-COCO dataset show that DESTR outperforms DETR and its successors.
-
The reasonable trajectory prediction of surrounding traffic participants is crucial for autonomous driving. Especially, how to predict multiple plausible trajectories is still a challenging problem because of the multiple possibilities of the future. Proposal-based prediction methods address the multi-modality issues with a two-stage approach, commonly using intention classification followed by motion regression. This paper proposes a two-stage proposal-based motion forecasting method that exploits the sliced lane segments as fine-grained, shareable, and interpretable proposals. We use Graph neural network and Transformer to encode the shape and interaction information among the map sub-graphs and the agents sub-graphs. In addition, we propose a variance-based non-maximum suppression strategy to select representative trajectories that ensure the diversity of the final output. Experiments on the Argoverse dataset show that the proposed method outperforms state-of-the-art methods, and the lane segments-based proposals as well as the variance-based non-maximum suppression strategy both contribute to the performance improvement. Moreover, we demonstrate that the proposed method can achieve reliable performance with a lower collision rate and fewer off-road scenarios in the closed-loop simulation.
-
Curating a large set of fully annotated training data can be costly, especially for the tasks of medical image segmentation. Scribble, a weaker form of annotation, is more obtainable in practice, but training segmentation models from limited supervision of scribbles is still challenging. To address the difficulties, we propose a new framework for scribble learning-based medical image segmentation, which is composed of mix augmentation and cycle consistency and thus is referred to as CycleMix. For augmentation of supervision, CycleMix adopts the mixup strategy with a dedicated design of random occlusion, to perform increments and decrements of scribbles. For regularization of supervision, CycleMix intensifies the training objective with consistency losses to penalize inconsistent segmentation, which results in significant improvement of segmentation performance. Results on two open datasets, i.e., ACDC and MSCMRseg, showed that the proposed method achieved exhilarating performance, demonstrating comparable or even better accuracy than the fully-supervised methods. The code and expert-made scribble annotations for MSCMRseg are publicly available at https://github.com/BWGZK/CycleMIx.
-
Videos typically record the streaming and continuous visual data as discrete consecutive frames. Since the storage cost is expensive for videos of high fidelity, most of them are stored in a relatively low resolution and frame rate. Recent works of Space-Time Video Super-Resolution (STVSR) are developed to incorporate temporal interpolation and spatial super-resolution in a unified framework. However, most of them only support a fixed up-sampling scale, which limits their flexibility and applications. In this work, instead of following the discrete representations, we propose Video Implicit Neural Representation (VideoINR), and we show its applications for STVSR. The learned implicit neural representation can be decoded to videos of arbitrary spatial resolution and frame rate. We show that VideoINR achieves competitive performances with state-of-the-art STVSR methods on common up-sampling scales and significantly outperforms prior works on continuous and out-of-training-distribution scales. Our project page is at http://zeyuan-chen.com/VideoINR/ and code is available at https://github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution.
-
Scene text detection and document layout analysis have long been treated as two separate tasks in different image domains. In this paper, we bring them together and introduce the task of unified scene text detection and layout analysis. The first hierarchical scene text dataset is introduced to enable this novel research task. We also propose a novel method that is able to simultaneously detect scene text and form text clusters in a unified way. Comprehensive experiments show that our unified model achieves better performance than multiple well-designed baseline methods. Additionally, this model achieves state-of-the-art results on multiple scene text detection datasets without the need of complex post-processing. Dataset and code: https://github.com/google-research-datasets/hiertext.
-
In this work, we present a solution to the challenging problem of reconstructing liquids from image data. The challenges in reconstructing liquids, which is not faced in previous reconstruction works on rigid and deforming surfaces, lies in the inability to use depth sensing and color features due the variable index of refraction, opacity, and environmental reflections. Therefore, we limit ourselves to only surface detections (i.e. binary mask) of liquids as observations and do not assume any prior knowledge on the liquids properties. A novel optimization problem is posed which reconstructs the liquid as particles by minimizing the error between a rendered surface from the particles and the surface detections while satisfying liquid constraints. Our solvers to this optimization problem are presented and no training data is required to apply them. We also propose a dynamic prediction to seed the reconstruction optimization from the previous time-step. We test our proposed methods in simulation and on two new liquid datasets which we open source so the broader research community can continue developing in this under explored area.
-
We study the problem of contextual outpainting, which aims to hallucinate the missing background contents based on the remaining foreground contents. Existing image outpainting methods focus on completing object shapes or extending existing scenery textures, neglecting the semantically meaningful relationship between the missing and remaining contents. To explore the semantic cues provided by the remaining foreground contents, we propose a novel ConTextual Outpainting GAN (CTO-GAN), leveraging the semantic layout as a bridge to synthesize coherent and diverse background contents. To model the contextual correlation between foreground and background contents, we incorporate an object-level contrastive loss to regularize the learning of cross-modal representations of foreground contents and the corresponding background semantic layout, facilitating accurate semantic reasoning. Furthermore, we improve the realism of the generated background contents via detecting generated context in adversarial training. Extensive experiments demonstrate that the proposed method achieves superior performance compared with existing solutions on the challenging COCO-stuff dataset.
-
Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical assumptions like pixel-wise independent noise. Hence, it is challenging to deal with spatially correlated real-world noise using self-supervised BSN. Recently, pixel-shuffle downsampling (PD) has been proposed to remove the spatial correlation of real-world noise. However, it is not trivial to integrate PD and BSN directly, which prevents the fully self-supervised denoising model on real-world images. We propose an Asymmetric PD (AP) to address this issue, which introduces different PD stride factors for training and inference. We systematically demonstrate that the proposed AP can resolve inherent trade-offs caused by specific PD stride factors and make BSN applicable to practical scenarios. To this end, we develop AP-BSN, a state-of-the-art self-supervised denoising method for real-world sRGB images. We further propose random-replacing refinement, which significantly improves the performance of our AP-BSN without any additional parameters. Extensive studies demonstrate that our method outperforms the other self-supervised and even unpaired denoising methods by a large margin, without using any additional knowledge, e.g., noise level, regarding the underlying unknown noise.
-
Powerful priors allow us to perform inference with insufficient information. In this paper, we propose an autoregressive prior for 3D shapes to solve multimodal 3D tasks such as shape completion, reconstruction, and generation. We model the distribution over 3D shapes as a non-sequential autoregressive distribution over a discretized, low-dimensional, symbolic grid-like latent representation of 3D shapes. This enables us to represent distributions over 3D shapes conditioned on information from an arbitrary set of spatially anchored query locations and thus perform shape completion in such arbitrary settings (e.g. generating a complete chair given only a view of the back leg). We also show that the learned autoregressive prior can be leveraged for conditional tasks such as single-view reconstruction and language-based generation. This is achieved by learning task-specific 'naive' conditionals which can be approximated by light-weight models trained on minimal paired data. We validate the effectiveness of the proposed method using both quantitative and qualitative evaluation and show that the proposed method outperforms the specialized state-of-the-art methods trained for individual tasks. The project page with code and video visualizations can be found at https://yccyenchicheng.github.io/AutoSDF/.
-
Recent works show that convolutional neural network (CNN) architectures have a spectral bias towards lower frequencies, which has been leveraged for various image restoration tasks in the Deep Image Prior (DIP) framework. The benefit of the inductive bias the network imposes in the DIP framework depends on the architecture. Therefore, researchers have studied how to automate the search to determine the best-performing model. However, common neural architecture search (NAS) techniques are resource and time-intensive. Moreover, best-performing models are determined for a whole dataset of images instead of for each image independently, which would be prohibitively expensive. In this work, we first show that optimal neural architectures in the DIP framework are image-dependent. Leveraging this insight, we then propose an image-specific NAS strategy for the DIP framework that requires substantially less training than typical NAS approaches, effectively enabling image-specific NAS. We justify the proposed strategy's effectiveness by (1) demonstrating its performance on a NAS Dataset for DIP that includes 522 models from a particular search space (2) conducting extensive experiments on image denoising, inpainting, and super-resolution tasks. Our experiments show that image-specific metrics can reduce the search space to a small cohort of models, of which the best model outperforms current NAS approaches for image restoration. Codes and datasets are available at https://github.com/ozgurkara99/ISNAS-DIP.
-
Existing approaches for Structure from Motion (SfM) produce impressive 3D reconstruction results especially when using imagery captured with large parallax. However, to create engaging video-content in movies and TV shows, the amount by which a camera can be moved while filming a particular shot is often limited. The resulting small-motion parallax between video frames makes standard geometry-based SfM approaches not as effective for movies and TV shows. To address this challenge, we propose a simple yet effective approach that uses single-frame depth-prior obtained from a pretrained network to significantly improve geometry-based SfM for our small-parallax setting. To this end, we first use the depth-estimates of the detected keypoints to reconstruct the point cloud and camera-pose for initial two-view reconstruction. We then perform depth-regularized optimization to register new images and triangulate the new points during incremental reconstruction. To comprehensively evaluate our approach, we introduce a new dataset (StudioSfM) consisting of 130 shots with 21K frames from 15 studio-produced videos that are manually annotated by a professional CG studio. We demonstrate that our approach: (a) significantly improves the quality of 3D reconstruction for our small-parallax setting, (b) does not cause any degradation for data with large-parallax, and (c) maintains the generalizability and scalability of geometry-based sparse SfM. Our dataset can be obtained at github.com/amazon-research/small-baseline-camera-tracking.
-
The referring video object segmentation task (RVOS) involves segmentation of a text-referred object instance in the frames of a given video. Due to the complex nature of this multimodal task, which combines text reasoning, video understanding, instance segmentation and tracking, existing approaches typically rely on sophisticated pipelines in order to tackle it. In this paper, we propose a simple Transformer-based approach to RVOS. Our framework, termed Multimodal Tracking Transformer (MTTR), models the RVOS task as a sequence prediction problem. Following recent advancements in computer vision and natural language processing, MTTR is based on the realization that video and text can be processed together effectively and elegantly by a single multimodal Transformer model. MTTR is end-to-end trainable, free of text-related inductive bias components and requires no additional mask-refinement post-processing steps. As such, it simplifies the RVOS pipeline considerably compared to existing methods. Evaluation on standard benchmarks reveals that MTTR significantly outperforms previous art across multiple metrics. In particular, MTTR shows impressive +5.7 and +5.0 mAP gains on the A2D-Sentences and JHMDB-Sentences datasets respectively, while processing 76 frames per second. In addition, we report strong results on the public validation set of Refer-YouTube-VOS, a more challenging RVOS dataset that has yet to receive the attention of researchers. The code to reproduce our experiments is available at https://github.com/mttr2021/MTTR
-
In this paper, we present a general-purpose solution to cartoon image synthesis with unpaired training data. In contrast to previous works learning pre-defined cartoon styles for specified usage scenarios (portrait or scene), we aim to train a common cartoon translator which can not only simultaneously render exaggerated anime faces and realistic cartoon scenes, but also provide flexible user controls for desired cartoon styles. It is challenging due to the complexity of the task and the absence of paired data. The core idea of the proposed method is to introduce gated cycle mapping, that utilizes a novel gated mapping unit to produce the category-specific style code and embeds this code into cycle networks to control the translation process. For the concept of category, we classify images into different categories (e.g., 4 types: photo/cartoon portrait/scene) and learn finer-grained category translations rather than overall mappings between two domains (e.g., photo and cartoon). Furthermore, the proposed method can be easily extended to cartoon video generation with an auxiliary dataset and a new adaptive style loss. Experimental results demonstrate the superiority of the proposed method over the state of the art and validate its effectiveness in the brand-new task of general cartoon image synthesis.
-
We present IterMVS, a new data-driven method for high-resolution multi-view stereo. We propose a novel GRU-based estimator that encodes pixel-wise probability distributions of depth in its hidden state. Ingesting multi-scale matching information, our model refines these distributions over multiple iterations and infers depth and confidence. To extract the depth maps, we combine traditional classification and regression in a novel manner. We verify the efficiency and effectiveness of our method on DTU, Tanks&Temples and ETH3D. While being the most efficient method in both memory and run-time, our model achieves competitive performance on DTU and better generalization ability on Tanks&Temples as well as ETH3D than most state-of-the-art methods. Code is available at https://github.com/FangjinhuaWang/IterMVS.
-
We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection. In particular, the foreground points are inherently more important than background points for object detectors. Motivated by this, we propose a highly-efficient single-stage point-based 3D detector in this paper, termed IA-SSD. The key of our approach is to exploit two learnable, task-oriented, instance-aware downsampling strategies to hierarchically select the foreground points belonging to objects of interest. Additionally, we also introduce a contextual centroid perception module to further estimate precise instance centers. Finally, we build our \nickname following the encoder-only architecture for efficiency. Extensive experiments conducted on several large-scale detection benchmarks demonstrate the competitive performance of our IA-SSD. Thanks to the low memory footprint and a high degree of parallelism, it achieves a superior speed of 80+ frames-per-second on the KITTI dataset with a single RTX2080Ti GPU. The code is available at https://github.com/yifanzhang713/IA-SSD.
-
Federated learning (FL) is a privacy-preserving distributed learning paradigm that enables clients to jointly train a global model. In real-world FL implementations, client data could have label noise, and different clients could have vastly different label noise levels. Although there exist methods in centralized learning for tackling label noise, such methods do not perform well on heterogeneous label noise in FL settings, due to the typically smaller sizes of client datasets and data privacy requirements in FL. In this paper, we propose FedCorr, a general multi-stage framework to tackle heterogeneous label noise in FL, without making any assumptions on the noise models of local clients, while still maintaining client data privacy. In particular, (1) FedCorr dynamically identifies noisy clients by exploiting the dimensionalities of the model prediction subspaces independently measured on all clients, and then identifies incorrect labels on noisy clients based on per-sample losses. To deal with data heterogeneity and to increase training stability, we propose an adaptive local proximal regularization term that is based on estimated local noise levels. (2) We further finetune the global model on identified clean clients and correct the noisy labels for the remaining noisy clients after finetuning. (3) Finally, we apply the usual training on all clients to make full use of all local data. Experiments conducted on CIFAR-10/100 with federated synthetic label noise, and on a real-world noisy dataset, Clothing1M, demonstrate that FedCorr is robust to label noise and substantially outperforms the state-of-the-art methods at multiple noise levels.
-
Camouflaged object detection (COD) aims to identify objects that are perfectly embedded in their environment, which has various downstream applications in fields such as medicine, art, and agriculture. However, it is an extremely challenging task to spot camouflaged objects with the perception ability of human eyes. Hence, we claim that the goal of COD task is not just to mimic the human visual ability in a single RGB domain, but to go beyond the human biological vision. We then introduce the frequency domain as an additional clue to better detect camouflaged objects from backgrounds. To well involve the frequency clues into the CNN models, we present a powerful network with two special components. We first design a novel frequency enhancement module (FEM) to dig clues of camouflaged objects in the frequency domain. It contains the offline discrete cosine transform followed by the learnable enhancement. Then we use a feature alignment to fuse the features from RGB domain and frequency domain. Moreover, to further make full use of the frequency information, we propose the high-order relation module (HOR) to handle the rich fusion feature. Comprehensive experiments on three widely-used COD datasets show the proposed method significantly outperforms other state-of-the-art methods by a large margin. The code and results are released in https://github.com/luckybird1994/FDCOD.
-
Volumetric neural rendering methods, such as neural ra-diance fields (NeRFs), have enabled photo-realistic novel view synthesis. However, in their standard form, NeRFs do not support the editing of objects, such as a human head,within a scene. In this work, we propose RigNeRF, a system that goes beyond just novel view synthesis and enables full control of head pose and facial expressions learned from a single portrait video. We model changes in head pose and facial expressions using a deformation field that is guided by a 3D morphable face model (3DMM). The 3DMM effectively acts as a prior for RigNeRF that learns to predict only residuals to the 3DMM deformations and allows us to render novel (rigid) poses and (non-rigid) expressions that were not present in the input sequence. Using only a smartphone-captured short video of a subject for training,we demonstrate the effectiveness of our method on free view synthesis of a portrait scene with explicit head pose and expression controls.
-
Generating shapes using natural language can enable new ways of imagining and creating the things around us. While significant recent progress has been made in text-to-image generation, text-to-shape generation remains a challenging problem due to the unavailability of paired text and shape data at a large scale. We present a simple yet effective method for zero-shot text-to-shape generation that circumvents such data scarcity. Our proposed method, named CLIP-Forge, is based on a two-stage training process, which only depends on an unlabelled shape dataset and a pre-trained image-text network such as CLIP. Our method has the benefits of avoiding expensive inference time optimization, as well as the ability to generate multiple shapes for a given text. We not only demonstrate promising zero-shot generalization of the CLIP-Forge model qualitatively and quantitatively, but also provide extensive comparative evaluations to better understand its behavior.
-
Image-based virtual try-on aims to fit an in-shop garment into a clothed person image. To achieve this, a key step is garment warping which spatially aligns the target garment with the corresponding body parts in the person image. Prior methods typically adopt a local appearance flow estimation model. They are thus intrinsically susceptible to difficult body poses/occlusions and large mis-alignments between person and garment images. To overcome this limitation, a novel global appearance flow estimation model is proposed in this work. For the first time, a StyleGAN based architecture is adopted for appearance flow estimation. This enables us to take advantage of a global style vector to encode a whole-image context to cope with the aforementioned challenges. To guide the StyleGAN flow generator to pay more attention to local garment deformation, a flow refinement module is introduced to add local context. Experiment results on a popular virtual try-on benchmark show that our method achieves new state-of-the-art performance. It is particularly effective in a 'in-the-wild' application scenario where the reference image is full-body resulting in a large mis-alignment with the garment image.
-
Source-free object detection (SFOD) needs to adapt a detector pre-trained on a labeled source domain to a target domain, with only unlabeled training data from the target domain. Existing SFOD methods typically adopt the pseudo labeling paradigm with model adaption alternating between predicting pseudo labels and fine-tuning the model. This approach suffers from both unsatisfactory accuracy of pseudo labels due to the presence of domain shift and limited use of target domain training data. In this work, we present a novel Learning to Overlook Domain Style (LODS) method with such limitations solved in a principled manner. Our idea is to reduce the domain shift effect by enforcing the model to overlook the target domain style, such that model adaptation is simplified and becomes easier to carry on. To that end, we enhance the style of each target domain image and leverage the style degree difference between the original image and the enhanced image as a self-supervised signal for model adaptation. By treating the enhanced image as an auxiliary view, we exploit a student-teacher architecture for learning to overlook the style degree difference against the original image, also characterized with a novel style enhancement algorithm and graph alignment constraint. Extensive experiments demonstrate that our LODS yields new state-of-the-art performance on four benchmarks.
-
Existing active learning studies typically work in the closed-set setting by assuming that all data examples to be labeled are drawn from known classes. However, in real annotation tasks, the unlabeled data usually contains a large amount of examples from unknown classes, resulting in the failure of most active learning methods. To tackle this open-set annotation (OSA) problem, we propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation. The LfOSA framework introduces an auxiliary network to model the per-example max activation value (MAV) distribution with a Gaussian Mixture Model, which can dynamically select the examples with highest probability from known classes in the unlabeled set. Moreover, by reducing the temperature T of the loss function, the detection model will be further optimized by exploiting both known and unknown supervision. The experimental results show that the proposed method can significantly improve the selection quality of known classes, and achieve higher classification accuracy with lower annotation cost than state-of-the-art active learning methods. To the best of our knowledge, this is the first work of active learning for open-set annotation.
-
Standard visual localization methods build a priori 3D model of a scene which is used to establish correspondences against the 2D keypoints in a query image. Storing these pre-built 3D scene models can be prohibitively expensive for large-scale environments, especially on mobile devices with limited storage and communication bandwidth. We design a novel framework that compresses a scene while still maintaining localization accuracy. The scene is compressed in three stages: first, the database frames are clustered using pairwise co-visibility information. Then, a learned point selection module prunes the points in each cluster taking into account the final pose estimation accuracy. In the final stage, the features of the selected points are further compressed using learned quantization. Query image registration is done using only the compressed scene points. To the best of our knowledge, we are the first to propose learned scene compression for visual localization. We also demonstrate the effectiveness and efficiency of our method on various outdoor datasets where it can perform accurate localization with low memory consumption.
-
We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods require a predefined template mesh for a given sequence, while the template is hard to acquire for a specific subject. Meanwhile, the fixed topology limits the reconstruction accuracy and clothing types. Implicit representation supports arbitrary topology and can represent high-fidelity geometry shapes due to its continuous nature. However, it is difficult to integrate multi-frame information to produce a consistent registration sequence for downstream applications. We propose to combine the advantages of both representations. We utilize differential mask loss of the explicit mesh to obtain the coherent overall shape, while the details on the implicit surface are refined with the differentiable neural rendering. Meanwhile, the explicit mesh is updated periodically to adjust its topology changes, and a consistency loss is designed to match both representations. Compared with existing methods, SelfRecon can produce high-fidelity surfaces for arbitrary clothed humans with self-supervised optimization. Extensive experimental results demonstrate its effectiveness on real captured monocular videos. The source code is available at https://github.com/jby1993/SelfReconCode.
-
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers. However, it is very challenging to estimate the transition matrix T(x), where T(x) denotes the instance, because it is unidentifiable under the instance-dependent noise (IDN). To address this problem, we have noticed that, there are psychological and physiological evidences showing that we humans are more likely to annotate instances of similar appearances to the same classes, and thus poor-quality or ambiguous instances of similar appearances are easier to be mislabeled to the correlated or same noisy classes. Therefore, we propose assumption on the geometry of T(x) that "the closer two instances are, the more similar their corresponding transition matrices should be". More specifically, we formulate above assumption into the manifold embedding, to effectively reduce the degree of freedom of T(x) and make it stably estimable in practice. This proposed manifold-regularized technique works by directly reducing the estimation error without hurting the approximation error about the estimation problem of T(x) Experimental evaluations on four synthetic and two real-world datasets demonstrate our method is superior to state-of-the-art approaches for label-noise learning under the challenging IDN.
-
A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the pre-determined composition of multiple data augmentations brings two drawbacks. First, the artificial choice of augmentation types brings specific representational invariances to the model, which have different degrees of positive and negative effects on different downstream tasks. Treating each type of augmentation equally during training makes the model learn non-optimal representations for various downstream tasks and limits the flexibility to choose augmentation types beforehand. Second, the strong data augmentations used in classic contrastive learning methods may bring too much invariance in some cases, and fine-grained information that is essential to some downstream tasks may be lost. This paper proposes a general method to alleviate these two problems by considering "where" and "what" to contrast in a general contrastive learning framework. We first propose to learn different augmentation invariances at different depths of the model according to the importance of each data augmentation instead of learning representational invariances evenly in the backbone. We then propose to expand the contrast content with augmentation embeddings to reduce the misleading effects of strong data augmentations. Experiments based on several baseline methods demonstrate that we learn better representations for various benchmarks on classification, detection, and segmentation downstream tasks.
-
Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically reduced in a Continual Learning (CL) scenario where data is presented to the model sequentially. In this paper, we show that self-supervised loss functions can be seamlessly converted into distillation mechanisms for CL by adding a predictor network that maps the current state of the representations to their past state. This enables us to devise a framework for Continual self-supervised visual representation Learning that (i) significantly improves the quality of the learned representations, (ii) is compatible with several state-of-the-art self-supervised objectives, and (iii) needs little to no hyperparameter tuning. We demonstrate the effectiveness of our approach empirically by training six popular self-supervised models in various CL settings. Code: github.com/DonkeyShot21/cassle
-
Convolutional image deraining networks have achieved great success while suffering from tremendous computational and memory costs. Most model compression methods require original data for iterative fine-tuning, which is limited in real-world applications due to storage, privacy, and transmission constraints. We note that it is overstretched to fine-tune the compressed model using self-collected data, as it exhibits poor generalization over images with different degradation characteristics. To address this problem, we propose a novel data-free compression framework for deraining networks. It is based on our observation that deep degradation representations can be clustered by degradation characteristics (types of rain) while independent of image content. Therefore, in our framework, we "dream" diverse in-distribution degraded images using a deep inversion paradigm, thus leveraging them to distill the pruned model. Specifically, we preserve the performance of the pruned model in a dual-branch way. In one branch, we invert the pre-trained model (teacher) to reconstruct the degraded inputs that resemble the original distribution and employ the orthogonal regularization for deep features to yield degradation diversity. In the other branch, the pruned model (student) is distilled to fit the teacher's original statistical modeling on these dreamed inputs. Further, an adaptive pruning scheme is proposed to determine the hierarchical sparsity, which alleviates the regression drift of the initial pruned model. Experiments on various deraining datasets demonstrate that our method can reduce about 40% FLOPs of the state-of-the-art models while maintaining comparable performance without original data.
-
Equivariance has been a long-standing concern in various fields ranging from computer vision to physical modeling. Most previous methods struggle with generality, simplicity, and expressiveness --- some are designed ad hoc for specific data types, some are too complex to be accessible, and some sacrifice flexible transformations. In this work, we propose a novel and simple framework to achieve equivariance for point cloud analysis based on the message passing (graph neural network) scheme. We find the equivariant property could be obtained by introducing an orientation for each point to decouple the relative position for each point from the global pose of the entire point cloud. Therefore, we extend current message passing networks with a module that learns orientations for each point. Before aggregating information from the neighbors of a point, the networks transforms the neighbors' coordinates based on the point's learned orientations. We provide formal proofs to show the equivariance of the proposed framework. Empirically, we demonstrate that our proposed method is competitive on both point cloud analysis and physical modeling tasks. Code is available at https://github.com/luost26/Equivariant-OrientedMP.
-
Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well understood, the field still lacks widely accepted best practices for replicating this success on other datasets. As a first step in this direction, we study contrastive self-supervised learning on four diverse large-scale datasets. By looking through the lenses of data quantity, data domain, data quality, and task granularity, we provide new insights into the necessary conditions for successful self-supervised learning. Our key findings include observations such as: (i) the benefit of additional pretraining data beyond 500k images is modest, (ii) adding pretraining images from another domain does not lead to more general representations, (iii) corrupted pretraining images have a disparate impact on supervised and self-supervised pretraining, and (iv) contrastive learning lags far behind supervised learning on fine-grained visual classification tasks.
-
We study the problem of developing autonomous agents that can follow human instructions to infer and perform a sequence of actions to complete the underlying task. Significant progress has been made in recent years, especially for tasks with short horizons. However, when it comes to long-horizon tasks with extended sequences of actions, an agent can easily ignore some instructions or get stuck in the middle of the long instructions and eventually fail the task. To address this challenge, we propose a model-agnostic milestone-based task tracker (M-Track) to guide the agent and monitor its progress. Specifically, we propose a milestone builder that tags the instructions with navigation and interaction milestones which the agent needs to complete step by step, and a milestone checker that systemically checks the agent's progress in its current milestone and determines when to proceed to the next. On the challenging ALFRED dataset, our M-Track leads to a notable 33% and 52% relative improvement in unseen success rate over two competitive base models.
-
The key towards learning informative node representations in graphs lies in how to gain contextual information from the neighbourhood. In this work, we present a simple-yet-effective self-supervised node representation learning strategy via directly maximizing the mutual information between the hidden representations of nodes and their neighbourhood, which can be theoretically justified by its link to graph smoothing. Following InfoNCE, our framework is optimized via a surrogate contrastive loss, where the positive selection underpins the quality and efficiency of representation learning. To this end, we propose a topology-aware positive sampling strategy, which samples positives from the neighbourhood by considering the structural dependencies between nodes and thus enables positive selection upfront. In the extreme case when only one positive is sampled, we fully avoid expensive neighbourhood aggregation. Our methods achieve promising performance on various node classification datasets. It is also worth mentioning by applying our loss function to MLP based node encoders, our methods can be orders of faster than existing solutions. Our codes and supplementary materials are available at https://github.com/dongwei156/n2n.
-
The construction of 3D point cloud datasets requires a great deal of human effort. Therefore, constructing a largescale 3D point clouds dataset is difficult. In order to remedy this issue, we propose a newly developed point cloud fractal database (PC-FractalDB), which is a novel family of formula-driven supervised learning inspired by fractal geometry encountered in natural 3D structures. Our research is based on the hypothesis that we could learn representations from more real-world 3D patterns than conventional 3D datasets by learning fractal geometry. We show how the PC-FractalDB facilitates solving several recent dataset-related problems in 3D scene understanding, such as 3D model collection and labor-intensive annotation. The experimental section shows how we achieved the performance rate of up to 61.9% and 59.0% for the ScanNetV2 and SUN RGB-D datasets, respectively, over the current highest scores obtained with the PointContrast, contrastive scene contexts (CSC), and RandomRooms. Moreover, the PC-FractalDB pre-trained model is especially effective in training with limited data. For example, in 10% of training data on ScanNetV2, the PC-FractalDB pre-trained VoteNet performs at 38.3%, which is +14.8% higher accuracy than CSC. Of particular note, we found that the proposed method achieves the highest results for 3D object detection pre-training in limited point cloud data.
-
A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene boundary from the long-term video is a challenging task, since a model must understand the storyline of the video to figure out where a scene starts and ends. To this end, we propose an effective Self-Supervised Learning (SSL) framework to learn better shot representations from unlabeled long-term videos. More specifically, we present an SSL scheme to achieve scene consistency, while exploring considerable data augmentation and shuffling methods to boost the model generalizability. Instead of explicitly learning the scene boundary features as in the previous methods, we introduce a vanilla temporal model with less inductive bias to verify the quality of the shot features. Our method achieves the state-of-the-art performance on the task of Video Scene Segmentation. Additionally, we suggest a more fair and reasonable benchmark to evaluate the performance of Video Scene Segmentation methods. The code is made available.
-
Correctly classifying adversarial examples is an essential but challenging requirement for safely deploying machine learning models. As reported in RobustBench, even the state-of-the-art adversarially trained models struggle to exceed 67% robust test accuracy on CIFAR-10, which is far from practical. A complementary way towards robustness is to introduce a rejection option, allowing the model to not return predictions on uncertain inputs, where confidence is a commonly used certainty proxy. Along with this routine, we find that confidence and a rectified confidence (R-Con) can form two coupled rejection metrics, which could provably distinguish wrongly classified inputs from correctly classified ones. This intriguing property sheds light on using coupling strategies to better detect and reject adversarial examples. We evaluate our rectified rejection (RR) module on CIFAR-10, CIFAR-10-C, and CIFAR-100 under several attacks including adaptive ones, and demonstrate that the RR module is compatible with different adversarial training frameworks on improving robustness, with little extra computation.
-
Explaining the generalization characteristics of deep learning is an emerging topic in advanced machine learning. There are several unanswered questions about how learning under stochastic optimization really works and why certain strategies are better than others. In this paper, we address the following question: can we probe intermediate layers of a deep neural network to identify and quantify the learning quality of each layer? With this question in mind, we propose new explainability metrics that measure the redundant information in a network's layers using a low-rank factorization framework and quantify a complexity measure that is highly correlated with the generalization performance of a given optimizer, network, and dataset. We subsequently exploit these metrics to augment the Stochastic Gradient Descent (SGD) optimizer by adaptively adjusting the learning rate in each layer to improve in generalization performance. Our augmented SGD -- dubbed RMSGD -- introduces minimal computational overhead compared to SOTA methods and outperforms them by exhibiting strong generalization characteristics across application, architecture, and dataset.
-
One major challenge for semantic segmentation in real-world scenarios is only limited pixel-level labels available due to high expense of human labor though a vast volume of video data is provided. Existing semi-supervised methods attempt to exploit unlabeled data in model training, but they just regard video as a set of independent images. To better explore semi-supervised segmentation problem with video data, we formulate a semi-supervised video semantic segmentation task in this paper. For this task, we observe that the overfitting is surprisingly severe between labeled and unlabeled frames within a training video although they are very similar in style and contents. This is called inner-video overfitting, and it would actually lead to inferior performance. To tackle this issue, we propose a novel inter-frame feature reconstruction (IFR) technique to leverage the ground-truth labels to supervise the model training on unlabeled frames. IFR is essentially to utilize the internal relevance of different frames within a video. During training, IFR would enforce the feature distributions between labeled and unlabeled frames to be narrowed. Consequently, the inner-video overfitting issue can be effectively alleviated. We conduct extensive experiments on Cityscapes and CamVid, and the results demonstrate the superiority of our proposed method to previous state-of-the-art methods. The code is available at https://github.com/jfzhuang/IFR.
-
In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formalize the requirements for each component.We instantiate our general differentiable renderer, which generalizes existing differentiable renderers like SoftRas and DIB-R, with an array of different smoothing distributions to cover a large spectrum of reasonable settings. We evaluate an array of differentiable renderer instantiations on the popular ShapeNet 3D reconstruction benchmark and analyze the implications of our results. Surprisingly, the simple uniform distribution yields the best overall results when averaged over 13 classes; in general, however, the optimal choice of distribution heavily depends on the task.
-
Neural implicit surfaces have become an important technique for multi-view 3D reconstruction but their accuracy remains limited. In this paper, we argue that this comes from the difficulty to learn and render high frequency textures with neural networks. We thus propose to add to the standard neural rendering optimization a direct photo-consistency term across the different views. Intuitively, we optimize the implicit geometry so that it warps views on each other in a consistent way. We demonstrate that two elements are key to the success of such an approach: (i) warping entire patches, using the predicted occupancy and normals of the 3D points along each ray, and measuring their similarity with a robust structural similarity (SSIM); (ii) handling visibility and occlusion in such a way that incorrect warps are not given too much importance while encouraging a reconstruction as complete as possible. We evaluate our approach, dubbed NeuralWarp, on the standard DTU and EPFL benchmarks and show it outperforms state of the art unsupervised implicit surfaces reconstructions by over 20% on both datasets.
-
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings. However, most existing approaches utilize the position embeddings to incorporate the sequence information, neglecting the noisy improper reading order obtained by OCR tools. In this paper, we propose a robust layout-aware multimodal network named XYLayoutLM to capture and leverage rich layout information from proper reading orders produced by our Augmented XY Cut. Moreover, a Dilated Conditional Position Encoding module is proposed to deal with the input sequence of variable lengths, and it additionally extracts local layout information from both textual and visual modalities while generating position embeddings. Experiment results show that our XYLayoutLM achieves competitive results on document understanding tasks.
-
Amodal Segmentation Through Out-of-Task and Out-of-Distribution Generalization With a Bayesian Model
Amodal completion is a visual task that humans perform easily but which is difficult for computer vision algorithms. The aim is to segment those object boundaries which are occluded and hence invisible. This task is particularly challenging for deep neural networks because data is difficult to obtain and annotate. Therefore, we formulate amodal segmentation as an out-of-task and out-of-distribution generalization problem. Specifically, we replace the fully connected classifier in neural networks with a Bayesian generative model of the neural network features. The model is trained from non-occluded images using bounding box annotations and class labels only, but is applied to generalize out-of-task to object segmentation and to generalize out-of-distribution to segment occluded objects. We demonstrate how such Bayesian models can naturally generalize beyond the training task labels when they learn a prior that models the object's background context and shape. Moreover, by leveraging an outlier process, Bayesian models can further generalize out-of-distribution to segment partially occluded objects and to predict their amodal object boundaries. Our algorithm outperforms alternative methods that use the same supervision by a large margin, and even outperforms methods where annotated amodal segmentations are used during training, when the amount of occlusion is large. Code is publically available at https://github.com/anonymous-submission-vision/Amodal-Bayesian.
-
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets. Generally, more accurate models on the "upstream" dataset tend to provide better transfer accuracy "downstream". In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned--that is, compressed by sparsifiying their connections. We consider transfer using unstructured pruned models obtained by applying several state-of-the-art pruning methods, including magnitude-based, second-order, re-growth, lottery-ticket, and regularization approaches, in the context of twelve standard transfer tasks. In a nutshell, our study shows that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities, and, while doing so, can lead to significant inference and even training speedups. At the same time, we observe and analyze significant differences in the behaviour of different pruning methods. The code is available at: https://github.com/IST-DASLab/sparse-imagenet-transfer.
-
Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the rationales behind the decisions. As a result, they commonly take advantage of spurious biases instead of actually reasoning on the visual-textual data, and have yet developed the capability to explain their decision making by considering key information from both modalities. This paper aims to close the gap from three distinct perspectives: first, we define a new type of multi-modal explanations that explain the decisions by progressively traversing the reasoning process and grounding keywords in the images. We develop a functional program to sequentially execute different reasoning steps and construct a new dataset with 1,040,830 multi-modal explanations. Second, we identify the critical need to tightly couple important components across the visual and textual modalities for explaining the decisions, and propose a novel explanation generation method that explicitly models the pairwise correspondence between words and regions of interest. It improves the visual grounding capability by a considerable margin, resulting in enhanced interpretability and reasoning performance. Finally, with our new data and method, we perform extensive analyses to study the effectiveness of our explanation under different settings, including multi-task learning and transfer learning. Our code and data are available at https://github.com/szzexpoi/rex
-
Iterative denoising-based generation, also known as denoising diffusion models, has recently been shown to be comparable in quality to other classes of generative models, and even surpass them. Including, in particular, Generative Adversarial Networks, which are currently the state of the art in many sub-tasks of image generation. However, a major drawback of this method is that it requires hundreds of iterations to produce a competitive result. Recent works have proposed solutions that allow for faster generation with fewer iterations, but the image quality gradually deteriorates with increasingly fewer iterations being applied during generation. In this paper, we reveal some of the causes that affect the generation quality of diffusion models, especially when sampling with few iterations, and come up with a simple, yet effective, solution to mitigate them. We consider two opposite equations for the iterative denoising, the first predicts the applied noise, and the second predicts the image directly. Our solution takes the two options and learns to dynamically alternate between them through the denoising process. Our proposed solution is general and can be applied to any existing diffusion model. As we show, when applied to various SOTA architectures, our solution immediately improves their generation quality, with negligible added complexity and parameters. We experiment on multiple datasets and configurations and run an extensive ablation study to support these findings.
-
Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for robustness and fairness, e.g., inability to synthesize the face images of underrepresented demographic groups. In this paper, we introduce a new framework, StyleT2I, to improve the compositionality of text-to-image synthesis. Specifically, we propose a CLIP-guided Contrastive Loss to better distinguish different compositions among different sentences. To further improve the compositionality, we design a novel Semantic Matching Loss and a Spatial Constraint to identify attributes' latent directions for intended spatial region manipulations, leading to better disentangled latent representations of attributes. Based on the identified latent directions of attributes, we propose Compositional Attribute Adjustment to adjust the latent code, resulting in better compositionality of image synthesis. In addition, we leverage the l_2-norm regularization of identified latent directions (norm penalty) to strike a nice balance between image-text alignment and image fidelity. In the experiments, we devise a new dataset split and an evaluation metric to evaluate the compositionality of text-to-image synthesis models. The results show that StyleT2I outperforms previous approaches in terms of the consistency between the input text and synthesized images and achieves higher fidelity.
-
Physical products are often complex assemblies combining a multitude of 3D parts modeled in computer-aided design (CAD) software. CAD designers build up these assemblies by aligning individual parts to one another using constraints called joints. In this paper we introduce JoinABLe, a learning-based method that assembles parts together to form joints. JoinABLe uses the weak supervision available in standard parametric CAD files without the help of object class labels or human guidance. Our results show that by making network predictions over a graph representation of solid models we can outperform multiple baseline methods with an accuracy (79.53%) that approaches human performance (80%). Finally, to support future research we release the AssemblyJoint dataset, containing assemblies with rich information on joints, contact surfaces, holes, and the underlying assembly graph structure.
-
While neural representations for static 3D shapes are widely studied, representations for deformable surfaces are limited to be template-dependent or to lack efficiency. We introduce Canonical Deformation Coordinate Space (CaDeX), a unified representation of both shape and nonrigid motion. Our key insight is the factorization of the deformation between frames by continuous bijective canonical maps (homeomorphisms) and their inverses that go through a learned canonical shape. Our novel deformation representation and its implementation are simple, efficient, and guarantee cycle consistency, topology preservation, and, if needed, volume conservation. Our modelling of the learned canonical shapes provides a flexible and stable space for shape prior learning. We demonstrate state-of-the-art performance in modelling a wide range of deformable geometries: human bodies, animal bodies, and articulated objects.
-
3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations with an additional Multi-Layer-Perceptron network. Both their offset and orientation predictions are not accurate due to the fundamental difficulty in rotation classification. In the work, we disentangle the direct offset into Local Canonical Coordinates (LCC), box scales and box orientations. Only LCC and box scales are regressed, while box orientations are generated by a canonical voting scheme. Finally, an LCC-aware back-projection checking algorithm iteratively cuts out bounding boxes from the generated vote maps, with the elimination of false positives. Our model achieves state-of-the-art performance on three standard real-world benchmarks: ScanNet, SceneNN and SUN RGB-D. Our code is available on https://github.com/qq456cvb/CanonicalVoting.
-
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks. The V-Doc supports generating and using both extractive and abstractive question-answer pairs using documents images. The extractive QA selects a subset of tokens or phrases from the document contents to predict the answers, while the abstractive QA recognises the language in the content and generates the answer based on the trained model. Both aspects are crucial to understanding the documents, especially in an image format. We include a detailed scenario of question generation for the abstractive QA task. V-Doc supports a wide range of datasets and models, and is highly extensible through a declarative, framework-agnostic platform.
-
The best performing learning algorithms devised for event cameras work by first converting events into dense representations that are then processed using standard CNNs. However, these steps discard both the sparsity and high temporal resolution of events, leading to high computational burden and latency. For this reason, recent works have adopted Graph Neural Networks (GNNs), which process events as "static" spatio-temporal graphs, which are inherently "sparse". We take this trend one step further by introducing Asynchronous, Event-based Graph Neural Networks (AEGNNs), a novel event-processing paradigm that generalizes standard GNNs to process events as "evolving" spatio-temporal graphs. AEGNNs follow efficient update rules that restrict recomputation of network activations only to the nodes affected by each new event, thereby significantly reducing both computation and latency for event-by-event processing. AEGNNs are easily trained on synchronous inputs and can be converted to efficient, "asynchronous" networks at test time. We thoroughly validate our method on object classification and detection tasks, where we show an up to a 200-fold reduction in computational complexity (FLOPs), with similar or even better performance than state-of-the-art asynchronous methods. This reduction in computation directly translates to an 8-fold reduction in computational latency when compared to standard GNNs, which opens the door to low-latency event-based processing.
-
Personalized Federated Learning (pFL) not only can capture the common priors from broad range of distributed data, but also support customized models for heterogeneous clients. Researches over the past few years have applied the weighted aggregation manner to produce personalized models, where the weights are determined by calibrating the distance of the entire model parameters or loss values, and have yet to consider the layer-level impacts to the aggregation process, leading to lagged model convergence and inadequate personalization over non-IID datasets. In this paper, we propose a novel pFL training framework dubbed Layer-wised Personalized Federated learning (pFedLA) that can discern the importance of each layer from different clients, and thus is able to optimize the personalized model aggregation for clients with heterogeneous data. Specifically, we employ a dedicated hypernetwork per client on the server side, which is trained to identify the mutual contribution factors at layer granularity. Meanwhile, a parameterized mechanism is introduced to update the layer-wised aggregation weights to progressively exploit the inter-user similarity and realize accurate model personalization. Extensive experiments are conducted over different models and learning tasks, and we show that the proposed methods achieve significantly higher performance than state-of-the-art pFL methods.
-
We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of any pre-trained deep generative network (DGN). Leveraging the fact that DGNs are, or can be approximated by, continuous piecewise affine splines, we derive the analytical DGN output space distribution as a function of the product of the DGN's Jacobian singular values raised to a power rho. We dub rho the polarity parameter and prove that rho focuses the DGN sampling on the modes (rho < 0) or anti-modes (rho > 0) of the DGN output space probability distribution. We demonstrate that nonzero polarity values achieve a better precision-recall (quality-diversity) Pareto frontier than standard methods, such as truncation, for a number of state-of-the-art DGNs. We also present quantitative and qualitative results on the improvement of overall generation quality (e.g., in terms of the Frechet Inception Distance) for a number of state-of-the-art DGNs, including StyleGAN3, BigGAN-deep, NVAE, for different conditional and unconditional image generation tasks. In particular, Polarity Sampling redefines the state-of-the-art for StyleGAN2 on the FFHQ Dataset to FID 2.57, StyleGAN2 on the LSUN Car Dataset to FID 2.27 and StyleGAN3 on the AFHQv2 Dataset to FID 3.95. Colab Demo: bit.ly/polarity-samp
-
In this study, we present a colorization network that generates flat-color icons according to given sketches and semantic colorization styles. Specifically, our network contains a style-structure disentangled colorization module and a normalizing flow. The colorization module transforms a paired sketch image and style image into a flat-color icon. To enhance network generalization and the quality of icons, we present a pixel-wise decoder, a global style code, and a contour loss to reduce color gradients at flat regions and increase color discontinuity at boundaries. The normalizing flow maps Gaussian vectors to diverse style codes conditioned on the given semantic colorization label. This conditional sampling enables users to control attributes and obtain diverse colorization results. Compared to previous colorization methods built upon conditional generative adversarial networks, our approach enjoys the advantages of both high image quality and diversity. To evaluate its effectiveness, we compared the flat-color icons generated by our approach and recent colorization and image-to-image translation methods on various conditions. Experiment results verify that our method outperforms state-of-the-arts qualitatively and quantitatively.
-
Recently, by introducing large-scale dataset and strong transformer network, video-language pre-training has shown great success especially for retrieval. Yet, existing video-language transformer models do not explicitly fine-grained semantic align. In this work, we present Object-aware Transformers, an object-centric approach that extends video-language transformer to incorporate object representations. The key idea is to leverage the bounding boxes and object tags to guide the training process. We evaluate our model on three standard sub-tasks of video-text matching on four widely used benchmarks. We also provide deep analysis and detailed ablation about the proposed method. We show clear improvement in performance across all tasks and datasets considered, demonstrating the value of a model that incorporates object representations into a video-language architecture. The code has been released in https://github.com/FingerRec/OA-Transformer.
-
Rotated object detection is a challenging issue in computer vision field. Inadequate rotated representation and the confusion of parametric regression have been the bottleneck for high performance rotated detection. In this paper, we propose an orientation-sensitive keypoint based rotated detector OSKDet. First, we adopt a set of keypoints to represent the target and predict the keypoint heatmap on ROI to get the rotated box. By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for rotated representation, which improves the localization accuracy and acquires high quality detection results. Second, we explore a new unordered keypoint representation paradigm, which could avoid the confusion of keypoint regression caused by rule based ordering. Furthermore, we propose a localization quality uncertainty module to better predict the classification score by the distribution uncertainty of keypoints heatmap. Experimental results on several public benchmarks show the state-of-the-art performance of OSKDet. Specifically, we achieve an AP of 80.91% on DOTA, 89.98% on HRSC2016, 97.27% on UCAS-AOD, and a F-measure of 92.18% on ICDAR2015, 81.43% on ICDAR2017, respectively.
-
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low resolution in consideration of computational cost. In this paper, we present a novel transformer-based model for large hole inpainting, which unifies the merits of transformers and convolutions to efficiently process high-resolution images. We carefully design each component of our framework to guarantee the high fidelity and diversity of recovered images. Specifically, we customize an inpainting-oriented transformer block, where the attention module aggregates non-local information only from partial valid tokens, indicated by a dynamic mask. Extensive experiments demonstrate the state-of-the-art performance of the new model on multiple benchmark datasets. Code is released at https://github.com/fenglinglwb/MAT.
-
This paper investigates the geometric consistency for monocular 3D object detection, which suffers from the ill-posed depth estimation. We first conduct a thorough analysis to reveal how existing methods fail to consistently localize objects when different geometric shifts occur. In particular, we design a series of geometric manipulations to diagnose existing detectors and then illustrate their vulnerability to consistently associate the depth with object apparent sizes and positions. To alleviate this issue, we propose four geometry-aware data augmentation approaches to enhance the geometric consistency of the detectors. We first modify some commonly used data augmentation methods for 2D images so that they can maintain geometric consistency in 3D spaces. We demonstrate such modifications are important. In addition, we propose a 3D-specific image perturbation method that employs the camera movement. During the augmentation process, the camera system with the corresponding image is manipulated, while the geometric visual cues for depth recovery are preserved. We show that by using the geometric consistency constraints, the proposed augmentation techniques lead to improvements on the KITTI and nuScenes monocular 3D detection benchmarks with state-of-the-art results. In addition, we demonstrate that the augmentation methods are well suited for semi-supervised training and cross-dataset generalization.
-
Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture the relationships between nodes in the graph, we exploit the multi-head attention mechanism to compute a multi-head potential function, which is fed to the networks to output an optimized depth map. Then we build a bottom-up-top-down structure, where this neural window FC-CRFs module serves as the decoder, and a vision transformer serves as the encoder. The experiments demonstrate that our method significantly improves the performance across all metrics on both the KITTI and NYUv2 datasets, compared to previous methods. Furthermore, the proposed method can be directly applied to panorama images and outperforms all previous panorama methods on the MatterPort3D dataset.
-
Transformers have gained much attention by outperforming convolutional neural networks in many 2D vision tasks. However, they are known to have generalization problems and rely on massive-scale pre-training and sophisticated training techniques. When applying to 3D tasks, the irregular data structure and limited data scale add to the difficulty of transformer's application. We propose Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers. On the one hand, we propose the codebook-based attention that projects an attention space into its subspace represented by the combination of "prototypes" in a learnable codebook. It regularizes attention learning and improves generalization. On the other hand, we propose geometry-aware self-attention that utilizes geometric information (geometric pattern, density) to guide attention learning. CodedVTR could be embedded into existing sparse convolution-based methods, and bring consistent performance improvements for indoor and outdoor 3D semantic segmentation tasks.
-
This paper presents a simple and effective solution to the longstanding classical multi-view photometric stereo (MVPS) problem. It is well-known that photometric stereo (PS) is excellent at recovering high-frequency surface details, whereas multi-view stereo (MVS) can help remove the low-frequency distortion due to PS and retain the global geometry of the shape. This paper proposes an approach that can effectively utilize such complementary strengths of PS and MVS. Our key idea is to combine them suitably while considering the per-pixel uncertainty of their estimates. To this end, we estimate per-pixel surface normals and depth using an uncertainty-aware deep-PS network and deep-MVS network, respectively. Uncertainty modeling helps select reliable surface normal and depth estimates at each pixel which then act as a true representative of the dense surface geometry. At each pixel, our approach either selects or discards deep-PS and deep-MVS network prediction depending on the prediction uncertainty measure. For dense, detailed, and precise inference of the object's surface profile, we propose to learn the implicit neural shape representation via a multilayer perceptron (MLP). Our approach encourages the MLP to converge to a natural zero-level set surface using the confident prediction from deep-PS and deep-MVS networks, providing superior dense surface reconstruction. Extensive experiments on the DiLiGenT-MV benchmark dataset show that our method provides high-quality shape recovery with a much lower memory footprint while outperforming almost all of the existing approaches.
-
In this paper, we explore a new type of extrinsic method to directly align two geometric shapes with point-to-point correspondences in ambient space by recovering a deformation, which allows more continuous and smooth maps to be obtained. Specifically, the classic coherent point drift is revisited and generalizations have been proposed. First, by observing that the deformation model is essentially defined with respect to Euclidean space, we generalize the kernel method to non-Euclidean domains. This generally leads to better results for processing shapes, which are known as two-dimensional manifolds. Second, a generalized probabilistic model is proposed to address the sensibility of coherent point drift method to local optima. Instead of directly optimizing over the objective of coherent point drift, the new model allows to focus on a group of most confident ones, thus improves the robustness of the registration system. Experiments are conducted on multiple public datasets with comparison to state-of-the-art competitors, demonstrating the superiority of our method which is both flexible and efficient to improve the matching accuracy due to our extrinsic alignment objective in ambient space.
-
Existing person re-identification (ReID) methods typically directly load the pre-trained ImageNet weights for initialization. However, as a fine-grained classification task, ReID is more challenging and exists a large domain gap between ImageNet classification. Inspired by the great success of self-supervised representation learning with contrastive objectives, in this paper, we design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID. During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images. (2) the fine-grained local features of person images are not fully-explored. Therefore, we introduce an (I^2-)regularization in the UP-ReID, which is instantiated as two constraints coming from global image aspect and local patch aspect: a global consistency is enforced between augmented and original person images to increase robustness to augmentation, while an intrinsic contrastive constraint among local patches of each image is employed to fully explore the local discriminative clues. Extensive experiments on multiple popular Re-ID datasets, including PersonX, Market1501, CUHK03, and MSMT17, demonstrate that our UP-ReID pre-trained model can significantly benefit the downstream ReID fine-tuning and achieve state-of-the-art performance.
-
Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between unimodal video and text features. Besides, learning fine-grained visual-language alignment usually requires off-the-shelf object detectors to provide object information, which is bottlenecked by the detector's limited vocabulary and expensive computation cost. We propose Align and Prompt: an efficient and effective video-and-language pre-training framework with better cross-modal alignment. First, we introduce a video-text contrastive (VTC) loss to align unimodal video-text features at the instance level, which eases the modeling of cross-modal interactions. Then, we propose a new visually-grounded pre-training task, prompting entity modeling (PEM), which aims to learn fine-grained region-entity alignment. To achieve this, we first introduce an entity prompter module, which is trained with VTC to produce the similarity between a video crop and text prompts instantiated with entity names. The PEM task then asks the model to predict the entity pseudo-labels (i.e normalized similarity scores) for randomly-selected video crops. The resulting pre-trained model achieves state-of-the-art performance on both text-video retrieval and videoQA, outperforming prior work by a substantial margin. Our code and pre-trained models are available at https://github.com/salesforce/ALPRO.
-
3D point cloud understanding is an important component in autonomous driving and robotics. In this paper, we present a novel Embedding-Querying paradigm (EQ- Paradigm) for 3D understanding tasks including detection, segmentation and classification. EQ-Paradigm is a unified paradigm that enables combination of existing 3D backbone architectures with different task heads. Under the EQ- Paradigm, the input is first encoded in the embedding stage with an arbitrary feature extraction architecture, which is independent of tasks and heads. Then, the querying stage enables the encoded features for diverse task heads. This is achieved by introducing an intermediate representation, i.e., Q-representation, in the querying stage to bridge the embedding stage and task heads. We design a novel Q-Net as the querying stage network. Extensive experimental results on various 3D tasks show that EQ-Paradigm in tandem with Q-Net is a general and effective pipeline, which enables flexible collaboration of backbones and heads. It further boosts performance of state-of-the-art methods.
-
In this paper, we present a framework for reading analog clocks in natural images or videos. Specifically, we make the following contributions: First, we create a scalable pipeline for generating synthetic clocks, significantly reducing the requirements for the labour-intensive annotations; Second, we introduce a clock recognition architecture based on spatial transformer networks (STN), which is trained end-to-end for clock alignment and recognition. We show that the model trained on the proposed synthetic dataset generalises towards real clocks with good accuracy, advocating a Sim2Real training regime; Third, to further reduce the gap between simulation and real data, we leverage the special property of "time", i.e.uniformity, to generate reliable pseudo-labels on real unlabelled clock videos, and show that training on these videos offers further improvements while still requiring zero manual annotations. Lastly, we introduce three benchmark datasets based on COCO, Open Images, and The Clock movie, with full annotations for time, accurate to the minute.
-
Transformers have offered a new methodology of designing neural networks for visual recognition. Compared to convolutional networks, Transformers enjoy the ability of referring to global features at each stage, yet the attention module brings higher computational overhead that obstructs the application of Transformers to process high-resolution visual data. This paper aims to alleviate the conflict between efficiency and flexibility, for which we propose a specialized token for each region that serves as a messenger (MSG). Hence, by manipulating these MSG tokens, one can flexibly exchange visual information across regions and the computational complexity is reduced. We then integrate the MSG token into a multi-scale architecture named MSG-Transformer. In standard image classification and object detection, MSG-Transformer achieves competitive performance and the inference on both GPU and CPU is accelerated. Code is available at https://github.com/hustvl/MSG-Transformer.
-
Profiting from large-scale training datasets, advances in neural architecture design and efficient inference, joint embeddings have become the dominant approach for tackling cross-modal retrieval. In this work we first show that, despite their effectiveness, state-of-the-art joint embeddings suffer significantly from the longstanding "hubness problem" in which a small number of gallery embeddings form the nearest neighbours of many queries. Drawing inspiration from the NLP literature, we formulate a simple but effective framework called Querybank Normalisation (QB-Norm) that re-normalises query similarities to account for hubs in the embedding space. QB-Norm improves retrieval performance without requiring retraining. Differently from prior work, we show that QB-Norm works effectively without concurrent access to any test set queries. Within the QB-Norm framework, we also propose a novel similarity normalisation method, the Dynamic Inverted Softmax, that is significantly more robust than existing approaches. We showcase QB-Norm across a range of cross modal retrieval models and benchmarks where it consistently enhances strong baselines beyond the state of the art. Code is available at https://vladbogo.github.io/QB-Norm/.
-
Contrastive learning (or its variants) has recently become a promising direction in the self-supervised learning domain, achieving similar performance as supervised learning with minimum fine-tuning. Despite the labeling efficiency, wide and large networks are required to achieve high accuracy, which incurs a high amount of computation and hinders the pragmatic merit of self-supervised learning. To effectively reduce the computation of insignificant features or channels, recent dynamic pruning algorithms for supervised learning employed auxiliary salience predictors. However, we found that such salience predictors cannot be easily trained when they are naively applied to contrastive learning from scratch. To address this issue, we propose contrastive dual gating(CDG), a novel dynamic pruning algorithm that skips the uninformative features during contrastive learning without hurting the trainability of the networks. We demonstrate the superiority of CDG with ResNet models for CIFAR-10, CIFAR-100, and ImageNet-100 datasets. Compared to our implementations of state-of-the-art dynamic pruning algorithms for self-supervised learning, CDG achieves up to 15% accuracy improvement for CIFAR-10 dataset with higher computation reduction.
-
This paper tackles a new photometric stereo task, named universal photometric stereo. Unlike existing tasks that assumed specific physical lighting models; hence, drastically limited their usability, a solution algorithm of this task is supposed to work for objects with diverse shapes and materials under arbitrary lighting variations without assuming any specific models. To solve this extremely challenging task, we present a purely data-driven method, which eliminates the prior assumption of lighting by replacing the recovery of physical lighting parameters with the extraction of the generic lighting representation, named global lighting contexts. We use them like lighting parameters in a calibrated photometric stereo network to recover surface normal vectors pixelwisely. To adapt our network to a wide variety of shapes, materials and lightings, it is trained on a new synthetic dataset which simulates the appearance of objects in the wild. Our method is compared with other state-of-the-art uncalibrated photometric stereo methods on our test data to demonstrate the significance of our method.
-
Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information. Such approach withholds MLPs from getting comparable performance with their transformer-based counterparts and prevents them from becoming a general backbone for computer vision. This paper presents Hire-MLP, a simple yet competitive vision MLP architecture via Hierarchical rearrangement, which contains two levels of rearrangements. Specifically, the inner-region rearrangement is proposed to capture local information inside a spatial region, and the cross-region rearrangement is proposed to enable information communication between different regions and capture global context by circularly shifting all tokens along spatial directions. Extensive experiments demonstrate the effectiveness of Hire-MLP as a versatile backbone for various vision tasks. In particular, Hire-MLP achieves competitive results on image classification, object detection and semantic segmentation tasks, e.g., 83.8% top-1 accuracy on ImageNet, 51.7% box AP and 44.8% mask AP on COCO val2017, and 49.9% mIoU on ADE20K, surpassing previous transformer-based and MLP-based models with better trade-off for accuracy and throughput.
-
In this paper, we propose a novel monocular ray-based 3D (Ray3D) absolute human pose estimation with calibrated camera. Accurate and generalizable absolute 3D human pose estimation from monocular 2D pose input is an ill-posed problem. To address this challenge, we convert the input from pixel space to 3D normalized rays. This conversion makes our approach robust to camera intrinsic parameter changes. To deal with the in-the-wild camera extrinsic parameter variations, Ray3D explicitly takes the camera extrinsic parameters as an input and jointly models the distribution between the 3D pose rays and camera extrinsic parameters. This novel network design is the key to the outstanding generalizability of Ray3D approach. To have a comprehensive understanding of how the camera intrinsic and extrinsic parameter variations affect the accuracy of absolute 3D key-point localization, we conduct in-depth systematic experiments on three single person 3D benchmarks as well as one synthetic benchmark. These experiments demonstrate that our method significantly outperforms existing state-of-the-art models. Our code and the synthetic dataset are available at https://github.com/YxZhxn/Ray3D.
-
Top-down methods for monocular human mesh recovery have two stages: (1) detect human bounding boxes; (2) treat each bounding box as an independent single-human mesh recovery task. Unfortunately, the single-human assumption does not hold in images with multi-human occlusion and crowding. Consequently, top-down methods have difficulties in recovering accurate 3D human meshes under severe person-person occlusion. To address this, we present Occluded Human Mesh Recovery (OCHMR) - a novel top-down mesh recovery approach that incorporates image spatial context to overcome the limitations of the single-human assumption. The approach is conceptually simple and can be applied to any existing top-down architecture. Along with the input image, we condition the top-down model on spatial context from the image in the form of body-center heatmaps. To reason from the predicted body centermaps, we introduce Contextual Normalization (CoNorm) blocks to adaptively modulate intermediate features of the top-down model. The contextual conditioning helps our model disambiguate between two severely overlapping human bounding-boxes, making it robust to multi-person occlusion. Compared with state-of-the-art methods, OCHMR achieves superior performance on challenging multi-person benchmarks like 3DPW, CrowdPose, and OCHuman. Specifically, our proposed contextual reasoning architecture applied to the SPIN model with ResNet-50 backbone results in 75.2 PMPJPE on 3DPW-PC, 23.6 AP on CrowdPose, and 37.7 AP on OCHuman datasets, a significant improvement of 6.9 mm, 6.4 AP, and 20.8 AP respectively over the baseline. Code and models will be released.
-
Multi-object tracking in unmanned aerial vehicle (UAV) videos is an important vision task and can be applied in a wide range of applications. However, conventional multi-object trackers do not work well on UAV videos due to the challenging factors of irregular motion caused by moving camera and view change in 3D directions. In this paper, we propose a UAVMOT network specially for multi-object tracking in UAV views. The UAVMOT introduces an ID feature update module to enhance the object's feature association. To better handle the complex motions under UAV views, we develop an adaptive motion filter module. In addition, a gradient balanced focal loss is used to tackle the imbalance categories and small objects detection problem. Experimental results on the VisDrone2019 and UAVDT datasets demonstrate that the proposed UAVMOT achieves considerable improvement against the state-of-the-art tracking methods on UAV videos.
-
Weakly-supervised temporal action localization aims to recognize and localize action segments in untrimmed videos given only video-level action labels for training. Without the boundary information of action segments, existing methods mostly rely on multiple instance learning (MIL), where the predictions of unlabeled instances (i.e., video snippets) are supervised by classifying labeled bags (i.e., untrimmed videos). However, this formulation typically treats snippets in a video as independent instances, ignoring the underlying temporal structures within and across action segments. To address this problem, we propose \system, a novel WTAL framework that enables explicit, action-aware segment modeling beyond standard MIL-based methods. Our framework entails three segment-centric components: (i) dynamic segment sampling for compensating the contribution of short actions; (ii) intra- and inter-segment attention for modeling action dynamics and capturing temporal dependencies; (iii) pseudo instance-level supervision for improving action boundary prediction. Furthermore, a multi-step refinement strategy is proposed to progressively improve action proposals along the model training process. Extensive experiments on THUMOS-14 and ActivityNet-v1.3 demonstrate the effectiveness of our approach, establishing new state of the art on both datasets. The code and models are publicly available at https://github.com/boheumd/ASM-Loc.
-
A complex action consists of a sequence of atomic actions that interact with each other over a relatively long period of time. This paper introduces a probabilistic model named Uncertainty-Guided Probabilistic Transformer (UGPT) for complex action recognition. The self-attention mechanism of a Transformer is used to capture the complex and long-term dynamics of the complex actions. By explicitly modeling the distribution of the attention scores, we extend the deterministic Transformer to a probabilistic Transformer in order to quantify the uncertainty of the prediction. The model prediction uncertainty is used to improve both training and inference. Specifically, we propose a novel training strategy by introducing a majority model and a minority model based on the epistemic uncertainty. During the inference, the prediction is jointly made by both models through a dynamic fusion strategy. Our method is validated on the benchmark datasets, including Breakfast Actions, MultiTHUMOS, and Charades. The experiment results show that our model achieves the state-of-the-art performance under both sufficient and insufficient data.
-
We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small kernels could be a more powerful paradigm. We suggested five guidelines, e.g., applying re-parameterized large depth-wise convolutions, to design efficient high-performance large-kernel CNNs. Following the guidelines, we propose RepLKNet, a pure CNN architecture whose kernel size is as large as 31x31, in contrast to commonly used 3x3. RepLKNet greatly closes the performance gap between CNNs and ViTs, e.g., achieving comparable or superior results than Swin Transformer on ImageNet and a few typical downstream tasks, with lower latency. RepLKNet also shows nice scalability to big data and large models, obtaining 87.8% top-1 accuracy on ImageNet and 56.0% mIoU on ADE20K, which is very competitive among the state-of-the-arts with similar model sizes. Our study further reveals that, in contrast to small-kernel CNNs, large-kernel CNNs have much larger effective receptive fields and higher shape bias rather than texture bias. Code & models at https://github.com/megvii-research/RepLKNet.
-
Current methods of multi-person pose estimation typically treat the localization and association of body joints separately. In this paper, we propose the first fully end-to-end multi-person Pose Estimation framework with TRansformers, termed PETR. Our method views pose estimation as a hierarchical set prediction problem and effectively removes the need for many hand-crafted modules like RoI cropping, NMS and grouping post-processing. In PETR, multiple pose queries are learned to directly reason a set of full-body poses. Then a joint decoder is utilized to further refine the poses by exploring the kinematic relations between body joints. With the attention mechanism, the proposed method is able to adaptively attend to the features most relevant to target keypoints, which largely overcomes the feature misalignment difficulty in pose estimation and improves the performance considerably. Extensive experiments on the MS COCO and CrowdPose benchmarks show that PETR plays favorably against state-of-the-art approaches in terms of both accuracy and efficiency. The code and models are available at https://github.com/hikvision-research/opera.
-
Despite recent success in incorporating learning into point cloud registration, many works focus on learning feature descriptors and continue to rely on nearest-neighbor feature matching and outlier filtering through RANSAC to obtain the final set of correspondences for pose estimation. In this work, we conjecture that attention mechanisms can replace the role of explicit feature matching and RANSAC, and thus propose an end-to-end framework to directly predict the final set of correspondences. We use a network architecture consisting primarily of transformer layers containing self and cross attentions, and train it to predict the probability each point lies in the overlapping region and its corresponding position in the other point cloud. The required rigid transformation can then be estimated directly from the predicted correspondences without further post-processing. Despite its simplicity, our approach achieves state-of-the-art performance on 3DMatch and ModelNet benchmarks. Our source code can be found at https://github.com/yewzijian/RegTR.
-
This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view images. Many previous works have shown impressive reconstruction results on textured objects, but they still have difficulty in handling low-textured planar regions, which are common in indoor scenes. An approach to solving this issue is to incorporate planer constraints into the depth map estimation in multi-view stereo-based methods, but the per-view plane estimation and depth optimization lack both efficiency and multi-view consistency. In this work, we show that the planar constraints can be conveniently integrated into the recent implicit neural representation-based reconstruction methods. Specifically, we use an MLP network to represent the signed distance function as the scene geometry. Based on the Manhattan-world assumption, planar constraints are employed to regularize the geometry in floor and wall regions predicted by a 2D semantic segmentation network. To resolve the inaccurate segmentation, we encode the semantics of 3D points with another MLP and design a novel loss that jointly optimizes the scene geometry and semantics in 3D space. Experiments on ScanNet and 7-Scenes datasets show that the proposed method outperforms previous methods by a large margin on 3D reconstruction quality. The code and supplementary materials are available at https://zju3dv.github.io/manhattan_sdf.
-
Existing Voice Cloning (VC) tasks aim to convert a paragraph text to a speech with desired voice specified by a reference audio. This has significantly boosted the development of artificial speech applications. However, there also exist many scenarios that cannot be well reflected by these VC tasks, such as movie dubbing, which requires the speech to be with emotions consistent with the movie plots. To fill this gap, in this work we propose a new task named Visual Voice Cloning (V2C), which seeks to convert a paragraph of text to a speech with both desired voice specified by a reference audio and desired emotion specified by a reference video. To facilitate research in this field, we construct a dataset, V2C-Animation, and propose a strong baseline based on existing state-of-the-art (SoTA) VC techniques. Our dataset contains 10,217 animated movie clips covering a large variety of genres (e.g., Comedy, Fantasy) and emotions (e.g., happy, sad). We further design a set of evaluation metrics, named MCD-DTW-SL, which help evaluate the similarity between ground-truth speeches and the synthesised ones. Extensive experimental results show that even SoTA VC methods cannot generate satisfying speeches for our V2C task. We hope the proposed new task together with the constructed dataset and evaluation metric will facilitate the research in the field of voice cloning and broader vision-and-language community. Source code and dataset will be released in https://github.com/chenqi008/V2C.
-
Average precision (AP) loss has recently shown promising performance on the dense object detection task. However, a deep understanding of how AP loss affects the detector from a pairwise ranking perspective has not yet been developed. In this work, we revisit the average precision (AP) loss and reveal that the crucial element is that of selecting the ranking pairs between positive and negative samples. Based on this observation, we propose two strategies to improve the AP loss. The first of these is a novel Adaptive Pairwise Error (APE) loss that focusing on ranking pairs in both positive and negative samples. Moreover, we select more accurate ranking pairs by exploiting the normalized ranking scores and localization scores with a clustering algorithm. Experiments conducted on the MS-COCO dataset support our analysis and demonstrate the superiority of our proposed method compared with current classification and ranking loss. The code is available at https://github.com/Xudangliatiger/APE-Loss.
-
3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these models against real-world deformations must be addressed practically and reliably. In this work, we propose 3DeformRS, a method to certify the robustness of point cloud Deep Neural Networks (DNNs) against real-world deformations. We developed 3DeformRS by building upon recent work that generalized Randomized Smoothing (RS) from pixel-intensity perturbations to vector-field deformations. In particular, we specialized RS to certify DNNs against parameterized deformations (e.g. rotation, twisting), while enjoying practical computational costs. We leverage the virtues of 3DeformRS to conduct a comprehensive empirical study on the certified robustness of four representative point cloud DNNs on two datasets and against seven different deformations. Compared to previous approaches for certifying point cloud DNNs, 3DeformRS is fast, scales well with point cloud size, and provides comparable-to-better certificates. For instance, when certifying a plain PointNet against a 3deg z-rotation on 1024-point clouds, 3DeformRS grants a certificate 3x larger and 20x faster than previous work.
-
Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated motion capture systems. Therefore, we propose an unsupervised approach that learns to predict a 3D human pose from a single image while only being trained with 2D pose data, which can be crowd-sourced and is already widely available. To this end, we estimate the 3D pose that is most likely over random projections, with the likelihood estimated using normalizing flows on 2D poses. While previous work requires strong priors on camera rotations in the training data set, we learn the distribution of camera angles which significantly improves the performance. Another part of our contribution is to stabilize training with normalizing flows on high-dimensional 3D pose data by first projecting the 2D poses to a linear subspace. We outperform state-of-the-art in unsupervised human pose estimation on the benchmark dataset Human3.6M in all metrics.
-
The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques. In comparison, limited effort has been made at assessing the fitness of these datasets for the video-language grounding task. Recent works have begun to discover significant limitations in these datasets, suggesting that state-of-the-art techniques commonly overfit to hidden dataset biases. In this work, we present MAD (Movie Audio Descriptions), a novel benchmark that departs from the paradigm of augmenting existing video datasets with text annotations and focuses on crawling and aligning available audio descriptions of mainstream movies. MAD contains over 384,000 natural language sentences grounded in over 1,200 hours of videos and exhibits a significant reduction in the currently diagnosed biases for video-language grounding datasets. MAD's collection strategy enables a novel and more challenging version of video-language grounding, where short temporal moments (typically seconds long) must be accurately grounded in diverse long-form videos that can last up to three hours. We have released MAD's data and baselines code at https://github.com/Soldelli/MAD.
-
This paper proposes to use neuromorphic events for correcting rolling shutter (RS) images as consecutive global shutter (GS) frames. RS effect introduces edge distortion and region occlusion into images caused by row-wise readout of CMOS sensors. We introduce a novel computational imaging setup consisting of an RS sensor and an event sensor, and propose a neural network called EvUnroll to solve this problem by exploring the high-temporal-resolution property of events. We use events to bridge a spatio-temporal connection between RS and GS, establish a flow estimation module to correct edge distortions, and design a synthesis-based restoration module to restore occluded regions. The results of two branches are fused through a refining module to generate corrected GS images. We further propose datasets captured by a high-speed camera and an RS-Event hybrid camera system for training and testing our network. Experimental results on both public and proposed datasets show a systematic performance improvement compared to state-of-the-art methods.
-
Existing studies for gait recognition are dominated by 2D representations like the silhouette or skeleton of the human body in constrained scenes. However, humans live and walk in the unconstrained 3D space, so projecting the 3D human body onto the 2D plane will discard a lot of crucial information like the viewpoint, shape, and dynamics for gait recognition. Therefore, this paper aims to explore dense 3D representations for gait recognition in the wild, which is a practical yet neglected problem. In particular, we propose a novel framework to explore the 3D Skinned Multi-Person Linear (SMPL) model of the human body for gait recognition, named SMPLGait. Our framework has two elaborately-designed branches of which one extracts appearance features from silhouettes, the other learns knowledge of 3D viewpoints and shapes from the 3D SMPL model. In addition, due to the lack of suitable datasets, we build the first large-scale 3D representation-based gait recognition dataset, named Gait3D. It contains 4,000 subjects and over 25,000 sequences extracted from 39 cameras in an unconstrained indoor scene. More importantly, it provides 3D SMPL models recovered from video frames which can provide dense 3D information of body shape, viewpoint, and dynamics. Based on Gait3D, we comprehensively compare our method with existing gait recognition approaches, which reflects the superior performance of our framework and the potential of 3D representations for gait recognition in the wild. The code and dataset are available at: https://gait3d.github.io.
-
Estimating the articulated 3D hand-object pose from a single RGB image is a highly ambiguous and challenging problem, requiring large-scale datasets that contain diverse hand poses, object types, and camera viewpoints. Most real-world datasets lack these diversities. In contrast, data synthesis can easily ensure those diversities separately. However, constructing both valid and diverse hand-object interactions and efficiently learning from the vast synthetic data is still challenging. To address the above issues, we propose ArtiBoost, a lightweight online data enhancement method. ArtiBoost can cover diverse hand-object poses and camera viewpoints through sampling in a Composited hand-object Configuration and Viewpoint space (CCV-space) and can adaptively enrich the current hard-discernable items by loss-feedback and sample re-weighting. ArtiBoost alternatively performs data exploration and synthesis within a learning pipeline, and those synthetic data are blended into real-world source data for training. We apply ArtiBoost on a simple learning baseline network and witness the performance boost on several hand-object benchmarks. Our models and code are available at https://github.com/lixiny/ArtiBoost.
-
Temporal Context Matters: Enhancing Single Image Prediction With Disease Progression Representations
Clinical outcome or severity prediction from medical images has largely focused on learning representations from single-timepoint or snapshot scans. It has been shown that disease progression can be better characterized by temporal imaging. We therefore hypothesized that outcome predictions can be improved by utilizing the disease progression information from sequential images. We present a deep learning approach that leverages temporal progression information to improve clinical outcome predictions from single-timepoint images. In our method, a self-attention based Temporal Convolutional Network (TCN) is used to learn a representation that is most reflective of the disease trajectory. Meanwhile, a Vision Transformer is pretrained in a self-supervised fashion to extract features from single-timepoint images. The key contribution is to design a recalibration module that employs maximum mean discrepancy loss (MMD) to align distributions of the above two contextual representations. We train our system to predict clinical outcomes and severity grades from single-timepoint images. Experiments on chest and osteoarthritis radiography datasets demonstrate that our approach outperforms other state-of-the-art techniques.
-
While general object detection with deep learning has achieved great success in the past few years, the performance and efficiency of detecting small objects are far from satisfactory. The most common and effective way to promote small object detection is to use high-resolution images or feature maps. However, both approaches induce costly computation since the computational cost grows squarely as the size of images and features increases. To get the best of two worlds, we propose QueryDet that uses a novel query mechanism to accelerate the inference speed of feature-pyramid based object detectors. The pipeline composes two steps: it first predicts the coarse locations of small objects on low-resolution features and then computes the accurate detection results using high-resolution features sparsely guided by those coarse positions. In this way, we can not only harvest the benefit of high-resolution feature maps but also avoid useless computation for the background area. On the popular COCO dataset, the proposed method improves the detection mAP by 1.0 and mAP small by 2.0, and the high-resolution inference speed is improved to 3.0x on average. On VisDrone dataset, which contains more small objects, we create a new state-of-the-art while gaining a 2.3x high-resolution acceleration on average. Code is available at https://github.com/ ChenhongyiYang/QueryDet-PyTorch.
-
This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation. We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) and further reason that temporal irregularity and under-sampling are two major challenges. To tackle the challenges, we propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. Specifically, we propose a temporal consistency learning module to align two consecutive point cloud frames point-wisely, based on which we can employ linear interpolation to obtain coarse trajectories/in-between frames. To compensate the high-order nonlinear components of trajectories, we apply aligned feature embeddings that encode local geometry properties to regress point-wise increments, which are combined with the coarse estimations. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually. Our framework can bring benefits to 3D motion data acquisition. The source code is publicly available at https://github.com/ZENGYIMING-EAMON/IDEA-Net.git.
-
Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization performance of deep neural networks. To combat label noise, recent state-of-the-art methods employ some sort of sample selection mechanism to select a possibly clean subset of data. Next, an off-the-shelf semi-supervised learning method is used for training where rejected samples are treated as unlabeled data. Our comprehensive analysis shows that current selection methods disproportionately select samples from easy (fast learnable) classes while rejecting those from relatively harder ones. This creates class imbalance in the selected clean set and in turn, deteriorates performance under high label noise. In this work, we propose UNICON, a simple yet effective sample selection method which is robust to high label noise. To address the disproportionate selection of easy and hard samples, we introduce a Jensen-Shannon divergence based uniform selection mechanism which does not require any probabilistic modeling and hyperparameter tuning. We complement our selection method with contrastive learning to further combat the memorization of noisy labels. Extensive experimentation on multiple benchmark datasets demonstrates the effectiveness of UNICON; we obtain an 11.4% improvement over the current state-of-the-art on CIFAR100 dataset with a 90% noise rate. Our code is publicly available.
-
In this paper, we present a system to train driving policies from experiences collected not just from the ego-vehicle, but all vehicles that it observes. This system uses the behaviors of other agents to create more diverse driving scenarios without collecting additional data. The main difficulty in learning from other vehicles is that there is no sensor information. We use a set of supervisory tasks to learn an intermediate representation that is invariant to the viewpoint of the controlling vehicle. This not only provides a richer signal at training time but also allows more complex reasoning during inference. Learning how all vehicles drive helps predict their behavior at test time and can avoid collisions. We evaluate this system in closed-loop driving simulations. Our system outperforms all prior methods on the public CARLA Leaderboard by a wide margin, improving driving score by 25 and route completion rate by 24 points.
-
Modelling interactions between humans and objects in natural environments is central to many applications including gaming, virtual and mixed reality, as well as human behavior analysis and human-robot collaboration. This challenging operation scenario requires generalization to vast number of objects, scenes, and human actions. Unfortunately, there exist no such dataset. Moreover, this data needs to be acquired in diverse natural environments, which rules out 4D scanners and marker based capture systems. We present BEHAVE dataset, the first full body human-object interaction dataset with multi-view RGBD frames and corresponding 3D SMPL and object fits along with the annotated contacts between them. We record 15k frames at 5 locations with 8 subjects performing a wide range of interactions with 20 common objects. We use this data to learn a model that can jointly track humans and objects in natural environments with an easy-to-use portable multi-camera setup. Our key insight is to predict correspondences from the human and the object to a statistical body model to obtain human-object contacts during interactions. Our approach can record and track not just the humans and objects but also their interactions, modeled as surface contacts, in 3D. Our code and data can be found at: http://virtualhumans.mpi-inf.mpg.de/behave.
-
Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs which use neural 3D volumetric representations for synthesis. Images are synthesized by rendering the volumes from a given camera. These models can disentangle the 3D scene from the camera viewpoint in any generated image. However, most models do not disentangle other factors of image formation, such as geometry and appearance. In this paper, we design a 3D GAN which can learn a disentangled model of objects, just from monocular observations. Our model can disentangle the geometry and appearance variations in the scene, i.e., we can independently sample from the geometry and appearance spaces of the generative model. This is achieved using a novel non-rigid deformable scene formulation. A 3D volume which represents an object instance is computed as a non-rigidly deformed canonical 3D volume. Our method learns the canonical volume, as well as its deformations, jointly during training. This formulation also helps us improve the disentanglement between the 3D scene and the camera viewpoints using a novel pose regularization loss defined on the 3D deformation field. In addition, we further model the inverse deformations, enabling the computation of dense correspondences between images generated by our model. Finally, we design an approach to embed real images onto the latent space of our disentangled generative model, enabling editing of real images.
-
Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of neural networks. There has been a flurry of algorithms that try to solve this practical problem, each being claimed effective in some ways. Yet, a benchmark to compare those algorithms directly is lacking, mainly due to the complexity of the algorithms and some custom settings such as the particular network configuration or training procedure. A fair benchmark is important for the further development of channel pruning. Meanwhile, recent investigations reveal that the channel configurations discovered by pruning algorithms are at least as important as the pre-trained weights. This gives channel pruning a new role, namely searching the optimal channel configuration. In this paper, we try to determine the channel configuration of the pruned models by random search. The proposed approach provides a new way to compare different methods, namely how well they behave compared with random pruning. We show that this simple strategy works quite well compared with other channel pruning methods. We also show that under this setting, there are surprisingly no clear winners among different channel importance evaluation methods, which then may tilt the research efforts into advanced channel configuration searching methods. Code will be released at https://github.com/ofsoundof/random_channel_pruning.
-
How to achieve better results with fewer labeling costs remains a challenging task. In this paper, we present a new active learning framework, which for the first time incorporates contrastive learning into recently proposed one-bit supervision. Here one-bit supervision denotes a simple Yes or No query about the correctness of the model's prediction, and is more efficient than previous active learning methods requiring assigning accurate labels to the queried samples. We claim that such one-bit information is intrinsically in accordance with the goal of contrastive loss that pulls positive pairs together and pushes negative samples away. Towards this goal, we design an uncertainty metric to actively select samples for query. These samples are then fed into different branches according to the queried results. The Yes query is treated as positive pairs of the queried category for contrastive pulling, while the No query is treated as hard negative pairs for contrastive repelling. Additionally, we design a negative loss that penalizes the negative samples away from the incorrect predicted class, which can be treated as optimizing hard negatives for the corresponding category. Our method, termed as ObCP, produces a more powerful active learning framework, and experiments on several benchmarks demonstrate its superiority.
-
Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can only be trained on synthetic data due to the unavailability of large-scale in-the-wild egocentric datasets. Furthermore, these methods easily fail when the body parts are occluded by or interacting with the surrounding scene. To address the shortage of in-the-wild data, we collect a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW). This dataset is captured by a head-mounted fisheye camera and an auxiliary external camera, which provides an additional observation of the human body from a third-person perspective during training. We present a new egocentric pose estimation method, which can be trained on the new dataset with weak external supervision. Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision. The pseudo labels are then used to train an egocentric pose estimation network. To facilitate the network training, we propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. The experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.
-
Knowledge distillation has shown great effectiveness for improving neural architecture search (NAS). Mutual knowledge distillation (MKD), where a group of models mutually generate knowledge to train each other, has achieved promising results in many applications. In existing MKD methods, mutual knowledge distillation is performed between models without scrutiny: a worse-performing model is allowed to generate knowledge to train a better-performing model, which may lead to collective failures. To address this problem, we propose a performance-aware MKD (PAMKD) approach for NAS, where knowledge generated by model A is allowed to train model B only if the performance of A is better than B. We propose a three-level optimization framework to formulate PAMKD, where three learning stages are performed end-to-end: 1) each model trains an initial model independently; 2) the initial models are evaluated on a validation set and better-performing models generate knowledge to train worse-performing models; 3) architectures are updated by minimizing a validation loss. Experimental results on a variety of datasets demonstrate that our method is effective.
-
E-commerce images are playing a central role in attracting people's attention when retailing and shopping online, and an accurate attention prediction is of significant importance for both customers and retailers, where its research is yet to start. In this paper, we establish the first dataset of saliency e-commerce images (SalECI), which allows for learning to predict saliency on the e-commerce images. We then provide specialized and thorough analysis by highlighting the distinct features of e-commerce images, e.g., non-locality and correlation to text regions. Correspondingly, taking advantages of the non-local and self-attention mechanisms, we propose a salient SWin-Transformer backbone, followed by a multi-task learning with saliency and text detection heads, where an information flow mechanism is proposed to further benefit both tasks. Experimental results have verified the state-of-the-art performances of our work in the e-commerce scenario.
-
We present a new framework to learn dense 3D reconstruction and correspondence from a single 2D image. The shape is represented implicitly as deformation over a category-level occupancy field and learned in an unsupervised manner from an unaligned image collection without using any 3D supervision. However, image collections usually contain large intra-category topological variation, e.g. images of different chair instances, posing a major challenge. Hence, prior methods are either restricted only to categories with no topological variation for estimating shape and correspondence or focus only on learning shape independently for each instance without any correspondence. To address this issue, we propose a topologically-aware deformation field that maps 3D points in object space to a higher-dimensional canonical space. Given a single image, we first implicitly deform a 3D point in the object space to a learned category-specific canonical space using the topologically-aware field and then learn the 3D shape in the canonical space. Both the canonical shape and deformation field are trained end-to-end using differentiable rendering via learned recurrent ray marcher. Our approach, dubbed TARS, achieves state-of-the-art reconstruction fidelity on several datasets: ShapeNet, Pascal3D+, CUB, and Pix3D chairs.
-
Real-world image manipulation has achieved fantastic progress in recent years as a result of the exploration and utilization of GAN latent spaces. GAN inversion is the first step in this pipeline, which aims to map the real image to the latent code faithfully. Unfortunately, the majority of existing GAN inversion methods fail to meet at least one of the three requirements listed below: high reconstruction quality, editability, and fast inference. We present a novel two-phase strategy in this research that fits all requirements at the same time. In the first phase, we train an encoder to map the input image to StyleGAN2 W-space, which was proven to have excellent editability but lower reconstruction quality. In the second phase, we supplement the reconstruction ability in the initial phase by leveraging a series of hypernetworks to recover the missing information during inversion. These two steps complement each other to yield high reconstruction quality thanks to the hypernetwork branch and excellent editability due to the inversion done in the W-space. Our method is entirely encoder-based, resulting in extremely fast inference. Extensive experiments on two challenging datasets demonstrate the superiority of our method.
-
CRF is a classical computer vision model which is also useful for deep learning. There are two common CRF types: sparse and dense. Sparse CRF connects only the nearby pixels, while dense CRF has global connectivity. Therefore dense CRF is a more general model, but it is much harder to optimize compared to sparse CRF. In fact, only a certain form of dense CRF is optimized in practice, and even then approximately. We propose a new sparse non-local CRF: it has a sparse number of connections, but it has both local and non-local ones. Like sparse CRF, the total number of connections is small, and our model is easy to optimize exactly. Like dense CRF, our model is more general than sparse CRF due to non-local connections. We show that our sparse non-local CRF can model properties similar to that of the popular Gaussian edge dense CRF. Besides efficiency, another advantage is that our edge weights are less restricted compared to Gaussian edge dense CRF. We design models that take advantage of this flexibility. We also discuss connection of our model to other CRF models. Finally, to prove the usefulness of our model, we evaluate it on the classical application of segmentation from a bounding box and for deep learning based salient object segmentation. We improve state of the art for both applications.
-
Dataset distillation is the task of synthesizing a small dataset such that a model trained on the synthetic set will match the test accuracy of the model trained on the full dataset. The task is extremely challenging as it often involves backpropagating through the full training process or assuming the strong constraint that a single training step on distilled data can only imitate a single step on real data. In this paper, we propose a new formulation that optimizes our distilled data to guide networks to a similar state as those trained on real data across many training steps. Given a network, we train it for several iterations on our distilled data and optimize the distilled data with respect to the distance between the synthetically trained parameters and the parameters trained on real data. To efficiently obtain the initial and target network parameters for large-scale datasets, we pre-compute and store training trajectories of expert networks trained on the real dataset. Our method handily outperforms existing methods and also allows us to distill with higher-resolution visual data.
-
After the 2017 TuSimple Lane Detection Challenge, its dataset and evaluation based on accuracy and F1 score have become the de facto standard to measure the performance of lane detection methods. While they have played a major role in improving the performance of lane detection methods, the validity of this evaluation method in downstream tasks has not been adequately researched. In this study, we design 2 new driving-oriented metrics for lane detection: End-to-End Lateral Deviation metric (E2E-LD) is directly formulated based on the requirements of autonomous driving, a core task downstream of lane detection; Per-frame Simulated Lateral Deviation metric (PSLD) is a lightweight surrogate metric of E2E-LD. To evaluate the validity of the metrics, we conduct a large-scale empirical study with 4 major types of lane detection approaches on the TuSimple dataset and our newly constructed dataset Comma2k19-LD. Our results show that the conventional metrics have strongly negative correlations (<=-0.55) with E2E-LD, meaning that some recent improvements purely targeting the conventional metrics may not have led to meaningful improvements in autonomous driving, but rather may actually have made it worse by overfitting to the conventional metrics. On the contrary, PSLD shows statistically significant strong positive correlations (>=0.38) with E2E-LD. As a result, the conventional metrics tend to overestimate less robust models. As autonomous driving is a security/safety-critical system, the underestimation of robustness hinders the sound development of practical lane detection models. We hope that our study will help the community achieve more downstream task-aware evaluations for lane detection.
-
Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, so that 2D-3D point correspondences can be partly learned by backpropagating the gradient w.r.t. object pose. Yet, learning the entire set of unrestricted 2D-3D points from scratch fails to converge with existing approaches, since the deterministic pose is inherently non-differentiable. In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose on the SE(3) manifold, essentially bringing categorical Softmax to the continuous domain. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle unifies the existing approaches and resembles the attention mechanism. EPro-PnP significantly outperforms competitive baselines, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation and nuScenes 3D object detection benchmarks.
-
In some scenarios, classifier requires detecting out-of-distribution samples far from its training data. With desirable characteristics, reconstruction autoencoder-based methods deal with this problem by using input reconstruction error as a metric of novelty vs. normality. We formulate the essence of such approach as a quadruplet domain translation with an intrinsic bias to only query for a proxy of conditional data uncertainty. Accordingly, an improvement direction is formalized as maximumly compressing the autoencoder's latent space while ensuring its reconstructive power for acting as a described domain translator. From it, strategies are introduced including semantic reconstruction, data certainty decomposition and normalized L2 distance to substantially improve original methods, which together establish state-of-the-art performance on various benchmarks, e.g., the FPR@95%TPR of CIFAR-100 vs. TinyImagenet-crop on Wide-ResNet is 0.2%. Importantly, our method works without any additional data, hard-to-implement structure, time-consuming pipeline, and even harming the classification accuracy of known classes.
-
Many convolutional neural networks (CNNs) for single image deblurring employ a U-Net structure to estimate latent sharp images. Having long been proven to be effective in image restoration tasks, a single lane of encoder-decoder architecture overlooks the characteristic of deblurring, where a blurry image is generated from complicated blur kernels caused by tangled motions. Toward an effective network architecture, we present complemental sub-solutions learning with a one-encoder-two-decoder architecture for single image deblurring. Observing that multiple decoders successfully learn to decompose information in the encoded features into directional components, we further improve both the network efficiency and the deblurring performance by rotating and sharing kernels exploited in the decoders, which prevents the decoders from separating unnecessary components such as color shift. As a result, our proposed network shows superior results as compared to U-Net while preserving the network parameters, and the use of the proposed network as the base network can improve the performance of existing state-of-the-art deblurring networks.
-
Automated generation of 3D human motions from text is a challenging problem. The generated motions are expected to be sufficiently diverse to explore the text-grounded motion space, and more importantly, accurately depicting the content in prescribed text descriptions. Here we tackle this problem with a two-stage approach: text2length sampling and text2motion generation. Text2length involves sampling from the learned distribution function of motion lengths conditioned on the input text. This is followed by our text2motion module using temporal variational autoencoder to synthesize a diverse set of human motions of the sampled lengths. Instead of directly engaging with pose sequences, we propose motion snippet code as our internal motion representation, which captures local semantic motion contexts and is empirically shown to facilitate the generation of plausible motions faithful to the input text. Moreover, a large-scale dataset of scripted 3D Human motions, HumanML3D, is constructed, consisting of 14,616 motion clips and 44,970 text descriptions. Extensive empirical experiments demonstrate the effectiveness of our approach. Project webpage: https://ericguo5513.github.io/text-to-motion/.
-
A camera begins to sense light the moment we press the shutter button. During the exposure interval, relative motion between the scene and the camera causes motion blur, a common undesirable visual artifact. This paper presents E-CIR, which converts a blurry image into a sharp video represented as a parametric function from time to intensity. E-CIR leverages events as an auxiliary input. We discuss how to exploit the temporal event structure to construct the parametric bases. We demonstrate how to train a deep learning model to predict the function coefficients. To improve the appearance consistency, we further introduce a refinement module to propagate visual features among consecutive frames. Compared to state-of-the-art event-enhanced deblurring approaches, E-CIR generates smoother and more realistic results. The implementation of E-CIR is available at https://github.com/chensong1995/E-CIR.
-
Rain removal aims to remove rain streaks from images/videos and reduce the disruptive effects caused by rain. It not only enhances image/video visibility but also allows many computer vision algorithms to function properly. This paper makes the first attempt to conduct a comprehensive study on the robustness of deep learning-based rain removal methods against adversarial attacks. Our study shows that, when the image/video is highly degraded, rain removal methods are more vulnerable to the adversarial attacks as small distortions/perturbations become less noticeable or detectable. In this paper, we first present a comprehensive empirical evaluation of various methods at different levels of attacks and with various losses/targets to generate the perturbations from the perspective of human perception and machine analysis tasks. A systematic evaluation of key modules in existing methods is performed in terms of their robustness against adversarial attacks. From the insights of our analysis, we construct a more robust deraining method by integrating these effective modules. Finally, we examine various types of adversarial attacks that are specific to deraining problems and their effects on both human and machine vision tasks, including 1) rain region attacks, adding perturbations only in the rain regions to make the perturbations in the attacked rain images less visible; 2) object-sensitive attacks, adding perturbations only in regions near the given objects. Code is available at https://github.com/yuyi-sd/Robust_Rain_Removal.
-
Accurately detecting and tracking pedestrians in 3D space is challenging due to large variations in rotations, poses and scales. The situation becomes even worse for dense crowds with severe occlusions. However, existing benchmarks either only provide 2D annotations, or have limited 3D annotations with low-density pedestrian distribution, making it difficult to build a reliable pedestrian perception system especially in crowded scenes. To better evaluate pedestrian perception algorithms in crowded scenarios, we introduce a large-scale multimodal dataset, STCrowd. Specifically, in STCrowd, there are a total of 219K pedestrian instances and 20 persons per frame on average, with various levels of occlusion. We provide synchronized LiDAR point clouds and camera images as well as their corresponding 3D labels and joint IDs. STCrowd can be used for various tasks, including LiDAR-only, image-only, and sensor-fusion based pedestrian detection and tracking. We provide baselines for most of the tasks. In addition, considering the property of sparse global distribution and density-varying local distribution of pedestrians, we further propose a novel method, Density-aware Hierarchical heatmap Aggregation (DHA), to enhance pedestrian perception in crowded scenes. Extensive experiments show that our new method achieves state-of-the-art performance on the STCrowd dataset, especially on cases with severe occlusion. The dataset and code will be released to facilitate related research when the paper is published.
-
Advection-diffusion equations describe a large family of natural transport processes, e.g., fluid flow, heat transfer, and wind transport. They are also used for optical flow and perfusion imaging computations. We develop a machine learning model, D^2-SONATA, built upon a stochastic advection-diffusion equation, which predicts the velocity and diffusion fields that drive 2D/3D image time-series of transport. In particular, our proposed model incorporates a model of transport atypicality, which isolates abnormal differences between expected normal transport behavior and the observed transport. In a medical context such a normal-abnormal decomposition can be used, for example, to quantify pathologies. Specifically, our model identifies the advection and diffusion contributions from the transport time-series and simultaneously predicts an anomaly value field to provide a decomposition into normal and abnormal advection and diffusion behavior. To achieve improved estimation performance for the velocity and diffusion-tensor fields underlying the advection-diffusion process and for the estimation of the anomaly fields, we create a 2D/3D anomaly-encoded advection-diffusion simulator, which allows for supervised learning. We further apply our model on a brain perfusion dataset from ischemic stroke patients via transfer learning. Extensive comparisons demonstrate that our model successfully distinguishes stroke lesions (abnormal) from normal brain regions, while reconstructing the underlying velocity and diffusion tensor fields.
-
The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) with autoregressive models as generation part has yielded high-quality results on image generation. However, the autoregressive models will strictly follow the progressive scanning order during the sampling phase. This leads the existing VQ series models to hardly escape the trap of lacking global information. Denoising Diffusion Probabilistic Models (DDPM) in the continuous domain have shown a capability to capture the global context, while generating high-quality images. In the discrete state space, some works have demonstrated the potential to perform text generation and low resolution image generation. We show that with the help of a content-rich discrete visual codebook from VQ-VAE, the discrete diffusion model can also generate high fidelity images with global context, which compensates for the deficiency of the classical autoregressive model along pixel space. Meanwhile, the integration of the discrete VAE with the diffusion model resolves the drawback of conventional autoregressive models being oversized, and the diffusion model which demands excessive time in the sampling process when generating images. It is found that the quality of the generated images is heavily dependent on the discrete visual codebook. Extensive experiments demonstrate that the proposed Vector Quantised Discrete Diffusion Model (VQ-DDM) is able to achieve comparable performance to top-tier methods with low complexity. It also demonstrates outstanding advantages over other vectors quantised with autoregressive models in terms of image inpainting tasks without additional training.
-
We propose a keypoint-based object-level SLAM framework that can provide globally consistent 6DoF pose estimates for symmetric and asymmetric objects alike. To the best of our knowledge, our system is among the first to utilize the camera pose information from SLAM to provide prior knowledge for tracking keypoints on symmetric objects - ensuring that new measurements are consistent with the current 3D scene. Moreover, our semantic keypoint network is trained to predict the Gaussian covariance for the keypoints that captures the true error of the prediction, and thus is not only useful as a weight for the residuals in the system's optimization problems, but also as a means to detect harmful statistical outliers without choosing a manual threshold. Experiments show that our method provides competitive performance to the state of the art in 6DoF object pose estimation, and at a real-time speed. Our code, pre-trained models, and keypoint labels are available https://github.com/rpng/suo_slam.
-
Studying the inherent symmetry of data is of great importance in machine learning. Point cloud, the most important data format for 3D environmental perception, is naturally endowed with strong radial symmetry. In this work, we exploit this radial symmetry via a divide-and-conquer strategy to boost 3D perception performance and ease optimization. We propose Azimuth Normalization (AziNorm), which normalizes the point clouds along the radial direction and eliminates the variability brought by the difference of azimuth. AziNorm can be flexibly incorporated into most LiDAR-based perception methods. To validate its effectiveness and generalization ability, we apply AziNorm in both object detection and semantic segmentation. For detection, we integrate AziNorm into two representative detection methods, the one-stage SECOND detector and the state-of-the-art two-stage PV-RCNN detector. Experiments on Waymo Open Dataset demonstrate that AziNorm improves SECOND and PV-RCNN by 7.03 mAPH and 3.01 mAPH respectively. For segmentation, we integrate AziNorm into KPConv. On SemanticKitti dataset, AziNorm improves KPConv by 1.6/1.1 mIoU on val/test set. Besides, AziNorm remarkably improves data efficiency and accelerates convergence, reducing the requirement of data amounts or training epochs by an order of magnitude. SECOND w/ AziNorm can significantly outperform fully trained vanilla SECOND, even trained with only 10% data or 10% epochs. Code and models are available at https://github.com/hustvl/AziNorm.
-
Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation methods either ignore these cases altogether or only deliver a weak performance. We argue that this is due current methods only considering a single "true" depth, even when multiple objects at different depths contributed to the color of a single pixel. Based on the simple idea of outputting a posterior depth distribution instead of only a single estimate, we develop and explore several different deep-learning-based approaches to the problem. Additionally, we contribute the first "multimodal light field depth dataset" that contains the depths of all objects which contribute to the color of a pixel. This allows us to supervise the multimodal depth prediction and also validate all methods by measuring the KL divergence of the predicted posteriors. With our thorough analysis and novel dataset, we aim to start a new line of depth estimation research that overcomes some of the long-standing limitations of this field.
-
In this paper we consider the problem of classifying fine-grained, multi-step activities (e.g., cooking different recipes, making disparate home improvements, creating various forms of arts and crafts) from long videos spanning up to several minutes. Accurately categorizing these activities requires not only recognizing the individual steps that compose the task but also capturing their temporal dependencies. This problem is dramatically different from traditional action classification, where models are typically optimized on videos that span only a few seconds and that are manually trimmed to contain simple atomic actions. While step annotations could enable the training of models to recognize the individual steps of procedural activities, existing large-scale datasets in this area do not include such segment labels due to the prohibitive cost of manually annotating temporal boundaries in long videos. To address this issue, we propose to automatically identify steps in instructional videos by leveraging the distant supervision of a textual knowledge base (wikiHow) that includes detailed descriptions of the steps needed for the execution of a wide variety of complex activities. Our method uses a language model to match noisy, automatically-transcribed speech from the video to step descriptions in the knowledge base. We demonstrate that video models trained to recognize these automatically-labeled steps (without manual supervision) yield a representation that achieves superior generalization performance on four downstream tasks: recognition of procedural activities, step classification, step forecasting and egocentric video classification.
-
Recognition of materials from their visual appearance is essential for computer vision tasks, especially those that involve interaction with the real world. Material segmentation, i.e., dense per-pixel recognition of materials, remains challenging as, unlike objects, materials do not exhibit clearly discernible visual signatures in their regular RGB appearances. Different materials, however, do lead to different radiometric behaviors, which can often be captured with non-RGB imaging modalities. We realize multimodal material segmentation from RGB, polarization, and near-infrared images. We introduce the MCubeS dataset (from MultiModal Material Segmentation) which contains 500 sets of multimodal images capturing 42 street scenes. Ground truth material segmentation as well as semantic segmentation are annotated for every image and pixel. We also derive a novel deep neural network, MCubeSNet, which learns to focus on the most informative combinations of imaging modalities for each material class with a newly derived region-guided filter selection (RGFS) layer. We use semantic segmentation, as a prior to "guide" this filter selection. To the best of our knowledge, our work is the first comprehensive study on truly multimodal material segmentation. We believe our work opens new avenues of practical use of material information in safety critical applications.
-
Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching for self-supervised monocular depth estimation, and propose a novel transformer architecture for cost volume generation. We use depth-discretized epipolar sampling to select matching candidates, and refine predictions through a series of self- and cross-attention layers. These layers sharpen the matching probability between pixel features, improving over standard similarity metrics prone to ambiguities and local minima. The refined cost volume is decoded into depth estimates, and the whole pipeline is trained end-to-end from videos using only a photometric objective. Experiments on the KITTI and DDAD datasets show that our DepthFormer architecture establishes a new state of the art in self-supervised monocular depth estimation, and is even competitive with highly specialized supervised single-frame architectures. We also show that our learned cross-attention network yields representations transferable across datasets, increasing the effectiveness of pre-training strategies.
-
Object rotation is among long-standing, yet still unexplored, hard issues encountered in the task of weakly supervised object detection (WSOD) from aerial images. Existing predominant WSOD approaches built on regular CNNs which are not inherently designed to tackle object rotations without corresponding constraints, thereby leading to rotation-sensitive object detector. Meanwhile, current solutions have been prone to fall into the issue with unstable detectors, as they ignore lower-scored instances and may regard them as backgrounds. To address these issues, in this paper, we construct a novel end-to-end weakly supervised Rotation-Invariant aerial object detection Network (RINet). It is implemented with a flexible multi-branch online detector refinement, to be naturally more rotation-perceptive against oriented objects. Specifically, RINet first performs label propagating from the predicted instances to their rotated ones in a progressive refinement manner. Meanwhile, we propose to couple the predicted instance labels among different rotation-perceptive branches for generating rotation-consistent supervision and meanwhile pursuing all possible instances. With the rotation-consistent supervisions, RINet enforces and encourages consistent yet complementary feature learning for WSOD without additional annotations and hyper-parameters. On the challenging NWPU VHR-10.v2 and DIOR datasets, extensive experiments clearly demonstrate that we significantly boost existing WSOD methods to a new state-of-the-art performance. The code will be available at: https://github.com/XiaoxFeng/RINet.
-
Text-based video segmentation aims to segment the target object in a video based on a describing sentence. Incorporating motion information from optical flow maps with appearance and linguistic modalities is crucial yet has been largely ignored by previous work. In this paper, we design a method to fuse and align appearance, motion, and linguistic features to achieve accurate segmentation. Specifically, we propose a multi-modal video transformer, which can fuse and aggregate multi-modal and temporal features between frames. Furthermore, we design a language-guided feature fusion module to progressively fuse appearance and motion features in each feature level with guidance from linguistic features. Finally, a multi-modal alignment loss is proposed to alleviate the semantic gap between features from different modalities. Extensive experiments on A2D Sentences and J-HMDB Sentences verify the performance and the generalization ability of our method compared to the state-of-the-art methods.
-
Surface reconstruction from point clouds is vital for 3D computer vision. State-of-the-art methods leverage large datasets to first learn local context priors that are represented as neural network-based signed distance functions (SDFs) with some parameters encoding the local contexts. To reconstruct a surface at a specific query location at inference time, these methods then match the local reconstruction target by searching for the best match in the local prior space (by optimizing the parameters encoding the local context) at the given query location. However, this requires the local context prior to generalize to a wide variety of unseen target regions, which is hard to achieve. To resolve this issue, we introduce Predictive Context Priors by learning Predictive Queries for each specific point cloud at inference time. Specifically, we first train a local context prior using a large point cloud dataset similar to previous techniques. For surface reconstruction at inference time, however, we specialize the local context prior into our Predictive Context Prior by learning Predictive Queries, which predict adjusted spatial query locations as displacements of the original locations. This leads to a global SDF that fits the specific point cloud the best. Intuitively, the query prediction enables us to flexibly search the learned local context prior over the entire prior space, rather than being restricted to the fixed query locations, and this improves the generalizability. Our method does not require ground truth signed distances, normals, or any additional procedure of signed distance fusion across overlapping regions. Our experimental results in surface reconstruction for single shapes or complex scenes show significant improvements over the state-of-the-art under widely used benchmarks. Code and data are available at https://github.com/mabaorui/PredictableContextPrior.
-
Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare patches within and across frames. These fixed attention schemes not only have high computational cost but, by comparing patches at predetermined locations, they neglect the motion dynamics in the video. In this paper, we introduce the Deformable Video Transformer (DVT), which dynamically predicts a small subset of video patches to attend for each query location based on motion information, thus allowing the model to decide where to look in the video based on correspondences across frames. Crucially, these motion-based correspondences are obtained at zero-cost from information stored in the compressed format of the video. Our deformable attention mechanism is optimized directly with respect to classification performance, thus eliminating the need for suboptimal hand-design of attention strategies. Experiments on four large-scale video benchmarks (Kinetics-400, Something-Something-V2, EPIC-KITCHENS and Diving-48) demonstrate that, compared to existing video transformers, our model achieves higher accuracy at the same or lower computational cost, and it attains state-of-the-art results on these four datasets.
-
We propose a method for learning the posture and structure of agents from unlabelled behavioral videos. Starting from the observation that behaving agents are generally the main sources of movement in behavioral videos, our method, Behavioral Keypoint Discovery (B-KinD), uses an encoder-decoder architecture with a geometric bottleneck to reconstruct the spatiotemporal difference between video frames. By focusing only on regions of movement, our approach works directly on input videos without requiring manual annotations. Experiments on a variety of agent types (mouse, fly, human, jellyfish, and trees) demonstrate the generality of our approach and reveal that our discovered keypoints represent semantically meaningful body parts, which achieve state-of-the-art performance on keypoint regression among self-supervised methods. Additionally, B-KinD achieve comparable performance to supervised keypoints on downstream tasks, such as behavior classification, suggesting that our method can dramatically reduce model training costs vis-a-vis supervised methods.
-
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible and invisible light sources require reasoning about long-range interactions for inverse rendering, which seeks to recover the components of image formation, namely, shape, material, and lighting. In this work, our intuition is that the long-range attention learned by transformer architectures is ideally suited to solve longstanding challenges in single-image inverse rendering. We demonstrate with a specific instantiation of a dense vision transformer, \Ours , that excels at both single-task and multi-task reasoning required for inverse rendering. Specifically, we propose a transformer architecture to simultaneously estimate depths, normals, spatially-varying albedo, roughness and lighting from a single image of an indoor scene. Our extensive evaluations on benchmark datasets demonstrate state-of-the-art results on each of the above tasks, enabling applications like object insertion and material editing in a single unconstrained real image, with greater photorealism than prior works. Code and data are publicly released at https://github.com/ViLab-UCSD/IRISformer
-
Earth observation is a fundamental tool for monitoring the evolution of land use in specific areas of interest. Observing and precisely defining change, in this context, requires both time-series data and pixel-wise segmentations. To that end, we propose the DynamicEarthNet dataset that consists of daily, multi-spectral satellite observations of 75 selected areas of interest distributed over the globe with imagery from Planet Labs. These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes. DynamicEarthNet is the first dataset that provides this unique combination of daily measurements and high-quality labels. In our experiments, we compare several established baselines that either utilize the daily observations as additional training data (semi-supervised learning) or multiple observations at once (spatio-temporal learning) as a point of reference for future research. Finally, we propose a new evaluation metric SCS that addresses the specific challenges associated with time-series semantic change segmentation. The data is available at: https://mediatum.ub.tum.de/1650201.
-
We attempt to connect the data from complementary views, i.e., top view from drone-mounted cameras in the air, and side view from wearable cameras on the ground. Collaborative analysis of such complementary-view data can facilitate to build the air-ground cooperative visual system for various kinds of applications. This is a very challenging problem due to the large view difference between top and side views. In this paper, we develop a new approach that can simultaneously handle three tasks: i) localizing the side-view camera in the top view; ii) estimating the view direction of the side-view camera; iii) detecting and associating the same subjects on the ground across the complementary views. Our main idea is to explore the spatial position layout of the subjects in two views. In particular, we propose a spatial-aware position representation method to embed the spatial-position distribution of the subjects in different views. We further design a cross-view video collaboration framework composed of a camera identification module and a subject association module to simultaneously perform the above three tasks. We collect a new synthetic dataset consisting of top-view and side-view video sequence pairs for performance evaluation and the experimental results show the effectiveness of the proposed method.
-
In this paper, we aim to forecast a future trajectory distribution of a moving agent in the real world, given the social scene images and historical trajectories. Yet, it is a challenging task because the ground-truth distribution is unknown and unobservable, while only one of its samples can be applied for supervising model learning, which is prone to bias. Most recent works focus on predicting diverse trajectories in order to cover all modes of the real distribution, but they may despise the precision and thus give too much credit to unrealistic predictions. To address the issue, we learn the distribution with symmetric cross-entropy using occupancy grid maps as an explicit and scene-compliant approximation to the ground-truth distribution, which can effectively penalize unlikely predictions. In specific, we present an inverse reinforcement learning based multi-modal trajectory distribution forecasting framework that learns to plan by an approximate value iteration network in an end-to-end manner. Besides, based on the predicted distribution, we generate a small set of representative trajectories through a differentiable Transformer-based network, whose attention mechanism helps to model the relations of trajectories. In experiments, our method achieves state-of-the-art performance on the Stanford Drone Dataset and Intersection Drone Dataset.
-
Previous partial permutation synchronization (PPS) algorithms, which are commonly used for multi-object matching, often involve computation-intensive and memory-demanding matrix operations. These operations become intractable for large scale structure-from-motion datasets. For pure permutation synchronization, the recent Cycle-Edge Message Passing (CEMP) framework suggests a memory-efficient and fast solution. Here we overcome the restriction of CEMP to compact groups and propose an improved algorithm, CEMP-Partial, for estimating the corruption levels of the observed partial permutations. It allows us to subsequently implement a nonconvex weighted projected power method without the need of spectral initialization. The resulting new PPS algorithm, MatchFAME (Fast, Accurate and Memory-Efficient Matching), only involves sparse matrix operations, and thus enjoys lower time and space complexities in comparison to previous PPS algorithms. We prove that under adversarial corruption, though without additive noise and with certain assumptions, CEMP-Partial is able to exactly classify corrupted and clean partial permutations. We demonstrate the state-of-the-art accuracy, speed and memory efficiency of our method on both synthetic and real datasets.
-
Diffractive snapshot hyperspectral imaging based on the deep optics framework has been striving to capture the spectral images of dynamic scenes. However, existing deep optics frameworks all suffer from the mismatch between the optical hardware and the reconstruction algorithm due to the quantization operation in the diffractive optical element (DOE) fabrication, leading to the limited performance of hyperspectral imaging in practice. In this paper, we propose the quantization-aware deep optics for diffractive snapshot hyperspectral imaging. Our key observation is that common lithography techniques used in fabricating DOEs need to quantize the DOE height map to a few levels, and can freely set the height for each level. Therefore, we propose to integrate the quantization operation into the DOE height map optimization and design an adaptive mechanism to adjust the physical height of each quantization level. According to the optimization, we fabricate the quantized DOE directly and build a diffractive hyperspectral snapshot imaging system. Our method develops the deep optics framework to be more practical through the awareness of and adaptation to the quantization operation of the DOE physical structure, making the fabricated DOE and the reconstruction algorithm match each other systematically. Extensive synthetic simulation and real hardware experiments validate the superior performance of our method.
-
Weakly supervised temporal action localization targets at localizing temporal boundaries of actions and simultaneously identify their categories with only video-level category labels. Many existing methods seek to generate pseudo labels for bridging the discrepancy between classification and localization, but usually only make use of limited contextual information for pseudo label generation. To alleviate this problem, we propose a representative snippet summarization and propagation framework. Our method seeks to mine the representative snippets in each video for better propagating information between video snippets. For each video, its own representative snippets and the representative snippets from a memory bank are propagated to update the input features in an intra- and inter-video manner. The pseudo labels are generated from the temporal class activation maps of the updated features to rectify the predictions of the main branch. Our method obtains superior performance in comparison to the existing methods on two benchmarks, THUMOS14 and ActivityNet1.3, achieving gains as high as 1.2% in terms of average mAP on THUMOS14. Our code is available at https://github.com/LeonHLJ/RSKP.
-
The wavelet scattering transform creates geometric invariants and deformation stability. In multiple signal domains, it has been shown to yield more discriminative representations compared to other non-learned representations and to outperform learned representations in certain tasks, particularly on limited labeled data and highly structured signals. The wavelet filters used in the scattering transform are typically selected to create a tight frame via a parameterized mother wavelet. In this work, we investigate whether this standard wavelet filterbank construction is optimal. Focusing on Morlet wavelets, we propose to learn the scales, orientations, and aspect ratios of the filters to produce problem-specific parameterizations of the scattering transform. We show that our learned versions of the scattering transform yield significant performance gains in small-sample classification settings over the standard scattering transform. Moreover, our empirical results suggest that traditional filterbank constructions may not always be necessary for scattering transforms to extract effective representations.
-
Sketch-based image manipulation is an interactive image editing task to modify an image based on input sketches from users. Existing methods typically convert this task into a conditional inpainting problem, which requires an additional mask from users indicating the region to modify. Then the masked regions are regarded as missing and filled by an inpainting model conditioned on the sketch. With this formulation, paired training data can be easily obtained by randomly creating masks and extracting edges or contours. Although this setup simplifies data preparation and model design, it complicates user interaction and discards useful information in masked regions. To this end, we propose a new framework for sketch-based image manipulation that only requires sketch inputs from users and utilizes the entire original image. Given an image and sketch, our model automatically predicts the target modification region and encodes it into a structure agnostic style vector. A generator then synthesizes the new image content based on the style vector and sketch. The manipulated image is finally produced by blending the generator output into the modification region of the original image. Our model can be trained in a self-supervised fashion by learning the reconstruction of an image region from the style vector and sketch. The proposed framework offers simpler and more intuitive user workflows for sketch-based image manipulation and provides better results than previous approaches. The code and interactive demo can be found in the supplementary material.
-
In this paper, we address the problem of estimating scale factors between images. We formulate the scale estimation problem as a prediction of a probability distribution over scale factors. We design a new architecture, ScaleNet, that exploits dilated convolutions as well as self- and cross-correlation layers to predict the scale between images. We demonstrate that rectifying images with estimated scales leads to significant performance improvements for various tasks and methods. Specifically, we show how ScaleNet can be combined with sparse local features and dense correspondence networks to improve camera pose estimation, 3D reconstruction, or dense geometric matching in different benchmarks and datasets. We provide an extensive evaluation on several tasks, and analyze the computational overhead of ScaleNet. The code, evaluation protocols, and trained models are publicly available.
-
Contour-based instance segmentation methods have developed rapidly recently but feature rough and handcrafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label vertex pairing, which contributes to the learning difficulty. In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation. Firstly, E2EC applies a novel learnable contour initialization architecture instead of handcrafted contour initialization. This consists of a contour initialization module for constructing more explicit learning goals and a global contour deformation module for taking advantage of all of the vertices' features better. Secondly, we propose a novel label sampling scheme, named multi-direction alignment, to reduce the learning difficulty. Thirdly, to improve the quality of the boundary details, we dynamically match the most appropriate predicted-ground truth vertex pairs and propose the corresponding loss function named dynamic matching loss. The experiments showed that E2EC can achieve a state-of-the-art performance on the KITTI INStance (KINS) dataset, the Semantic Boundaries Dataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient for use in real-time applications, with an inference speed of 36 fps for 512x512 images on an NVIDIA A6000 GPU. Code will be released at https://github.com/zhang-tao-whu/e2ec.
-
We propose a novel adversarial attack targeting content features in some deep layer, that is, individual neurons in the layer. A naive method that enforces a fixed value/percentage bound for neuron activation values can hardly work and generates very noisy samples. The reason is that the level of perceptual variation entailed by a fixed value bound is non-uniform across neurons and even for the same neuron. We hence propose a novel distribution quantile bound for activation values and a polynomial barrier loss function. Given a benign input, a fixed quantile bound is translated to many value bounds, one for each neuron, based on the distributions of the neuron's activations and the current activation value on the given input. These individualized bounds enable fine-grained regulation, allowing content feature mutations with bounded perceptional variations. Our evaluation on ImageNet and five different model architectures demonstrates that our attack is effective. Compared to seven other latest adversarial attacks in both the pixel space and the feature space, our attack can achieve the state-of-the-art trade-off between attack success rate and imperceptibility.
-
Despite the success of deep neural networks, there are still many challenges in deep representation learning due to the data scarcity issues such as data imbalance, unseen distribution, and domain shift. To address the above-mentioned issues, a variety of methods have been devised to explore the sample relationships in a vanilla way (i.e., from the perspectives of either the input or the loss function), failing to explore the internal structure of deep neural networks for learning with sample relationships. Inspired by this, we propose to enable deep neural networks themselves with the ability to learn the sample relationships from each mini-batch. Specifically, we introduce a batch transformer module or BatchFormer, which is then applied into the batch dimension of each mini-batch to implicitly explore sample relationships during training. By doing this, the proposed method enables the collaboration of different samples, e.g., the head-class samples can also contribute to the learning of the tail classes for long-tailed recognition. Furthermore, to mitigate the gap between training and testing, we share the classifier between with or without the BatchFormer during training, which can thus be removed during testing. We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications without any bells and whistles, including the tasks of long-tailed recognition, compositional zero-shot learning, domain generalization, and contrastive learning. Code is made publicly available at https://github.com/zhihou7/BatchFormer.
-
Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has attracted much attention due to low annotation costs. Existing methods often rely on Class Activation Mapping (CAM) that measures the correlation between image pixels and classifier weight. However, the classifier focuses only on the discriminative regions while ignoring other useful information in each image, resulting in incomplete localization maps. To address this issue, we propose a Self-supervised Image-specific Prototype Exploration (SIPE) that consists of an Image-specific Prototype Exploration (IPE) and a General-Specific Consistency (GSC) loss. Specifically, IPE tailors prototypes for every image to capture complete regions, formed our Image-Specific CAM (IS-CAM). GSC is proposed to construct the consistency of general CAM and our specific IS-CAM, which further optimizes the feature representation and empowers a self-correction ability of prototype exploration. Extensive experiments are conducted on PASCAL VOC 2012 and MS COCO 2014 segmentation benchmark and results show our SIPE achieves new state-of-the-art performance using only image-level labels. The code is available at https://github.com/chenqi1126/SIPE.
-
Few-shot classification is a challenging problem that aims to learn a model that can adapt to unseen classes given a few labeled samples. Recent approaches pre-train a feature extractor, and then fine-tune for episodic meta-learning. Other methods leverage spatial features to learn pixel-level correspondence while jointly training a classifier. However, results using such approaches show marginal improvements. In this paper, inspired by the transformer style self-attention mechanism, we propose a strategy to cross-attend and re-weight discriminative features for few-shot classification. Given a base representation of support and query images after global pooling, we introduce a single shared module that projects features and cross-attends in two aspects: (i) query to support, and (ii) support to query. The module computes attention scores between features to produce an attention pooled representation of features in the same class that is later added to the original representation followed by a projection head. This effectively re-weights features in both aspects (i & ii) to produce features that better facilitate improved metric-based meta-learning. Extensive experiments on public benchmarks show our approach outperforms state-of-the-art methods by 3% 5%.
-
In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks. Our key insight is that the profile of a DNN model's decision boundary can be uniquely characterized by its Universal Adversarial Perturbations (UAPs). UAPs belong to a low-dimensional subspace and piracy models' subspaces are more consistent with victim model's subspace compared with non-piracy model. Based on this, we propose a UAP fingerprinting method for DNN models and train an encoder via contrastive learning that takes fingerprint as inputs, outputs a similarity score. Extensive studies show that our framework can detect model IP breaches with confidence > 99.99% within only 20 fingerprints of the suspect model. It has good generalizability across different model architectures and is robust against post-modifications on stolen models.
-
Recent works on 3D semantic segmentation propose to exploit the synergy between images and point clouds by processing each modality with a dedicated network and projecting learned 2D features onto 3D points. Merging large-scale point clouds and images raises several challenges, such as constructing a mapping between points and pixels, and aggregating features between multiple views. Current methods require mesh reconstruction or specialized sensors to recover occlusions, and use heuristics to select and aggregate available images. In contrast, we propose an end-to-end trainable multi-view aggregation model leveraging the viewing conditions of 3D points to merge features from images taken at arbitrary positions. Our method can combine standard 2D and 3D networks and outperforms both 3D models operating on colorized point clouds and hybrid 2D/3D networks without requiring colorization, meshing, or true depth maps. We set a new state-of-the-art for large-scale indoor/outdoor semantic segmentation on S3DIS (74.7 mIoU 6-Fold) and on KITTI-360 (58.3 mIoU). Our full pipeline is accessible at https://github.com/drprojects/DeepViewAgg, and only requires raw 3D scans and a set of images and poses.
-
Existing text-guided image manipulation methods aim to modify the appearance of the image or to edit a few objects in a virtual or simple scenario, which is far from practical application. In this work, we study a novel task on text-guided image manipulation on the entity level in the real world. The task imposes three basic requirements, (1) to edit the entity consistent with the text descriptions, (2) to preserve the text-irrelevant regions, and (3) to merge the manipulated entity into the image naturally. To this end, we propose a new transformer-based framework based on the two-stage image synthesis method, namely ManiTrans, which can not only edit the appearance of entities but also generate new entities corresponding to the text guidance. Our framework incorporates a semantic alignment module to locate the image regions to be manipulated, and a semantic loss to help align the relationship between the vision and language. We conduct extensive experiments on the real datasets, CUB, Oxford, and COCO datasets to verify that our method can distinguish the relevant and irrelevant regions and achieve more precise and flexible manipulation compared with baseline methods.
-
Temporal modeling is an essential element in video understanding. While deep convolution-based architectures have been successful at solving large-scale video recognition datasets, recent work has pointed out that they are biased towards modeling short-range relations, often failing to capture long-term temporal structures in the videos, leading to poor transfer and generalization to new datasets. In this work, the problem of dynamic representation learning (DRL) is studied. We propose dynamic score, a measure of video dynamic modeling that describes the additional amount of information learned by a video network that cannot be captured by pure spatial student through knowledge distillation. DRL is then formulated as an adversarial learning problem between the video and spatial models, with the objective of maximizing the dynamic score of learned spatiotemporal classifier. The quality of learned video representations are evaluated on a diverse set of transfer learning problems concerning many-shot and few-shot action classification. Experimental results show that models learned with DRL outperform baselines in dynamic modeling, demonstrating higher transferability and generalization capacity to novel domains and tasks.
-
Intrinsic image decomposition is the process of recovering the image formation components (reflectance and shading) from an image. Previous methods employ either explicit priors to constrain the problem or implicit constraints as formulated by their losses (deep learning). These methods can be negatively influenced by strong illumination conditions causing shading-reflectance leakages. Therefore, in this paper, an end-to-end edge-driven hybrid CNN approach is proposed for intrinsic image decomposition. Edges correspond to illumination invariant gradients. To handle hard negative illumination transitions, a hierarchical approach is taken including global and local refinement layers. We make use of attention layers to further strengthen the learning process. An extensive ablation study and large scale experiments are conducted showing that it is beneficial for edge-driven hybrid IID networks to make use of illumination invariant descriptors and that separating global and local cues helps in improving the performance of the network. Finally, it is shown that the proposed method obtains state of the art performance and is able to generalise well to real world images. The project page with pretrained models, finetuned models and network code can be found at: https://ivi.fnwi.uva.nl/cv/pienet/
-
The key to address clothes-changing person re-identification (re-id) is to extract clothes-irrelevant features, e.g., face, hairstyle, body shape, and gait. Most current works mainly focus on modeling body shape from multi-modality information (e.g., silhouettes and sketches), but do not make full use of the clothes-irrelevant information in the original RGB images. In this paper, we propose a Clothes-based Adversarial Loss (CAL) to mine clothes-irrelevant features from the original RGB images by penalizing the predictive power of re-id model w.r.t. clothes. Extensive experiments demonstrate that using RGB images only, CAL outperforms all state-of-the-art methods on widely-used clothes-changing person re-id benchmarks. Besides, compared with images, videos contain richer appearance and additional temporal information, which can be used to model proper spatiotemporal patterns to assist clothes-changing re-id. Since there is no publicly available clothes-changing video re-id dataset, we contribute a new dataset named CCVID and show that there exists much room for improvement in modeling spatiotemporal information. The code and new dataset are available at: https://github.com/guxinqian/Simple-CCReID.
-
Current stereo matching techniques are challenged by restricted searching space, occluded regions and sheer size. While single image depth estimation is spared from these challenges and can achieve satisfactory results with the extracted monocular cues, the lack of stereoscopic relationship renders the monocular prediction less reliable on its own, especially in highly dynamic or cluttered environments. To address these issues in both scenarios, we present an optic-chiasm-inspired self-supervised binocular depth estimation method, wherein a vision transformer (ViT) with gated positional cross-attention (GPCA) layers is designed to enable feature-sensitive pattern retrieval between views while retaining the extensive context information aggregated through self-attentions. Monocular cues from a single view are thereafter conditionally rectified by a blending layer with the retrieved pattern pairs. This crossover design is biologically analogous to the optic-chasma structure in the human visual system and hence the name, ChiTransformer. Our experiments show that this architecture yields substantial improvements over state-of-the-art self-supervised stereo approaches by 11%, and can be used on both rectilinear and non-rectilinear (e.g., fisheye) images.
-
The increasing abuse of image editing softwares, such as Photoshop and Meitu, causes the authenticity of digital images questionable. Meanwhile, the widespread availability of online social networks (OSNs) makes them the dominant channels for transmitting forged images to report fake news, propagate rumors, etc. Unfortunately, various lossy operations adopted by OSNs, e.g., compression and resizing, impose great challenges for implementing the robust image forgery detection. To fight against the OSN-shared forgeries, in this work, a novel robust training scheme is proposed. We first conduct a thorough analysis of the noise introduced by OSNs, and decouple it into two parts, i.e., predictable noise and unseen noise, which are modelled separately. The former simulates the noise introduced by the disclosed (known) operations of OSNs, while the latter is designed to not only complete the previous one, but also take into account the defects of the detector itself. We then incorporate the modelled noise into a robust training framework, significantly improving the robustness of the image forgery detector. Extensive experimental results are presented to validate the superiority of the proposed scheme compared with several state-of-the-art competitors. Finally, to promote the future development of the image forgery detection, we build a public forgeries dataset based on four existing datasets and three most popular OSNs. The designed detector recently won the top ranking in a certificate forgery detection competition. The source code and dataset are available at https://github.com/HighwayWu/ImageForensicsOSN.
-
Unpaired image-to-image (I2I) translation often requires to maximize the mutual information between the source and the translated images across different domains, which is critical for the generator to keep the source content and prevent it from unnecessary modifications. The self-supervised contrastive learning has already been successfully applied in the I2I. By constraining features from the same location to be closer than those from different ones, it implicitly ensures the result to take content from the source. However, previous work uses the features from random locations to impose the constraint, which may not be appropriate since some locations contain less information of source domain. Moreover, the feature itself does not reflect the relation with others. This paper deals with these problems by intentionally selecting significant anchor points for contrastive learning. We design a query-selected attention (QS-Attn) module, which compares feature distances in the source domain, giving an attention matrix with a probability distribution in each row. Then we select queries according to their measurement of significance, computed from the distribution. The selected ones are regarded as anchors for contrastive loss. At the same time, the reduced attention matrix is employed to route features in both domains, so that source relations maintain in the synthesis. We validate our proposed method in three different I2I datasets, showing that it increases the image quality without adding learnable parameters.
-
Learning-based image dehazing methods have achieved marvelous progress during the past few years. On one hand, most approaches heavily rely on synthetic data and may face difficulties to generalize well in real scenes, due to the huge domain gap between synthetic and real images. On the other hand, very few works have considered the varicolored haze, caused by chromatic casts in real scenes. In this work, our goal is to handle the new task: real-world varicolored haze removal. To this end, we propose a physically disentangled joint intra- and inter-domain adaptation paradigm, in which intra-domain adaptation focuses on color correction and inter-domain procedure transfers knowledge between synthetic and real domains. We first learn to physically disentangle haze images into three components complying with the scattering model: background, transmission map, and atmospheric light. Since haze color is determined by atmospheric light, we perform intra-domain adaptation by specifically translating atmospheric light from varicolored space to unified color-balanced space, and then reconstructing color-balanced haze image through the scattering model. Consequently, we perform inter-domain adaptation between the synthetic and real images by mutually exchanging the background and other two components. Then we can reconstruct both identity and domain-translated haze images with self-consistency and adversarial loss. Extensive experiments demonstrate the superiority of the proposed method over the state-of-the-art for real varicolored image dehazing.
-
Fusion of multiple sensor modalities such as camera, Lidar, and Radar, which are commonly found on autonomous vehicles, not only allows for accurate detection but also robustifies perception against adverse weather conditions and individual sensor failures. Due to inherent sensor characteristics, Radar performs well under extreme weather conditions (snow, rain, fog) that significantly degrade camera and Lidar. Recently, a few works have developed vehicle detection methods fusing Lidar and Radar signals, i.e., MVDNet. However, these models are typically developed under the assumption that the models always have access to two error-free sensor streams. If one of the sensors is unavailable or missing, the model may fail catastrophically. To mitigate this problem, we propose the Self-Training Multimodal Vehicle Detection Network (ST-MVDNet) which leverages a Teacher-Student mutual learning framework and a simulated sensor noise model used in strong data augmentation for Lidar and Radar. We show that by (1) enforcing output consistency between a Teacher network and a Student network and by (2) introducing missing modalities (strong augmentations) during training, our learned model breaks away from the error-free sensor assumption. This consistency enforcement enables the Student model to handle missing data properly and improve the Teacher model by updating it with the Student model's exponential moving average. Our experiments demonstrate that our proposed learning framework for multi-modal detection is able to better handle missing sensor data during inference. Furthermore, our method achieves new state-of-the-art performance (5% gain) on the Oxford Radar Robotcar dataset under various evaluation settings.
-
Real-world data often exhibits class-imbalanced distributions, where a few classes (a.k.a. majority classes) occupy most instances and lots of classes (a.k.a. minority classes) have few instances. Neural classification models usually perform poorly on minority classes when training on such imbalanced datasets. To improve the performance on minority classes, existing methods typically re-balance the data distribution at the class level, i.e., assigning higher weights to minority classes and lower weights to majority classes during the training process. However, we observe that even the majority classes contain difficult instances to learn. By reducing the weights of the majority classes, such instances would become more difficult to learn and hurt the overall performance consequently. To tackle this problem, we propose a novel instance-level re-balancing strategy, which dynamically adjusts the sampling probabilities of instances according to the instance difficulty. Here the instance difficulty is measured based on the learning speed of instance, which is inspired by the human-leaning process (i.e., easier instances will be learned faster). We theoretically prove the correctness and convergence of our re-sampling algorithm. Empirical experiments demonstrate that our method significantly outperforms state-of-the-art re-balancing methods on the class-imbalanced datasets.
-
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-parameterization mechanism, named representation compensation (RC) module, to decouple the representation learning of both old and new knowledge. The RC module consists of two dynamically evolved branches with one frozen and one trainable. Besides, we design a pooled cube knowledge distillation strategy on both spatial and channel dimensions to further enhance the plasticity and stability of the model. We conduct experiments on two challenging continual semantic segmentation scenarios, continual class segmentation and continual domain segmentation. Without any extra computational overhead and parameters during inference, our method outperforms state-of-the-art performance. The code is available at https://github.com/zhangchbin/RCIL.
-
Single-photon avalanche diodes (SPADs) are growing in popularity for depth sensing tasks. However, SPADs still struggle in the presence of high ambient light due to the effects of pile-up. Conventional techniques leverage fixed or asynchronous gating to minimize pile-up effects, but these gating schemes are all non-adaptive, as they are unable to incorporate factors such as scene priors and previous photon detections into their gating strategy. We propose an adaptive gating scheme built upon Thompson sampling. Adaptive gating periodically updates the gate position based on prior photon observations in order to minimize depth errors. Our experiments show that our gating strategy results in significantly reduced depth reconstruction error and acquisition time, even when operating outdoors under strong sunlight conditions.
-
We present an approach for tracking people in monocular videos by predicting their future 3D representations. To achieve this, we first lift people to 3D from a single frame in a robust manner. This lifting includes information about the 3D pose of the person, their location in the 3D space, and the 3D appearance. As we track a person, we collect 3D observations over time in a tracklet representation. Given the 3D nature of our observations, we build temporal models for each one of the previous attributes. We use these models to predict the future state of the tracklet, including 3D appearance, 3D location, and 3D pose. For a future frame, we compute the similarity between the predicted state of a tracklet and the single frame observations in a probabilistic manner. Association is solved with simple Hungarian matching, and the matches are used to update the respective tracklets. We evaluate our approach on various benchmarks and report state-of-the-art results. Code and models are available at: https://brjathu.github.io/PHALP.
-
In this work, we develop intuitive controls for editing the style of 3D objects. Our framework, Text2Mesh, stylizes a 3D mesh by predicting color and local geometric details which conform to a target text prompt. We consider a disentangled representation of a 3D object using a fixed mesh input (content) coupled with a learned neural network, which we term a neural style field network (NSF). In order to modify style, we obtain a similarity score between a text prompt (describing style) and a stylized mesh by harnessing the representational power of CLIP. Text2Mesh requires neither a pre-trained generative model nor a specialized 3D mesh dataset. It can handle low-quality meshes (non-manifold, boundaries, etc.) with arbitrary genus, and does not require UV parameterization. We demonstrate the ability of our technique to synthesize a myriad of styles over a wide variety of 3D meshes. Our code and results are available in our project webpage: https://threedle.github.io/text2mesh/.
-
We present an approach to solving hard geometric optimization problems in the RANSAC framework. The hard minimal problems arise from relaxing the original geometric optimization problem into a minimal problem with many spurious solutions. Our approach avoids computing large numbers of spurious solutions. We design a learning strategy for selecting a starting problem-solution pair that can be numerically continued to the problem and the solution of interest. We demonstrate our approach by developing a RANSAC solver for the problem of computing the relative pose of three calibrated cameras, via a minimal relaxation using four points in each view. On average, we can solve a single problem in under 70 microseconds. We also benchmark and study our engineering choices on the very familiar problem of computing the relative pose of two calibrated cameras, via the minimal case of five points in two views.
-
Despite the impressive results achieved by deep learning based 3D reconstruction, the techniques of directly learning to model 4D human captures with detailed geometry have been less studied. This work presents a novel framework that can effectively learn a compact and compositional representation for dynamic human by exploiting the human body prior from the widely used SMPL parametric model. Particularly, our representation, named H4D, represents a dynamic 3D human over a temporal span with the SMPL parameters of shape and initial pose, and latent codes encoding motion and auxiliary information. A simple yet effective linear motion model is proposed to provide a rough and regularized motion estimation, followed by per-frame compensation for pose and geometry details with the residual encoded in the auxiliary code. Technically, we introduce novel GRU-based architectures to facilitate learning and improve the representation capability. Extensive experiments demonstrate our method is not only efficacy in recovering dynamic human with accurate motion and detailed geometry, but also amenable to various 4D human related tasks, including motion retargeting, motion completion and future prediction.
-
Novel view synthesis (NVS) is a challenging task requiring systems to generate photorealistic images of scenes from new viewpoints, where both quality and speed are important for applications. Previous image-based rendering (IBR) methods are fast, but have poor quality when input views are sparse. Recent Neural Radiance Fields (NeRF) and generalizable variants give impressive results but are not real-time. In our paper, we propose a generalizable NVS method with sparse inputs, called \FWDds, which gives high-quality synthesis in real-time. With explicit depth and differentiable rendering, it achieves competitive results to the SOTA methods with 130-1000xspeedup and better perceptual quality. If available, we can seamlessly integrate sensor depth during either training or inference to improve image quality while retaining real-time speed. With the growing prevalence of depths sensors, we hope that methods making use of depth will become increasingly useful.
-
Synthesizing pseudo samples is currently the most effective way to solve the Generalized Zero Shot Learning (GZSL) problem. Most models achieve competitive performance but still suffer from two problems: (1) Feature confounding, the overall representations confound task-correlated and task-independent features, and existing models disentangle them in a generative way, but they are unreasonable to synthesize reliable pseudo samples with limited samples; (2) Distribution uncertainty, that massive data is needed when existing models synthesize samples from the uncertain distribution, which causes poor performance in limited samples of seen classes. In this paper, we propose a non-generative model to address these problems correspondingly in two modules: (1) Task-correlated feature disentanglement, to exclude the task-correlated features from task-independent ones by adversarial learning of domain adaption towards reasonable synthesis; (2) Controllable pseudo sample synthesis, to synthesize edge-pseudo and center-pseudo samples with certain characteristics towards more diversity generated and intuitive transfer. In addation, to describe the new scene that is the limit seen class samples in the training process, we further formulate a new ZSL task named the 'Few-shot Seen class and Zero-shot Unseen class learning' (FSZU). Extensive experiments on four benchmarks verify that the proposed method is competitive in the GZSL and the FSZU tasks.
-
Recently, many excellent weakly supervised semantic segmentation (WSSS) works are proposed based on class activation mapping (CAM). However, there are few works that consider the characteristics of medical images. In this paper, we find that there are mainly two challenges of medical images in WSSS: i) the boundary of object foreground and background is not clear; ii) the co-occurrence phenomenon is very severe in training stage. We thus propose a Causal CAM (C-CAM) method to overcome the above challenges. Our method is motivated by two cause-effect chains including category-causality chain and anatomy-causality chain. The category-causality chain represents the image content (cause) affects the category (effect). The anatomy-causality chain represents the anatomical structure (cause) affects the organ segmentation (effect). Extensive experiments were conducted on three public medical image data sets. Our C-CAM generates the best pseudo masks with the DSC of 77.26%, 80.34% and 78.15% on ProMRI, ACDC and CHAOS compared with other CAM-like methods. The pseudo masks of C-CAM are further used to improve the segmentation performance for organ segmentation tasks. Our C-CAM achieves DSC of 83.83% on ProMRI and DSC of 87.54% on ACDC, which outperforms state-of-the-art WSSS methods. Our code is available at https://github.com/Tian-lab/C-CAM.
-
One of the most pressing challenges for the detection of face-manipulated videos is generalising to forgery methods not seen during training while remaining effective under common corruptions such as compression. In this paper, we examine whether we can tackle this issue by harnessing videos of real talking faces, which contain rich information on natural facial appearance and behaviour and are readily available in large quantities online. Our method, termed RealForensics, consists of two stages. First, we exploit the natural correspondence between the visual and auditory modalities in real videos to learn, in a self-supervised cross-modal manner, temporally dense video representations that capture factors such as facial movements, expression, and identity. Second, we use these learned representations as targets to be predicted by our forgery detector along with the usual binary forgery classification task; this encourages it to base its real/fake decision on said factors. We show that our method achieves state-of-the-art performance on cross-manipulation generalisation and robustness experiments, and examine the factors that contribute to its performance. Our results suggest that leveraging natural and unlabelled videos is a promising direction for the development of more robust face forgery detectors.
-
Novel classes frequently arise in our dynamically changing world, e.g., new users in the authentication system, and a machine learning model should recognize new classes without forgetting old ones. This scenario becomes more challenging when new class instances are insufficient, which is called few-shot class-incremental learning (FSCIL). Current methods handle incremental learning retrospectively by making the updated model similar to the old one. By contrast, we suggest learning prospectively to prepare for future updates, and propose ForwArd Compatible Training (FACT) for FSCIL. Forward compatibility requires future new classes to be easily incorporated into the current model based on the current stage data, and we seek to realize it by reserving embedding space for future new classes. In detail, we assign virtual prototypes to squeeze the embedding of known classes and reserve for new ones. Besides, we forecast possible new classes and prepare for the updating process. The virtual prototypes allow the model to accept possible updates in the future, which act as proxies scattered among embedding space to build a stronger classifier during inference. FACT efficiently incorporates new classes with forward compatibility and meanwhile resists forgetting of old ones. Extensive experiments validate FACT's state-of-the-art performance. Code is available at: https://github.com/zhoudw-zdw/CVPR22-Fact
-
Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation. However, more recent works find that existing differentiable NAS techniques struggle to outperform naive baselines, yielding deteriorative architectures as the search proceeds. Rather than directly optimizing the architecture parameters, this paper formulates the neural architecture search as a distribution learning problem through relaxing the architecture weights into Gaussian distributions. By leveraging the natural-gradient variational inference (NGVI), the architecture distribution can be easily optimized based on existing codebases without incurring more memory and computational consumption. We demonstrate how the differentiable NAS benefits from Bayesian principles, enhancing exploration and improving stability. The experimental results on NAS benchmark datasets confirm the significant improvements the proposed framework can make. In addition, instead of simply applying the argmax on the learned parameters, we further leverage the recently-proposed training-free proxies in NAS to select the optimal architecture from a group architectures drawn from the optimized distribution, where we achieve state-of-the-art results on the NAS-Bench-201 and NAS-Bench-1shot1 benchmarks. Our best architecture in the DARTS search space also obtains competitive test errors with 2.37%, 15.72%, and 24.2% on CIFAR-10, CIFAR-100, and ImageNet, respectively.
-
Recently, both long-tailed recognition and object tracking have made great advances individually. TAO benchmark presented a mixture of the two, long-tailed object tracking, in order to further reflect the aspect of the real-world. To date, existing solutions have adopted detectors showing robustness in long-tailed distributions, which derive per-frame results. Then, they used tracking algorithms that combine the temporally independent detections to finalize tracklets. However, as the approaches did not take temporal changes in scenes into account, inconsistent classification results in videos led to low overall performance. In this paper, we present a set classifier that improves accuracy of classifying tracklets by aggregating information from multiple viewpoints contained in a tracklet. To cope with sparse annotations in videos, we further propose augmentation of tracklets that can maximize data efficiency. The set classifier is plug-and-playable to existing object trackers, and highly improves the performance of long-tailed object tracking. By simply attaching our method to QDTrack on top of ResNet-101, we achieve the new state-of-the-art, 19.9% and 15.7% TrackAP50 on TAO validation and test sets, respectively.
-
Canonical correlation analysis (CCA) matters in multiview representation learning. But, CCA and its most variants are essentially based on explicit or implicit covariance matrices. It means that they have no ability to model the nonlinear relationship among features due to intrinsic linearity of covariance. In this paper, we address the preceding problem and propose a novel canonical F-correlation framework by exploring and exploiting the nonlinear relationship between different features. The framework projects each feature rather than observation into a certain new space by an arbitrary nonlinear mapping, thus resulting in more flexibility in real applications. With this framework as a tool, we propose a correlative covariation projection (CCP) method by using an explicit nonlinear mapping. Moreover, we further propose a multiset version of CCP dubbed MCCP for learning compact representation of more than two views. The proposed MCCP is solved by an iterative method, and we prove the convergence of this iteration. A series of experimental results on six benchmark datasets demonstrate the effectiveness of our proposed CCP and MCCP methods.
-
Current Image captioning (IC) methods predict textual words sequentially based on the input visual information from the visual feature extractor and the partially generated sentence information. However, for most cases, the partially generated sentence may dominate the target word prediction due to the insufficiency of visual information, making the generated descriptions irrelevant to the content of the given image. In this paper, we propose a Dual Information Flow Network (DIFNet) to address this issue, which takes segmentation feature as another visual information source to enhance the contribution of visual information for prediction. To maximize the use of two information flows, we also propose an effective feature fusion module termed Iterative Independent Layer Normalization (IILN) which can condense the most relevant inputs while retraining modality-specific information in each flow. Experiments show that our method is able to enhance the dependence of prediction on visual information, making word prediction more focused on the visual content, and thus achieve new state-of-the-art performance on the MSCOCO dataset, e.g., 136.2 CIDEr on COCO Karpathy test split.
-
Weakly supervised object localization (WSOL) focuses on localizing objects only with the supervision of image-level classification masks. Most previous WSOL methods follow the classification activation map (CAM) that localizes objects based on the classification structure with the multi-instance learning (MIL) mechanism. However, the MIL mechanism makes CAM only activate discriminative object parts rather than the whole object, weakening its performance for localizing objects. To avoid this problem, this work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects. Under this perspective, a DA-WSOL pipeline is designed to better engage DA approaches into WSOL to enhance localization performance. It utilizes a proposed target sampling strategy to select different types of target samples. Based on these types of target samples, domain adaption localization (DAL) loss is elaborated. It aligns the feature distribution between the two domains by DA and makes the estimator perceive target domain cues by Universum regularization. Experiments show that our pipeline outperforms SOTA methods on multi benchmarks. Code are released at https://github.com/zh460045050/DA-WSOL_CVPR2022.
-
Multi-modal video similarity evaluation is important for video recommendation systems such as video de-duplication, relevance matching, ranking, and diversity control. However, there still lacks a benchmark dataset that can support supervised training and accurate evaluation. In this paper, we propose the Tencent-MVSE dataset, which is the first benchmark dataset for the multi-modal video similarity evaluation task. The Tencent-MVSE dataset contains video pairs similarity annotations, and diverse metadata including Chinese title, automatic speech recognition (ASR) text, as well as human-annotated categories/tags. We provide a simple baseline with a multi-modal Transformer architecture to perform supervised multi-modal video similarity evaluation. We also explore pre-training strategies to make use of the unpaired data. The whole dataset as well as our baseline will be released to promote the development of the multi-modal video similarity evaluation. The dataset has been released in https://tencent-mvse.github.io/.
-
The key challenge for few-shot semantic segmentation (FSS) is how to tailor a desirable interaction among support and query features and/or their prototypes, under the episodic training scenario. Most existing FSS methods implement such support/query interactions by solely leveraging \it plain operations -- e.g., cosine similarity and feature concatenation -- for segmenting the query objects. However, these interaction approaches usually cannot well capture the intrinsic object details in the query images that are widely encountered in FSS, e.g., if the query object to be segmented has holes and slots, inaccurate segmentation almost always happens. To this end, we propose a dynamic prototype convolution network (DPCN) to fully capture the aforementioned intrinsic details for accurate FSS. Specifically, in DPCN, a dynamic convolution module (DCM) is firstly proposed to generate dynamic kernels from support foreground, then information interaction is achieved by convolution operations over query features using these kernels. Moreover, we equip DPCN with a support activation module (SAM) and a feature filtering module (FFM) to generate pseudo mask and filter out background information for the query images, respectively. SAM and FFM together can mine enriched context information from the query features. Our DPCN is also flexible and efficient under the k-shot FSS setting. Extensive experiments on PASCAL-5^i and COCO-20^i show that DPCN yields superior performances under both 1-shot and 5-shot settings.
-
State-of-the-art fully intrinsic network for non-rigid shape matching are unable to disambiguate between shape inner symmetries. Meanwhile, recent advances in the functional map framework allow to enforce orientation preservation using a functional representation for tangent vector field transfer, through so-called complex functional maps. Using this representation, we propose a new deep learning approach to learn orientation-aware features in a fully unsupervised setting. Our architecture is built on DiffusionNet, which makes our method robust to discretization changes, while adding a vector-field-based loss, which promotes orientation preservation without using (often unstable) extrinsic descriptors. Our source code is available at: https://github.com/nicolasdonati/DUO-FM
-
Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network with coarse-grained (i.e.,point-, scribble-, and block-wise) supervisions, where only a small proportion of pixels are labeled in each image. In this paper, we propose a novel tree energy loss for SASS by providing semantic guidance for unlabeled pixels. The tree energy loss represents images as minimum spanning trees to model both low-level and high-level pair-wise affinities. By sequentially applying these affinities to the network prediction, soft pseudo labels for unlabeled pixels are generated in a coarse-to-fine manner, resulting in dynamic online self-training. The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss. Compared with previous SASS methods, our method requires no multi-stage training strategies, alternating optimization procedures, additional supervised data, or time-consuming post-processing while outperforming them in all types of supervised settings. Code is available at https://github.com/megvii-research/TreeEnergyLoss.
-
Post-training quantization compresses a neural network within few hours with only a small unlabeled calibration set. However, so far it has been only discussed and empirically demonstrated in the context of uniform quantization on convolutional neural networks. We thus propose a new post-training non-uniform quantization method, called Mr.BiQ, allowing low bit-width quantization even on Transformer models. In particular, we leverage multi-level binarization for weights while allowing activations to be represented as various data formats (e.g., INT8, bfloat16, binary-coding, and FP32). Unlike conventional methods which optimize full-precision weights first, then decompose the weights into quantization parameters, Mr.BiQ recognizes the quantization parameters (i.e., scaling factors and bit-code) as directly and jointly learnable parameters during the optimization. To verify the superiority of the proposed quantization scheme, we test Mr.BiQ on various models including convolutional neural networks and Transformer models. According to experimental results, Mr.BiQ shows significant improvement in terms of accuracy when the bit-width of weights is equal to 2: up to 5.35 p.p. improvement in CNNs, up to 4.23 p.p. improvement in Vision Transformers, and up to 3.37 point improvement in Transformers for NLP.
-
In this paper, we propose a transformer-based image matting model called MatteFormer, which takes full advantage of trimap information in the transformer block. Our method first introduces a prior-token which is a global representation of each trimap region (e.g. foreground, background and unknown). These prior-tokens are used as global priors and participate in the self-attention mechanism of each block. Each stage of the encoder is composed of PAST (Prior-Attentive Swin Transformer) block, which is based on the Swin Transformer block, but differs in a couple of aspects: 1) It has PA-WSA (Prior-Attentive Window Self-Attention) layer, performing self-attention not only with spatial-tokens but also with prior-tokens. 2) It has prior-memory which saves prior-tokens accumulatively from the previous blocks and transfers them to the next block. We evaluate our MatteFormer on the commonly used image matting datasets: Composition-1k and Distinctions-646. Experiment results show that our proposed method achieves state-of-the-art performance with a large margin. Our codes are available at https://github.com/webtoon/matteformer.
-
It is challenging to annotate large-scale datasets for supervised video shadow detection methods. Using a model trained on labeled images to the video frames directly may lead to high generalization error and temporal inconsistent results. In this paper, we address these challenges by proposing a Spatio-Temporal Interpolation Consistency Training (STICT) framework to rationally feed the unlabeled video frames together with the labeled images into an image shadow detection network training. Specifically, we propose the Spatial and Temporal ICT, in which we define two new interpolation schemes, i.e., the spatial interpolation and the temporal interpolation. We then derive the spatial and temporal interpolation consistency constraints accordingly for enhancing generalization in the pixel-wise classification task and for encouraging temporal consistent predictions, respectively. In addition, we design a Scale-Aware Network for multi-scale shadow knowledge learning in images, and propose a scale-consistency constraint to minimize the discrepancy among the predictions at different scales. Our proposed approach is extensively validated on the ViSha dataset and a self-annotated dataset. Experimental results show that, even without video labels, our approach is better than most state of the art supervised, semi-supervised or unsupervised image/video shadow detection methods and other methods in related tasks. Code and dataset are available at https://github.com/yihong-97/STICT.
-
Recent progress in few-shot learning promotes a more realistic cross-domain setting, where the source and target datasets are in different domains. Due to the domain gap and disjoint label spaces between source and target datasets, their shared knowledge is extremely limited. This encourages us to explore more information in the target domain rather than to overly elaborate training strategies on the source domain as in many existing methods. Hence, we start from a generic representation pre-trained by a cross-entropy loss and a conventional distance-based classifier, along with an image retrieval view, to employ a re-ranking process to calibrate a target distance matrix by discovering the k-reciprocal neighbours within the task. Assuming the pre-trained representation is biased towards the source, we construct a non-linear subspace to minimise task-irrelevant features therewithin while keep more transferrable discriminative information by a hyperbolic tangent transformation. The calibrated distance in this target-aware non-linear sub-space is complementary to that in the pre-trained representation. To impose such distance calibration information onto the pre-trained representation, a Kullback-Leibler divergence loss is employed to gradually guide the model towards the calibrated distance-based distribution. Extensive evaluations on eight target domains show that this target ranking calibration process can improve conventional distance-based classifiers in few-shot learning.
-
Interpreting objects with basic geometric primitives has long been studied in computer vision. Among geometric primitives, superquadrics are well known for their ability to represent a wide range of shapes with few parameters. However, as the first and foremost step, recovering superquadrics accurately and robustly from 3D data still remains challenging. The existing methods are subject to local optima and sensitive to noise and outliers in real-world scenarios, resulting in frequent failure in capturing geometric shapes. In this paper, we propose the first probabilistic method to recover superquadrics from point clouds. Our method builds a Gaussian-uniform mixture model (GUM) on the parametric surface of a superquadric, which explicitly models the generation of outliers and noise. The superquadric recovery is formulated as a Maximum Likelihood Estimation (MLE) problem. We propose an algorithm, Expectation, Maximization, and Switching (EMS), to solve this problem, where: (1) outliers are predicted from the posterior perspective; (2) the superquadric parameter is optimized by the trust-region reflective algorithm; and (3) local optima are avoided by globally searching and switching among parameters encoding similar superquadrics. We show that our method can be extended to the multi-superquadrics recovery for complex objects. The proposed method outperforms the state-of-the-art in terms of accuracy, efficiency, and robustness on both synthetic and real-world datasets. The code is at http://github.com/bmlklwx/EMS-superquadric_fitting.git.
-
We combine neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions. Our method, Dream Fields, can generate the geometry and color of a wide range of objects without 3D supervision. Due to the scarcity of diverse, captioned 3D data, prior methods only generate objects from a handful of categories, such as ShapeNet. Instead, we guide generation with image-text models pre-trained on large datasets of captioned images from the web. Our method optimizes a Neural Radiance Field from many camera views so that rendered images score highly with a target caption according to a pre-trained CLIP model. To improve fidelity and visual quality, we introduce simple geometric priors, including sparsityinducing transmittance regularization, scene bounds, and new MLP architectures. In experiments, Dream Fields produce realistic, multi-view consistent object geometry and color from a variety of natural language captions.
-
A range of video modeling tasks, from optical flow to multiple object tracking, share the same fundamental challenge: establishing space-time correspondence. Yet, approaches that dominate each space differ. We take a step towards bridging this gap by extending the recent contrastive random walk formulation to much more dense, pixel-level space-time graphs. The main contribution is introducing hierarchy into the search problem by computing the transition matrix in a coarse-to-fine manner, forming a multiscale contrastive random walk. This establishes a unified technique for self-supervised learning of optical flow, keypoint tracking, and video object segmentation. Experiments demonstrate that, for each of these tasks, our unified model achieves performance competitive with strong self-supervised approaches specific to that task.
-
Person image generation aims to perform non-rigid deformation on source images, which generally requires unaligned data pairs for training. Recently, self-supervised methods express great prospects in this task by merging the disentangled representations for self-reconstruction. However, such methods fail to exploit the spatial correlation between the disentangled features. In this paper, we propose a Self-supervised Correlation Mining Network (SCM-Net) to rearrange the source images in the feature space, in which two collaborative modules are integrated, Decomposed Style Encoder (DSE) and Correlation Mining Module (CMM). Specifically, the DSE first creates unaligned pairs at the feature level. Then, the CMM establishes the spatial correlation field for feature rearrangement. Eventually, a translation module transforms the rearranged features to realistic results. Meanwhile, for improving the fidelity of cross-scale pose transformation, we propose a graph based Body Structure Retaining Loss (BSR Loss) to preserve reasonable body structures on half body to full body generation. Extensive experiments conducted on DeepFashion dataset demonstrate the superiority of our method compared with other supervised and unsupervised approaches. Furthermore, satisfactory results on face generation show the versatility of our method in other deformation tasks.
-
Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We analyze our dataset and compare it with five VQA-Grounding datasets to demonstrate what makes it similar and different. We then evaluate the SOTA VQA and VQA-Grounding models and demonstrate that current SOTA algorithms often fail to identify the correct visual evidence where the answer is located. These models regularly struggle when the visual evidence occupies a small fraction of the image, for images that are higher quality, as well as for visual questions that require skills in text recognition. The dataset, evaluation server, and leaderboard all can be found at the following link: https://vizwiz.org/tasks-and-datasets/answer-grounding-for-vqa/.
-
Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial memory cost. To efficiently learn multiple downstream tasks we introduce Task Adaptive Parameter Sharing (TAPS), a simple method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. This enables multi-task learning while minimizing the resources used and avoids catastrophic forgetting and competition between tasks. TAPS solves a joint optimization problem which determines both the layers that are shared with the base model and the value of the task-specific weights. Further, a sparsity penalty on the number of active layers promotes weight sharing with the base model. Compared to other methods, TAPS retains a high accuracy on the target tasks while still introducing only a small number of task-specific parameters. Moreover, TAPS is agnostic to the particular architecture used and requires only minor changes to the training scheme. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
-
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we propose a sparse set of instance activation maps, as a new object representation, to highlight informative regions for each foreground object. Then instance-level features are obtained by aggregating features according to the highlighted regions for recognition and segmentation. Moreover, based on bipartite matching, the instance activation maps can predict objects in a one-to-one style, thus avoiding non-maximum suppression (NMS) in post-processing. Owing to the simple yet effective designs with instance activation maps, SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark, which significantly outperforms the counterparts in terms of speed and accuracy. Code and models are available at https://github.com/hustvl/SparseInst.
-
Color image stitching is a challenging task in real-world applications. This paper first proposes a quaternion rank-1 alignment (QR1A) model for high-precision color image alignment. To solve the optimization problem of QR1A, we develop a nested iterative algorithm under the framework of complex-valued alternating direction method of multipliers. To quantitatively evaluate image stitching performance, we propose a perceptual seam quality (PSQ) measure to calculate misalignments of local regions along the seamline. Using QR1A and PSQ, we further propose an automatic color image stitching (ACIS-QR1A) framework. In this framework, the automatic strategy and iterative learning strategy are developed to simultaneously learn the optimal seamline and local alignment. Extensive experiments on challenging datasets demonstrate that the proposed ACIS-QR1A is able to obtain high-quality stitched images under several difficult scenarios including large parallax, low textures, moving objects, large occlusions or/and their combinations.
-
The limited availability of annotated data often hinders real-world applications of machine learning. To efficiently learn from small quantities of multimodal data, we leverage the linguistic knowledge from a large pre-trained language model (PLM) and quickly adapt it to new domains of image captioning. To effectively utilize a pretrained model, it is critical to balance the visual input and prior linguistic knowledge from pretraining. We propose VisualGPT, which employs a novel self-resurrecting encoder-decoder attention mechanism to quickly adapt the PLM with a small amount of in-domain image-text data. The proposed self-resurrecting activation unit produces sparse activations that prevent accidental overwriting of linguistic knowledge. When trained on 0.1%, 0.5% and 1% of the respective training sets, VisualGPT surpasses the best baseline by up to 10.0% CIDEr on MS COCO and 17.9% CIDEr on Conceptual Captions. Furthermore, VisualGPT achieves the state-of-the-art result on IU X-ray, a medical report generation dataset. Our code is available at https://github.com/Vision-CAIR/VisualGPT.
-
This paper aims to address the single image gaze target detection problem. Conventional methods either focus on 2D visual cues or exploit additional depth information in a very coarse manner. In this work, we propose to explicitly and effectively model 3D geometry under challenging scenario where only 2D annotations are available. We first obtain 3D point clouds of given scene with estimated depth and reference objects. Then we figure out the front-most points in all possible 3D directions of given person. These points are later leveraged in our ESCNet model. Specifically, ESCNet consists of geometry and scene parsing modules. The former produces an initial heatmap inferring the probability that each front-most point has been looking at according to estimated 3D gaze direction. And the latter further explores scene contextual cues to regulate detection results. We validate our idea on two publicly available dataset, GazeFollow and VideoAttentionTarget, and demonstrate the state-of-the-art performance. Our method also beats the human in terms of AUC on GazeFollow.
-
Co-salient object detection (CoSOD) has recently achieved significant progress and played a key role in retrieval-related tasks. However, it inevitably poses an entirely new safety and security issue, i.e., highly personal and sensitive content can potentially be extracting by powerful CoSOD methods. In this paper, we address this problem from the perspective of adversarial attacks and identify a novel task: adversarial co-saliency attack. Specially, given an image selected from a group of images containing some common and salient objects, we aim to generate an adversarial version that can mislead CoSOD methods to predict incorrect co-salient regions. Note that, compared with general white-box adversarial attacks for classification, this new task faces two additional challenges: (1) low success rate due to the diverse appearance of images in the group; (2) low transferability across CoSOD methods due to the considerable difference between CoSOD pipelines. To address these challenges, we propose the very first black-box joint adversarial exposure and noise attack (Jadena), where we jointly and locally tune the exposure and additive perturbations of the image according to a newly designed high-feature-level contrast-sensitive loss function. Our method, without any information on the state-of-the-art CoSOD methods, leads to significant performance degradation on various co-saliency detection datasets and makes the co-salient objects undetectable. This can have strong practical benefits in properly securing the large number of personal photos currently shared on the Internet. Moreover, our method is potential to be utilized as a metric for evaluating the robustness of CoSOD methods.
-
As lovely as bunnies are, your sketched version would probably not do it justice (Fig. 1). This paper recognises this very problem and studies sketch quality measurement for the first time -- letting you find these badly drawn ones. Our key discovery lies in exploiting the magnitude (L2 norm) of a sketch feature as a quantitative quality metric. We propose Geometry-Aware Classification Layer (GACL), a generic method that makes feature-magnitude-as-quality-metric possible and importantly does it without the need for specific quality annotations from humans. GACL sees feature magnitude and recognisability learning as a dual task, which can be simultaneously optimised under a neat cross-entropy classification loss. GACL is lightweight with theoretic guarantees and enjoys a nice geometric interpretation to reason its success. We confirm consistent quality agreements between our GACL-induced metric and human perception through a carefully designed human study. Last but not least, we demonstrate three practical sketch applications enabled for the first time using our quantitative quality metric. Code will be made publicly available.
-
We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a set of extrusion cylinders. Reverse engineering from a raw geometry to a CAD model is an essential task to enable manipulation of the 3D data in shape editing software and thus expand their usages in many downstream applications. Particularly, the form of CAD models having a sequence of extrusion cylinders --- a 2D sketch plus an extrusion axis and range --- and their boolean combinations is not only widely used in the CAD community/software but also has great expressivity of shapes, compared to having limited types of primitives (e.g., planes, spheres, and cylinders). In this work, we introduce a neural network that solves the extrusion cylinder decomposition problem in a geometry-grounded way by first learning underlying geometric proxies. Precisely, our approach first predicts per-point segmentation, base/barrel labels and normals, then estimates for the underlying extrusion parameters in differentiable and closed-form formulations. Our experiments show that our approach demonstrates the best performance on two recent CAD datasets, Fusion Gallery and DeepCAD, and we further showcase our approach on reverse engineering and editing.
-
Time-of-flight (ToF) sensors provide an image modality fueling applications across domains, including lidar in autonomous driving, robotics, and augmented reality. Conventional ToF imaging methods estimate the depth of a scene point by sending pulses of light into a scene and measuring the time of flight of the first arriving photons that are returned from the scene, the ones directly reflected from a scene surface without any temporal delay. As such, all photons following this first response are typically considered as unwanted noise, including multi-bounce and sub-surface scattering of real-world materials. While multi-bounce scene interreflections have been extensively in recent work on non-line-of-sight imaging, we investigate temporally resolved sub-surface scattering in this work. We depart from the principle of first arrival and instead propose an all-photon ToF imaging method relying on polarization changes that analyzes both first- and late-arriving photons for shape and material scene understanding. To this end, we propose a novel capture method, reflectance model, and a reconstruction algorithm that exploits the polarization state of light changes after reflection in addition to ToF information. The proposed temporal-polarimetric imaging method allows for accurate geometric and material information of the scene by utilizing all photons captured by the system, decoded by polarization cues, outperforming all tested existing methods in simulation and experimentally.
-
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are available at https://github.com/Vegetebird/MHFormer.
-
We propose a new method for reconstructing controllable implicit 3D human models from sparse multi-view RGB videos. Our method defines the neural scene representation on the mesh surface points and signed distances from the surface of a human body mesh. We identify an indistinguishability issue that arises when a point in 3D space is mapped to its nearest surface point on a mesh for learning surface-aligned neural scene representation. To address this issue, we propose projecting a point onto a mesh surface using a barycentric interpolation with modified vertex normals. Experiments with the ZJU-MoCap and Human3.6M datasets show that our approach achieves a higher quality in a novel-view and novel-pose synthesis than existing methods. We also demonstrate that our method easily supports the control of body shape and clothes. Project page: https://pfnet-research.github.io/surface-aligned-nerf/.
-
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g., FixMatch). Without specifically utilizing the temporal dynamics and inherent multimodal attributes, their results could be suboptimal. To better leverage the encoded temporal information in videos, we introduce temporal gradient as an additional modality for more attentive feature extraction in this paper. To be specific, our method explicitly distills the fine-grained motion representations from temporal gradient (TG) and imposes consistency across different modalities (i.e., RGB and TG). The performance of semi-supervised action recognition is significantly improved without additional computation or parameters during inference. Our method achieves the state-of-the-art performance on three video action recognition benchmarks (i.e., Kinetics-400, UCF-101, and HMDB-51) under several typical semi-supervised settings (i.e., different ratios of labeled data).
-
In this work, we explore the challenging task of generating 3D shapes from text. Beyond the existing works, we propose a new approach for text-guided 3D shape generation, capable of producing high-fidelity shapes with colors that match the given text description. This work has several technical contributions. First, we decouple the shape and color predictions for learning features in both texts and shapes, and propose the word-level spatial transformer to correlate word features from text with spatial features from shape. Also, we design a cyclic loss to encourage consistency between text and shape, and introduce the shape IMLE to diversify the generated shapes. Further, we extend the framework to enable text-guided shape manipulation. Extensive experiments on the largest existing text-shape benchmark manifest the superiority of this work. The code and the models are available at https://github.com/liuzhengzhe/Towards-Implicit Text-Guided-Shape-Generation.
-
Human speech is often accompanied by body gestures including arm and hand gestures. We present a method that reenacts a high-quality video with gestures matching a target speech audio. The key idea of our method is to split and re-assemble clips from a reference video through a novel video motion graph encoding valid transitions between clips. To seamlessly connect different clips in the reenactment, we propose a pose-aware video blending network which synthesizes video frames around the stitched frames between two clips. Moreover, we developed an audio-based gesture searching algorithm to find the optimal order of the reenacted frames. Our system generates reenactments that are consistent with both the audio rhythms and the speech content. We evaluate our synthesized video quality quantitatively, qualitatively, and with user studies, demonstrating that our method produces videos of much higher quality and consistency with the target audio compared to previous work and baselines.
-
Image collage task aims to create an informative and visual-aesthetic visual summarization for an image collection. While several recent works exploit tree-based algorithm to preserve image content better, all of them resort to hand-crafted adjustment rules to optimize the collage tree structure, leading to the failure of fully exploring the structure space of collage tree. Our key idea is to soften the discrete tree structure space into a continuous probability space. We propose SoftCollage, a novel method that employs a neural-based differentiable probabilistic tree generator to produce the probability distribution of correlation-preserving collage tree conditioned on deep image feature, aspect ratio and canvas size. The differentiable characteristic allows us to formulate the tree-based collage generation as a differentiable process and directly exploit gradient to optimize the collage layout in the level of probability space in an end-to-end manner. To facilitate image collage research, we propose AIC, a large-scale public-available annotated dataset for image collage evaluation. Extensive experiments on the introduced dataset demonstrate the superior performance of the proposed method. Data and codes are available at https://github.com/ChineseYjh/SoftCollage.
-
Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function. While this inductive bias integrates valuable domain knowledge, it limits the expressivity of the tracking network. In this work, we therefore propose a tracker architecture employing a Transformer-based model prediction module. Transformers capture global relations with little inductive bias, allowing it to learn the prediction of more powerful target models. We further extend the model predictor to estimate a second set of weights that are applied for accurate bounding box regression. The resulting tracker relies on training and on test frame information in order to predict all weights transductively. We train the proposed tracker end-to-end and validate its performance by conducting comprehensive experiments on multiple tracking datasets. Our tracker sets a new state of the art on three benchmarks, achieving an AUC of 68.5% on the challenging LaSOT dataset.
-
The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields. One major reason is its ease of integration into deep learning frameworks. To allow for an efficient training of respective neural networks, we propose an algorithm that obtains analytical gradients of a Sinkhorn layer via implicit differentiation. In comparison to prior work, our framework is based on the most general formulation of the Sinkhorn operator. It allows for any type of loss function, while both the target capacities and cost matrices are differentiated jointly. We further construct error bounds of the resulting algorithm for approximate inputs. Finally, we demonstrate that for a number of applications, simply replacing automatic differentiation with our algorithm directly improves the stability and accuracy of the obtained gradients. Moreover, we show that it is computationally more efficient, particularly when resources like GPU memory are scarce.
-
Monocular 6D pose estimation is a fundamental task in computer vision. Existing works often adopt a twostage pipeline by establishing correspondences and utilizing a RANSAC algorithm to calculate 6 degrees-of-freedom (6DoF) pose. Recent works try to integrate differentiable RANSAC algorithms to achieve an end-to-end 6D pose estimation. However, most of them hardly consider the geometric features in 3D space, and ignore the topology cues when performing differentiable RANSAC algorithms. To this end, we proposed a Depth-Guided Edge Convolutional Network (DGECN) for 6D pose estimation task. We have made efforts from the following three aspects: 1) We take advantages of estimated depth information to guide both the correspondences-extraction process and the cascaded differentiable RANSAC algorithm with geometric information. 2)We leverage the uncertainty of the estimated depth map to improve accuracy and robustness of the output 6D pose. 3) We propose a differentiable Perspective-n-Point(PnP) algorithm via edge convolution to explore the topology relations between 2D-3D correspondences. Experiments demonstrate that our proposed network outperforms current works on both effectiveness and efficiency.
-
Understanding realistic visual scene images together with language descriptions is a fundamental task towards generic visual understanding. Previous works have shown compelling comprehensive results by building hierarchical structures for visual scenes (e.g., scene graphs) and natural languages (e.g., dependency trees), individually. However, how to construct a joint vision-language (VL) structure has barely been investigated. More challenging but worthwhile, we introduce a new task that targets on inducing such a joint VL structure in an unsupervised manner. Our goal is to bridge the visual scene graphs and linguistic dependency trees seamlessly. Due to the lack of VL structural data, we start by building a new dataset VLParse. Rather than using labor-intensive labeling from scratch, we propose an automatic alignment procedure to produce coarse structures followed by human refinement to produce high-quality ones. Moreover, we benchmark our dataset by proposing a contrastive learning (CL)-based framework VLGAE, short for Vision-Language Graph Autoencoder. Our model obtains superior performance on two derived tasks, i.e., language grammar induction and VL phrase grounding. Ablations show the effectiveness of both visual cues and dependency relationships on fine-grained VL structure construction.
-
Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captioned images covering many novel classes and then finetune it on limited base classes with mask annotations. However, the high-level textual information learned from caption pretraining alone cannot effectively encode the details required for pixel-wise segmentation. To address this, we propose a cross-modal pseudo-labeling framework, which generates training pseudo masks by aligning word semantics in captions with visual features of object masks in images. Thus, our framework is capable of labeling novel classes in captions via their word semantics to self-train a student model. To account for noises in pseudo masks, we design a robust student model that selectively distills mask knowledge by estimating the mask noise levels, hence mitigating the adverse impact of noisy pseudo masks. By extensive experiments, we show the effectiveness of our framework, where we significantly improve mAP score by 4.5% on MS-COCO and 5.1% on the large-scale Open Images & Conceptual Captions datasets compared to the state-of-the-art.
-
Our target is to learn visual correspondence from unlabeled videos. We develop LIIR, a locality-aware inter-and intra-video reconstruction framework that fills in three missing pieces, i.e., instance discrimination, location awareness, and spatial compactness, of self-supervised correspondence learning puzzle. First, instead of most existing efforts focusing on intra-video self-supervision only, we exploit cross video affinities as extra negative samples within a unified, inter-and intra-video reconstruction scheme. This enables instance discriminative representation learning by contrasting desired intra-video pixel association against negative inter-video correspondence. Second, we merge position information into correspondence matching, and design a position shifting strategy to remove the side-effect of position encoding during inter-video affinity computation, making our LIIR location-sensitive. Third, to make full use of the spatial continuity nature of video data, we impose a compactness-based constraint on correspondence matching, yielding more sparse and reliable solutions. The learned representation surpasses self-supervised state-of-the-arts on label propagation tasks including objects, semantic parts, and keypoints.
-
3D object detection using LiDAR data is an indispensable component for autonomous driving systems. Yet, only a few LiDAR-based 3D object detection methods leverage segmentation information to further guide the detection process. In this paper, we propose a novel multi-task framework that jointly performs 3D object detection and panoptic segmentation. In our method, the 3D object detection backbone, which is in Bird's-Eye-View (BEV) plane, is augmented by the injection of Range-View (RV) feature maps from the 3D panoptic segmentation backbone. This enables the detection backbone to leverage multi-view information to address the shortcomings of each projection view. Furthermore, foreground semantic information is incorporated to ease the detection task by highlighting the locations of each object class in the feature maps. Finally, a new center density heatmap generated based on the instance-level information further guides the detection backbone by suggesting possible box center locations for objects in the BEV plane. Our method works with any BEV-based 3D object detection method, and as shown by extensive experiments on the nuScenes dataset, it provides significant performance gains. Notably, the proposed method based on a single-stage CenterPoint 3D object detection network achieved state-of-the-art performance on nuScenes 3D Detection Benchmark with 67.3 NDS.
-
Explainable visual question answering (VQA) models have been developed with neural modules and query-based knowledge incorporation to answer knowledge-requiring questions. Yet, most reasoning methods cannot effectively generate queries or incorporate external knowledge during the reasoning process, which may lead to suboptimal results. To bridge this research gap, we present Query and Attention Augmentation, a general approach that augments neural module networks to jointly reason about visual and external knowledge. To take both knowledge sources into account during reasoning, it parses the input question into a functional program with queries augmented through a novel reinforcement learning method, and jointly directs augmented attention to visual and external knowledge based on intermediate reasoning results. With extensive experiments on multiple VQA datasets, our method demonstrates significant performance, explainability, and generalizability over state-of-the-art models in answering questions requiring different extents of knowledge. Our source code is available at https://github.com/SuperJohnZhang/QAA.
-
We present a novel task and dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning, which we call Winoground. Given two images and two captions, the goal is to match them correctly--but crucially, both captions contain a completely identical set of words, only in a different order. The dataset was carefully hand-curated by expert annotators and is labeled with a rich set of fine-grained tags to assist in analyzing model performance. We probe a diverse range of state-of-the-art vision and language models and find that, surprisingly, none of them do much better than chance. Evidently, these models are not as skilled at visio-linguistic compositional reasoning as we might have hoped. We perform an extensive analysis to obtain insights into how future work might try to mitigate these models' shortcomings. We aim for Winoground to serve as a useful evaluation set for advancing the state of the art and driving further progress in the field. The dataset is available at https://huggingface.co/datasets/facebook/winoground.
-
In this paper, we propose a novel method to realize multi-modal image registration and fusion in a mutually reinforcing framework, termed as RFNet. We handle the registration in a coarse-to-fine fashion. For the first time, we exploit the feedback of image fusion to promote the registration accuracy rather than treating them as two separate issues. The fine-registered results also improve the fusion performance. Specifically, for image registration, we solve the bottlenecks of defining registration metrics applicable for multi-modal images and facilitating the network convergence. The metrics are defined based on image translation and image fusion respectively in the coarse and fine stages. The convergence is facilitated by the designed metrics and a deformable convolution-based network. For image fusion, we focus on texture preservation, which not only increases the information amount and quality of fusion results but also improves the feedback of fusion results. The proposed method is evaluated on multi-modal images with large global parallaxes, images with local misalignments and aligned images to validate the performances of registration and fusion. The results in these cases demonstrate the effectiveness of our method.
-
Generic event boundary detection is an important yet challenging task in video understanding, which aims at detecting the moments where humans naturally perceive event boundaries. The main challenge of this task is perceiving various temporal variations of diverse event boundaries. To this end, this paper presents an effective and end-to-end learnable framework (DDM-Net). To tackle the diversity and complicated semantics of event boundaries, we make three notable improvements. First, we construct a feature bank to store multi-level features of space and time, prepared for difference calculation at multiple scales. Second, to alleviate inadequate temporal modeling of previous methods, we present dense difference maps (DDM) to comprehensively characterize the motion pattern. Finally, we exploit progressive attention on multi-level DDM to jointly aggregate appearance and motion clues. As a result, DDM-Net respectively achieves a significant boost of 14% and 8% on Kinetics-GEBD and TAPOS benchmark, and outperforms the top-1 winner solution of LOVEU Challenge@CVPR 2021 without bells and whistles. The state-of-the-art result demonstrates the effectiveness of richer motion representation and more sophisticated aggregation, in handling the diversity of generic event boundary detection. The code is made available at https://github.com/MCG-NJU/DDM.
-
Over the years various methods have been proposed for the problem of object detection. Recently, we have witnessed great strides in this domain owing to the emergence of powerful deep neural networks. However, there are typically two main assumptions common among these approaches. First, the model is trained on a fixed training set and is evaluated on a pre-recorded test set. Second, the model is kept frozen after the training phase, so no further updates are performed after the training is finished. These two assumptions limit the applicability of these methods to real-world settings. In this paper, we propose Interactron, a method for adaptive object detection in an interactive setting, where the goal is to perform object detection in images observed by an embodied agent navigating in different environments. Our idea is to continue training during inference and adapt the model at test time without any explicit supervision via interacting with the environment. Our adaptive object detection model provides a 11.8 point improvement in AP (and 19.1 points in AP50) over DETR, a recent, high-performance object detector. Moreover, we show that our object detection model adapts to environments with completely different appearance characteristics, and its performance is on par with a model trained with full supervision for those environments. We will release the code to help ease future research in this domain.
-
We propose a novel approach to 3D scene painting using a configurable 3D scene layout. Our approach takes a 3D scene with semantic class labels as input and trains a 3D scene painting network that synthesizes color values for the input 3D scene. We exploit an off-the-shelf 2D semantic image synthesis method to teach the 3D painting network without explicit color supervision. Experiments show that our approach produces images with geometrically correct structures and supports scene manipulation, such as the change of viewpoint, object poses, and painting style. Our approach provides rich controllability to synthesized images in the aspect of 3D geometry.
-
We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects, and by adaptively referencing and aggregating useful information from the memory as needed. Our model, called MeMOT, consists of three main modules that are all Transformer-based: 1) Hypothesis Generation that produce object proposals in the current video frame; 2) Memory Encoding that extracts the core information from the memory for each tracked object; and 3) Memory Decoding that solves the object detection and data association tasks simultaneously for multi-object tracking. When evaluated on widely adopted MOT benchmark datasets, MeMOT observes very competitive performance.
-
Model pre-training is a cornerstone of modern visual recognition systems. Although fully supervised pre-training on datasets like ImageNet is still the de-facto standard, recent studies suggest that large-scale weakly supervised pre-training can outperform fully supervised approaches. This paper revisits weakly-supervised pre-training of models using hashtag supervision with modern versions of residual networks and the largest-ever dataset of images and corresponding hashtags. We study the performance of the resulting models in various transfer-learning settings including zero-shot transfer. We also compare our models with those obtained via large-scale self-supervised learning. We find our weakly-supervised models to be very competitive across all settings, and find they substantially outperform their self-supervised counterparts. We also include an investigation into whether our models learned potentially troubling associations or stereotypes. Overall, our results provide a compelling argument for the use of weakly supervised learning in the development of visual recognition systems. Our models, Supervised Weakly through hashtAGs (SWAG), are available publicly.
-
This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. The unlabeled images are usually assigned pseudo labels to be used in training, which however often causes the risk of performance degradation due to the confirmation bias towards errors on the pseudo labels. We present a novel method that resolves this chronic issue of pseudo labeling. At the heart of our method lies error localization network (ELN), an auxiliary module that takes an image and its segmentation prediction as input and identifies pixels whose pseudo labels are likely to be wrong. ELN enables semi-supervised learning to be robust against inaccurate pseudo labels by disregarding label noises during training and can be naturally integrated with self-training and contrastive learning. Moreover, we introduce a new learning strategy for ELN that simulates plausible and diverse segmentation errors during training of ELN to enhance its generalization. Our method is evaluated on PASCAL VOC 2012 and Cityscapes, where it outperforms all existing methods in every evaluation setting.
-
In single domain generalization, models trained with data from only one domain are required to perform well on many unseen domains. In this paper, we propose a new model, termed meta convolutional neural network, to solve the single domain generalization problem in image recognition. The key idea is to decompose the convolutional features of images into meta features. Acting as "visual words", meta features are defined as universal and basic visual elements for image representations (like words for documents in language). Taking meta features as reference, we propose compositional operations to eliminate irrelevant features of local convolutional features by an addressing process and then to reformulate the convolutional feature maps as a composition of related meta features. In this way, images are universally coded without biased information from the unseen domain, which can be processed by following modules trained in the source domain. The compositional operations adopt a regression analysis technique to learn the meta features in an online batch learning manner. Extensive experiments on multiple benchmark datasets verify the superiority of the proposed model in improving single domain generalization ability.
-
Recent advances of deep learning-based approaches have achieved remarkable performance on appearance-based gaze estimation. However, due to the shortage of target domain data and absence of target labels, generalizing gaze estimation algorithm to unseen environments is still challenging. In this paper, we discover the rotation-consistency property in gaze estimation and introduce the 'sub-label' for unsupervised domain adaptation. Consequently, we propose the Rotation-enhanced Unsupervised Domain Adaptation (RUDA) for gaze estimation. First, we rotate the original images with different angles for training. Then we conduct domain adaptation under the constraint of rotation consistency. The target domain images are assigned with sub-labels, derived from relative rotation angles rather than untouchable real labels. With such sub-labels, we propose a novel distribution loss that facilitates the domain adaptation. We evaluate the RUDA framework on four cross-domain gaze estimation tasks. Experimental results demonstrate that it improves the performance over the baselines with gains ranging from 12.2% to 30.5%. Our framework has the potential to be used in other computer vision tasks with physical constraints.
-
Knowledge distillation (KD) achieves promising results on the challenging problem of unsupervised anomaly detection (AD). The representation discrepancy of anomalies in the teacher-student (T-S) model provides essential evidence for AD. However, using similar or identical architectures to build the teacher and student models in previous studies hinders the diversity of anomalous representations. To tackle this problem, we propose a novel T-S model consisting of a teacher encoder and a student decoder and introduce a simple yet effective "reverse distillation" paradigm accordingly. Instead of receiving raw images directly, the student network takes teacher model's one-class embedding as input and targets to restore the teacher's multi-scale representations. Inherently, knowledge distillation in this study starts from abstract, high-level presentations to low-level features. In addition, we introduce a trainable one-class bottleneck embedding (OCBE) module in our T-S model. The obtained compact embedding effectively preserves essential information on normal patterns, but abandons anomaly perturbations. Extensive experimentation on AD and one-class novelty detection benchmarks shows that our method surpasses SOTA performance, demonstrating our proposed approach's effectiveness and generalizability.
-
Semantic patterns of fine-grained objects are determined by subtle appearance difference of local parts, which thus inspires a number of part-based methods. However, due to uncontrollable object poses in images, distinctive details carried by local regions can be spatially distributed or even self-occluded, leading to a large variation on object representation. For discounting pose variations, this paper proposes to learn a novel graph based object representation to reveal a global configuration of local parts for self-supervised pose alignment across classes, which is employed as an auxiliary feature regularization on a deep representation learning network. Moreover, a coarse-to-fine supervision together with the proposed pose-insensitive constraint on shallow-to-deep sub-networks encourages discriminative features in a curriculum learning manner. We evaluate our method on three popular fine-grained object classification benchmarks, consistently achieving the state-of-the-art performance. Source codes are available at https://github.com/yangxh11/P2P-Net.
-
Predicting future motion based on historical motion sequence is a fundamental problem in computer vision, and it has wide applications in autonomous driving and robotics. Some recent works have shown that Graph Convolutional Networks(GCN) are instrumental in modeling the relationship between different joints. However, considering the variants and diverse action types in human motion data, the cross-dependency of the spatio-temporal relationships will be difficult to depict due to the decoupled modeling strategy, which may also exacerbate the problem of insufficient generalization. Therefore, we propose the Spatio-Temporal Gating-Adjacency GCN(GAGCN) to learn the complex spatio-temporal dependencies over diverse action types. Specifically, we adopt gating networks to enhance the generalization of GCN via the trainable adaptive adjacency matrix obtained by blending the candidate spatio-temporal adjacency matrices. Moreover, GAGCN addresses the cross-dependency of space and time by balancing the weights of spatio-temporal modeling and fusing the decoupled spatio-temporal features. Extensive experiments on Human 3.6M, AMASS, and 3DPW demonstrate that GAGCN achieves state-of-the-art performance in both short-term and long-term predictions.
-
Classifying all cells in an organ is a relevant and difficult problem from plant developmental biology. We here abstract the problem into a new benchmark for node classification in a geo-referenced graph. Solving it requires learning the spatial layout of the organ including symmetries. To allow the convenient testing of new geometrical learning methods, the benchmark of Arabidopsis thaliana ovules is made available as a PyTorch data loader, along with a large number of precomputed features. Finally, we benchmark eight recent graph neural network architectures, finding that DeeperGCN currently works best on this problem.
-
Clustering is a popular approach to detecting patterns in unlabeled data. Existing clustering methods typically treat samples in a dataset as points in a metric space and compute distances to group together similar points. In this paper, we present a different way of clustering points in 2-dimensional space, inspired by how humans cluster data: by training neural networks to perform instance segmentation on plotted data. Our approach, Visual Clustering, has several advantages over traditional clustering algorithms: it is much faster than most existing clustering algorithms (making it suitable for very large datasets), it agrees strongly with human intuition for clusters, and it is by default hyperparameter free (although additional steps with hyperparameters can be introduced for more control of the algorithm). We describe the method and compare it to ten other clustering methods on synthetic data to illustrate its advantages and disadvantages. We then demonstrate how our approach can be extended to higher-dimensional data and illustrate its performance on real-world data. Our implementation of Visual Clustering is publicly available as a python package that can be installed and used on any dataset in a few lines of code. A demo on synthetic datasets is provided.
-
Understanding animals' behaviors is significant for a wide range of applications. However, existing animal behavior datasets have limitations in multiple aspects, including limited numbers of animal classes, data samples and provided tasks, and also limited variations in environmental conditions and viewpoints. To address these limitations, we create a large and diverse dataset, Animal Kingdom, that provides multiple annotated tasks to enable a more thorough understanding of natural animal behaviors. The wild animal footages used in our dataset record different times of the day in extensive range of environments containing variations in backgrounds, viewpoints, illumination and weather conditions. More specifically, our dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes. Such a challenging and comprehensive dataset shall be able to facilitate the community to develop, adapt, and evaluate various types of advanced methods for animal behavior analysis. Moreover, we propose a Collaborative Action Recognition (CARe) model that learns general and specific features for action recognition with unseen new animals. This method achieves promising performance in our experiments. Our dataset can be found at https://sutdcv.github.io/Animal-Kingdom.
-
Convolutional Neural Networks have achieved remarkable success in face recognition, in part due to the abundant availability of data. However, the data used for training CNNs is often imbalanced. Prior works largely focus on the long-tailed nature of face datasets in data volume per identity, or focus on single bias variation. In this paper, we show that many bias variations such as ethnicity, head pose, occlusion and blur can jointly affect the accuracy significantly. We propose a sample level weighting approach termed Multi-variation Cosine Margin (MvCoM), to simultaneously consider the multiple variation factors, which orthogonally enhances the face recognition losses to incorporate the importance of training samples. Further, we leverage a learning to learn approach, guided by a held-out meta learning set and use an additive modeling to predict the MvCoM. Extensive experiments on challenging face recognition benchmarks demonstrate the advantages of our method in jointly handling imbalances due to multiple variations.
-
In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i.e. annotations of object centers). In order to remedy the information loss from box annotations to centers, our method, namely Back to Reality (BR), makes use of synthetic 3D shapes to convert the weak labels into fully-annotated virtual scenes as stronger supervision, and in turn utilizes the perfect virtual labels to complement and refine the real labels. Specifically, we first assemble 3D shapes into physically reasonable virtual scenes according to the coarse scene layout extracted from position-level annotations. Then we go back to reality by applying a virtual-to-real domain adaptation method, which refine the weak labels and additionally supervise the training of detector with the virtual scenes. With less than 5% of the labeling labor, we achieve comparable detection performance with some popular fully-supervised approaches on the widely used ScanNet dataset.
-
In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem via training-free knowledge transfer. Our objective is to transfer knowledge acquired from information-rich common classes to semantically similar, and yet data-hungry, rare classes in order to obtain stronger tail class representations. We leverage the fact that class prototypes and learned cosine classifiers provide two different, complementary representations of class cluster centres in feature space, and use an attention mechanism to select and recompose learned classifiers features from common classes to obtain higher quality rare class representations. Our knowledge transfer process is training free, reducing overfitting risks, and can afford continual extension of classifiers to new classes. Experiments show that our approach can achieve significant performance boosts on rare classes while maintaining robust common class performance, outperforming directly comparable state-of-the-art models.
-
recommendation, and marketing services. Extensive efforts have been made to conquer the cross-modal retrieval problem in the general domain. When it comes to E-commerce, a common practice is to adopt the pretrained model and finetune on E-commerce data. Despite its simplicity, the performance is sub-optimal due to overlooking the uniqueness of E-commerce multimodal data. A few recent efforts have shown significant improvements over generic methods with customized designs for handling product images. Unfortunately, to the best of our knowledge, no existing method has addressed the unique challenges in the e-commerce language. This work studies the outstanding one, where it has a large collection of special meaning entities, e.g., "Dissel (brand)", "Top (category)", "relaxed (fit)" in the fashion clothing business. By formulating such out-of-distribution finetuning process in the Causal Inference paradigm, we view the erroneous semantics of these special entities as confounders to cause the retrieval failure. To rectify these semantics for aligning with e-commerce domain knowledge, we propose an intervention-based entity-aware contrastive learning framework with two modules, i.e., the Confounding Entity Selection Module and Entity-Aware Learning Module. Our method achieves competitive performance on the E-commerce benchmark Fashion-Gen. Particularly, in top-1 accuracy (R@1), we observe 10.3% and 10.5% relative improvements over the closest baseline in image-to-text and text-to-image retrievals, respectively.
-
Humans can perceive multiple expressions, each one with varying intensity, in the picture of a face. We propose a methodology for collecting and modeling multidimensional modulated expression annotations from human annotators. Our data reveals that the perception of some expressions can be quite different across observers; thus, our model is designed to represent ambiguity alongside intensity. An empirical exploration of how many dimensions are necessary to capture the perception of facial expression suggests six principal expression dimensions are sufficient. Using our method, we collected multidimensional modulated expression annotations for 1,000 images culled from the popular ExpW in-the-wild dataset. As a proof of principle of our improved measurement technique, we used these annotations to benchmark four public domain algorithms for automated facial expression prediction.
-
The development of computational tools allows the advancement of research in behavioral neuroscience and elevates the limits of experiment design. Many behavioral experiments need to determine the animal's position from its tracking, which is crucial for real-time decision-making and further analysis of experimental data. Modern experimental designs usually generate the recording of a large amount of data, requiring the development of automatic computational tools and intelligent algorithms for timely data acquisition and processing. The proposed tool in this study initially operates with the acquisition of images. Then the animal tracking step begins with background subtraction, followed by the animal contour detection and morphological operations to remove noise in the detected shapes. Finally, in the final stage of the algorithm, the principal components analysis (PCA) is applied in the obtained shape, resulting in the animal's gaze direction.
-
We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted relations as pseudo labels. At the heart of our framework lies an algorithm that investigates contexts of data on the embedding space to predict their class-equivalence relations as pseudo labels. The algorithm enables efficient end-to-end training since it demands no off-the-shelf module for pseudo labeling. Also, the class-equivalence relations provide rich supervisory signals for learning an embedding space. On standard benchmarks for metric learning, it clearly outperforms existing unsupervised learning methods and sometimes even beats supervised learning models using the same backbone network. It is also applied to semi-supervised metric learning as a way of exploiting additional unlabeled data, and achieves the state of the art by boosting performance of supervised learning substantially.
-
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without hitting the computation or memory bottlenecks. In this paper, we propose a new strategy to overcome this challenge. Instead of trying to process more frames at once like most existing methods, we propose to process videos in an online fashion and cache "memory" at each iteration. Through the memory, the model can reference prior context for long-term modeling, with only a marginal cost. Based on this idea, we build MeMViT, a Memory-augmented Multiscale Vision Transformer, that has a temporal support 30x longer than existing models with only 4.5 more compute; traditional methods need >3,000% more compute to do the same. On a wide range of settings, the increased temporal support enabled by MeMViT brings large gains in recognition accuracy consistently. MeMViT obtains state-of-the-art results on the AVA, EPIC-Kitchens-100 action classification, and action anticipation datasets.
-
We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training. Despite the recent progress, existing methods mainly embrace a localization-by-classification paradigm and overlook the fruitful fine-grained temporal distinctions between video sequences, thus suffering from severe ambiguity in classification learning and classification-to-localization adaption. This paper argues that learning by contextually comparing sequence-to-sequence distinctions offers an essential inductive bias in WSAL and helps identify coherent action instances. Specifically, under a differentiable dynamic programming formulation, two complementary contrastive objectives are designed, including Fine-grained Sequence Distance (FSD) contrasting and Longest Common Subsequence (LCS) contrasting, where the first one considers the relations of various action/background proposals by using match, insert, and delete operators and the second one mines the longest common subsequences between two videos. Both contrasting modules can enhance each other and jointly enjoy the merits of discriminative action-background separation and alleviated task gap between classification and localization. Extensive experiments show that our method achieves state-of-the-art performance on two popular benchmarks. Our code is available at https://github.com/MengyuanChen21/CVPR2022-FTCL.
-
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. In this paper, we start by rethinking how such multi-stride stereotype affects the LiDAR-based 3D object detectors. Our experiments point out that the downsampling operations bring few advantages, and lead to inevitable information loss. To remedy this issue, we propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network. Armed with transformers, our method addresses the problem of insufficient receptive field in single-stride architectures. It also cooperates well with the sparsity of point clouds and naturally avoids expensive computation. Eventually, our SST achieves state-of-the-art results on the large-scale Waymo Open Dataset. It is worth mentioning that our method can achieve exciting performance (83.8 LEVEL_1 AP on validation split) on small object (pedestrian) detection due to the characteristic of single stride. Our codes will be public soon.
-
Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few samples introduces uncertainty, and quantifying model confidence for few-shot predictions is essential for many critical domains. Furthermore, few-shot tasks used in meta training are usually sampled randomly from a task distribution for an iterative model update, leading to high labeling costs and computational overhead in meta-training. We propose a novel uncertainty-aware task selection model for label efficient meta-learning. The proposed model formulates a multidimensional belief measure, which can quantify the known uncertainty and lower bound the unknown uncertainty of any given task. Our theoretical result establishes an important relationship between the conflicting belief and the incorrect belief. The theoretical result allows us to estimate the total uncertainty of a task, which provides a principled criterion for task selection. A novel multi-query task formulation is further developed to improve both the computational and labeling efficiency of meta-learning. Experiments conducted over multiple real-world few-shot image classification tasks demonstrate the effectiveness of the proposed model.
-
Visual Dialog aims to answer multi-round, interactive questions based on the dialog history and image content. Existing methods either consider answer ranking and generating individually or only weakly capture the relation across the two tasks implicitly by two separate models. The research on a universal framework that jointly learns to rank and generate answers in a single model is seldom explored. In this paper, we propose a contrastive learning-based framework UTC to unify and facilitate both discriminative and generative tasks in visual dialog with a single model. Specifically, considering the inherent limitation of the previous learning paradigm, we devise two inter-task contrastive losses i.e., context contrastive loss and answer contrastive loss to make the discriminative and generative tasks mutually reinforce each other. These two complementary contrastive losses exploit dialog context and target answer as anchor points to provide representation learning signals from different perspectives. We evaluate our proposed UTC on the VisDial v1.0 dataset, where our method outperforms the state-of-the-art on both discriminative and generative tasks and surpasses previous state-of-the-art generative methods by more than 2 absolute points on Recall@1.
-
Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to appropriately define and alleviate the bias" one of the most important issues. Prior works mainly use label distribution or mean score information to indicate a coarse-grained bias. In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one. To this end, we propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences. PCB generates fightback soft labels for regularization during training. Besides, an iterative learning paradigm is developed to support a progressive and smooth regularization in such debiasing. PCB can be plugged and played to any existing methods as a complement. Experiments results on LVIS demonstrate that our method achieves state-of-the-art performance without bells and whistles. Superior results across various architectures show the generalization ability. The code and trained models are available at https://github.com/megvii-research/PCB.
-
Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inference-time cost. Though efficient during inference, such models rely heavily on the complicated training-time blocks to achieve high accuracy, leading to large extra training cost. In this paper, we present online convolutional re-parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. To achieve this goal, we introduce a linear scaling layer for better optimizing the online blocks. Assisted with the reduced training cost, we also explore some more effective re-param components. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. Meanwhile, equipped with OREPA, the models outperform previous methods on ImageNet by up to +0.6%. We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks. Codes are available at https://github.com/JUGGHM/OREPA_CVPR2022.
-
Class Incremental Learning (CIL) aims at learning a classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Previous works mainly focus on mitigating forgetting in phases after the initial one. However, we find that improving CIL at its initial phase is also a promising direction. Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance. Motivated by this, we study the difference between a naively-trained initial-phase model and the oracle model. Specifically, since one major difference between these two models is the number of training classes, we investigate how such difference affects the model representations. We find that, with fewer training classes, the data representations of each class lie in a long and narrow region; with more training classes, the representations of each class scatter more uniformly. Inspired by this observation, we propose Class-wise Decorrelation (CwD) that effectively regularizes representations of each class to scatter more uniformly, thus mimicking the model jointly trained with all classes (i.e., the oracle model). Our CwD is simple to implement and easy to plug into existing methods. Extensive experiments on various benchmark datasets show that CwD consistently and significantly improves the performance of existing state-of-the-art methods by around 1% to 3%. Code: https://github.com/Yujun-Shi/CwD.
-
Lidars are depth measuring sensors widely used in autonomous driving and augmented reality. However, the large volume of data produced by lidars can lead to high costs in data storage and transmission. While lidar data can be represented as two interchangeable representations: 3D point clouds and range images, most previous work focus on compressing the generic 3D point clouds. In this work, we show that directly compressing the range images can leverage the lidar scanning pattern, compared to compressing the unprojected point clouds. We propose a novel data-driven range image compression algorithm, named RIDDLE (Range Image Deep DeLta Encoding). At its core is a deep model that predicts the next pixel value in a raster scanning order, based on contextual laser shots from both the current and past scans (represented as a 4D point cloud of spherical coordinates and time). The deltas between predictions and original values can then be compressed by entropy encoding. Evaluated on the Waymo Open Dataset and KITTI, our method demonstrates significant improvement in the compression rate (under the same distortion) compared to widely used point cloud and range image compression algorithms as well as recent deep methods.
-
The visual relationship recognition (VRR) task aims at understanding the pairwise visual relationships between interacting objects in an image. These relationships typically have a long-tail distribution due to their compositional nature. This problem gets more severe when the vocabulary becomes large, rendering this task very challenging. This paper shows that modeling an effective message-passing flow through an attention mechanism can be critical to tackling the compositionality and long-tail challenges in VRR. The method, called RelTransformer, represents each im- age as a fully-connected scene graph and restructures the whole scene into the relation-triplet and global-scene contexts. It directly passes the message from each element in the relation-triplet and global-scene contexts to the target relation via self-attention. We also design a learnable memory to augment the long-tail relation representation learning. Through extensive experiments, we find that our model generalizes well on many VRR benchmarks. Our model outperforms the best-performing models on two large-scale long-tail VRR benchmarks, VG8K-LT (+2.0% overall acc) and GQA-LT (+26.0% overall acc), both having a highly skewed distribution towards the tail. It also achieves strong results on the VG200 relation detection task. Our code is available at https://github.com/Vision-CAIR/ RelTransformer.
-
High-order decomposition is a widely used model compression approach towards compact convolutional neural networks (CNNs). However, many of the existing solutions, though can efficiently reduce CNN model sizes, are very difficult to bring considerable saving for computational costs, especially when the compression ratio is not huge, thereby causing the severe computation inefficiency problem. To overcome this challenge, in this paper we propose efficient High-Order DEcomposed Convolution (HODEC). By performing systematic explorations on the underlying reason and mitigation strategy for the computation inefficiency, we develop a new decomposition and computation-efficient execution scheme, enabling simultaneous reductions in computational and storage costs. To demonstrate the effectiveness of HODEC, we perform empirical evaluations for various CNN models on different datasets. HODEC shows consistently outstanding compression and acceleration performance. For ResNet-56 on CIFAR-10 dataset, HODEC brings 67% fewer model parameters and 62% fewer FLOPs with 1.17% accuracy increase than the baseline. For ResNet-50 on ImageNet dataset, HODEC achieves 63% FLOPs reduction with 0.31% accuracy increase than the uncompressed model.
-
In this work, we focus on scene flow learning on point clouds in a self-supervised manner. A real-world scene can be well modeled as a collection of rigidly moving parts, therefore its scene flow can be represented as a combination of rigid motion of each part. Inspired by this observation, we propose to generate pseudo scene flow for self-supervised learning based on piecewise rigid motion estimation, in which the source point cloud is decomposed into a set of local regions and each region is treated as rigid. By rigidly aligning each region with its potential counterpart in the target point cloud, we obtain a region-specific rigid transformation to represent the flow, which together constitutes the pseudo scene flow labels of the entire scene to enable network training. Compared with most existing approaches relying on point-wise similarities for point matching, our method explicitly enforces region-wise rigid alignments, yielding locally rigid pseudo scene flow labels. We demonstrate the effectiveness of our self-supervised learning method on FlyingThings3D and KITTI datasets. Comprehensive experiments show that our method achieves new state-of-the-art performance in self-supervised scene flow learning, without any ground truth scene flow for supervision, even outperforming some supervised counterparts.
-
Deep learning researchers have a keen interest in proposing new novel activation functions that can boost neural network performance. A good choice of activation function can have a significant effect on improving network performance and training dynamics. Rectified Linear Unit (ReLU) is a popular hand-designed activation function and is the most common choice in the deep learning community due to its simplicity though ReLU has some drawbacks. In this paper, we have proposed two new novel activation functions based on approximation of the maximum function, and we call these functions Smooth Maximum Unit (SMU and SMU-1). We show that SMU and SMU-1 can smoothly approximate ReLU, Leaky ReLU, or more general Maxout family, and GELU is a particular case of SMU. Replacing ReLU by SMU, Top-1 classification accuracy improves by 6.22%, 3.39%, 3.51%, and 3.08% on the CIFAR100 dataset with ShuffleNet V2, PreActResNet-50, ResNet-50, and SeNet-50 models respectively. Also, our experimental evaluation shows that SMU and SMU-1 improve network performance in a variety of deep learning tasks like image classification, object detection, semantic segmentation, and machine translation compared to widely used activation functions.
-
QR (quick response) codes are widely used as an offline-to-online channel to convey information (e.g., links) from publicity materials (e.g., display and print) to mobile devices. However, QR Codes are not favorable for taking up valuable space of publicity materials. Recent works propose invisible codes/hyperlinks that can convey hidden information from offline to online. However, they require markers to locate invisible codes, which fails the purpose of invisible codes to be visible because of the markers. This paper proposes a novel invisible information hiding architecture for display/print-camera scenarios, consisting of hiding, locating, correcting, and recovery, where invisible markers are learned to make hidden codes truly invisible. We hide information in a sub-image rather than the entire image and include a localization module in the end-to-end framework. To achieve both high visual quality and high recovering robustness, an effective multi-stage training strategy is proposed. The experimental results show that the proposed method outperforms the state-of-the-art information hiding methods in both visual quality and robustness. In addition, the automatic localization of hidden codes significantly reduces the time of manually correcting geometric distortions for photos, which is a revolutionary innovation for information hiding in mobile applications.
-
Personalized image aesthetics assessment (PIAA) is challenging due to its highly subjective nature. People's aesthetic tastes depend on diversified factors, including image characteristics and subject characters. The existing PIAA databases are limited in terms of annotation diversity, especially the subject aspect, which can no longer meet the increasing demands of PIAA research. To solve the dilemma, we conduct so far, the most comprehensive subjective study of personalized image aesthetics and introduce a new Personalized image Aesthetics database with Rich Attributes (PARA), which consists of 31,220 images with annotations by 438 subjects. PARA features wealthy annotations, including 9 image-oriented objective attributes and 4 human-oriented subjective attributes. In addition, desensitized subject information, such as personality traits, is also provided to support study of PIAA and user portraits. A comprehensive analysis of the annotation data is provided and statistic study indicates that the aesthetic preferences can be mirrored by proposed subjective attributes. We also propose a conditional PIAA model by utilizing subject information as conditional prior. Experimental results indicate that the conditional PIAA model can outperform the control group, which is also the first attempt to demonstrate how image aesthetics and subject characters interact to produce the intricate personalized tastes on image aesthetics. We believe the database and the associated analysis would be useful for conducting next-generation PIAA study. The project page of PARA can be found at https://cv-datasets.institutecv.com/#/data-sets.
-
Pre-training models on Imagenet or other massive datasets of real images has led to major advances in computer vision, albeit accompanied with shortcomings related to curation cost, privacy, usage rights, and ethical issues. In this paper, for the first time, we study the transferability of pre-trained models based on synthetic data generated by graphics simulators to downstream tasks from very different domains. In using such synthetic data for pre-training, we find that downstream performance on different tasks are favored by different configurations of simulation parameters (e.g. lighting, object pose, backgrounds, etc.), and that there is no one-size-fits-all solution. It is thus better to tailor synthetic pre-training data to a specific downstream task, for best performance. We introduce Task2Sim, a unified model mapping downstream task representations to optimal simulation parameters to generate synthetic pre-training data for them. Task2Sim learns this mapping by training to find the set of best parameters on a set of "seen" tasks. Once trained, it can then be used to predict best simulation parameters for novel "unseen" tasks in one shot, without requiring additional training. Given a budget in number of images per class, our extensive experiments with 20 diverse downstream tasks show Task2Sim's task-adaptive pre-training data results in significantly better downstream performance than non-adaptively choosing simulation parameters on both seen and unseen tasks. It is even competitive with pre-training on real images from Imagenet.
-
Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques accomplish this task by using pseudo-labels, but these labels are inherently noisy and deteriorate the accuracy. To overcome this problem, several pseudo-label refinement methods have been proposed, but they neglect the fine-grained local context essential for person re-ID. In this paper, we propose a novel Part-based Pseudo Label Refinement (PPLR) framework that reduces the label noise by employing the complementary relationship between global and part features. Specifically, we design a cross agreement score as the similarity of k-nearest neighbors between feature spaces to exploit the reliable complementary relationship. Based on the cross agreement, we refine pseudo-labels of global features by ensembling the predictions of part features, which collectively alleviate the noise in global feature clustering. We further refine pseudo-labels of part features by applying label smoothing according to the suitability of given labels for each part. Thanks to the reliable complementary information provided by the cross agreement score, our PPLR effectively reduces the influence of noisy labels and learns discriminative representations with rich local contexts. Extensive experimental results on Market-1501 and MSMT17 demonstrate the effectiveness of the proposed method over the state-of-the-art performance. The code is available at https://github.com/yoonkicho/PPLR.
-
Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments, training agents that cannot generalize across the two. Although learning to navigate in continuous spaces is closer to the real-world, training such an agent is significantly more difficult than training an agent in discrete spaces. However, recent advances in discrete VLN are challenging to translate to continuous VLN due to the domain gap. The fundamental difference between the two setups is that discrete navigation assumes prior knowledge of the connectivity graph of the environment, so that the agent can effectively transfer the problem of navigation with low-level controls to jumping from node to node with high-level actions by grounding to an image of a navigable direction. To bridge the discrete-to-continuous gap, we propose a predictor to generate a set of candidate waypoints during navigation, so that agents designed with high-level actions can be transferred to and trained in continuous environments. We refine the connectivity graph of Matterport3D to fit the continuous Habitat-Matterport3D, and train the waypoints predictor with the refined graphs to produce accessible waypoints at each time step. Moreover, we demonstrate that the predicted waypoints can be augmented during training to diversify the views and paths, and therefore enhance agent's generalization ability. Through extensive experiments we show that agents navigating in continuous environments with predicted waypoints perform significantly better than agents using low-level actions, which reduces the absolute discrete-to-continuous gap by 11.76% Success Weighted by Path Length (SPL) for the Cross-Modal Matching Agent and 18.24% SPL for the Recurrent VLN-BERT. Our agents, trained with a simple imitation learning objective, outperform previous methods by a large margin, achieving new state-of-the-art results on the testing environments of the R2R-CE and the RxR-CE datasets.
-
The rapid development of deep learning provides a better solution for the end-to-end reconstruction of hyperspectral image (HSI). However, existing learning-based methods have two major defects. Firstly, networks with self-attention usually sacrifice internal resolution to balance model performance against complexity, losing fine-grained high-resolution (HR) features. Secondly, even if the optimization focusing on spatial-spectral domain learning (SDL) converges to the ideal solution, there is still a significant visual difference between the reconstructed HSI and the truth. So we propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy. Dynamic FDL supervision forces the model to reconstruct fine-grained frequencies and compensate for excessive smoothing and distortion caused by pixel-level losses. The HR pixel-level attention and frequency-level refinement in our HDNet mutually promote HSI perceptual quality. Extensive quantitative and qualitative experiments show that our method achieves SOTA performance on simulated and real HSI datasets. https://github.com/Huxiaowan/HDNet
-
Open-world object detection (OWOD) is a challenging computer vision problem, where the task is to detect a known set of object categories while simultaneously identifying unknown objects. Additionally, the model must incrementally learn new classes that become known in the next training episodes. Distinct from standard object detection, the OWOD setting poses significant challenges for generating quality candidate proposals on potentially unknown objects, separating the unknown objects from the background and detecting diverse unknown objects. Here, we introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection. The proposed OW-DETR comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification and objectness scoring to explicitly address the aforementioned OWOD challenges. Our OW-DETR explicitly encodes multi-scale contextual information, possesses less inductive bias, enables knowledge transfer from known classes to the unknown class and can better discriminate between unknown objects and background. Comprehensive experiments are performed on two benchmarks: MS-COCO and PASCAL VOC. The extensive ablations reveal the merits of our proposed contributions. Further, our model outperforms the recently introduced OWOD approach, ORE, with absolute gains ranging from 1.8% to 3.3% in terms of unknown recall on MS-COCO. In the case of incremental object detection, OW-DETR outperforms the state-of-the-art for all settings on PASCAL VOC. Our code is available at https://github.com/akshitac8/OW-DETR.
-
Deep Implicit Function (DIF) has gained popularity as an efficient 3D shape representation. To capture geometry details, current methods usually learn DIF using local latent codes, which discretize the space into a regular 3D grid (or octree) and store local codes in grid points (or octree nodes). Given a query point, the local feature is computed by interpolating its neighboring local codes with their positions. However, the local codes are constrained at discrete and regular positions like grid points, which makes the code positions difficult to be optimized and limits their representation ability. To solve this problem, we propose to learn DIF with Dynamic Code Cloud, named DCC-DIF. Our method explicitly associates local codes with learnable position vectors, and the position vectors are continuous and can be dynamically optimized, which improves the representation ability. In addition, we propose a novel code position loss to optimize the code positions, which heuristically guides more local codes to be distributed around complex geometric details. In contrast to previous methods, our DCC-DIF represents 3D shapes more efficiently with a small amount of local codes, and improves the reconstruction quality. Experiments demonstrate that DCC-DIF achieves better performance over previous methods. Code and data are available at https://github.com/lity20/DCCDIF.
-
We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory footprint from the depth of the model, Reversible Vision Transformers enable memory efficient scaling of transformer architectures. We adapt two popular models, namely Vision Transformer and Multi-scale Vision Transformers, to reversible variants and benchmark extensively across both model sizes and tasks of image classification, object detection and video classification. Reversible Vision Transformers achieve a reduced memory footprint of up to 15.5x at identical model complexity, parameters and accuracy, demonstrating the promise of reversible vision transformers as an efficient backbone for resource limited training regimes. Finally, we find that the additional computational burden of recomputing activations is more than overcome for deeper models, where throughput can increase up to 3.9x over their non-reversible counterparts. Code and models are available at https://github.com/facebookresearch/mvit.
-
Humans have the remarkable ability to perceive objects as a whole, even when parts of them are occluded. This ability of amodal perception forms the basis of our perceptual and cognitive understanding of our world. To enable robots to reason with this capability, we formulate and propose a novel task that we name amodal panoptic segmentation. The goal of this task is to simultaneously predict the pixel-wise semantic segmentation labels of the visible regions of stuff classes and the instance segmentation labels of both the visible and occluded regions of thing classes. To facilitate research on this new task, we extend two established benchmark datasets with pixel-level amodal panoptic segmentation labels that we make publicly available as KITTI-360-APS and BDD100K-APS. We present several strong baselines, along with the amodal panoptic quality (APQ) and amodal parsing coverage (APC) metrics to quantify the performance in an interpretable manner. Furthermore, we propose the novel amodal panoptic segmentation network (APSNet), as a first step towards addressing this task by explicitly modeling the complex relationships between the occluders and occludes. Extensive experimental evaluations demonstrate that APSNet achieves state-of-the-art performance on both benchmarks and more importantly exemplifies the utility of amodal recognition. The datasets are available at http://amodal-panoptic.cs.uni-freiburg.de
-
Measurements from the Event Horizon Telescope enabled the visualization of light emission around a black hole for the first time. So far, these measurements have been used to recover a 2D image under the assumption that the emission field is static over the period of acquisition. In this work, we propose BH-NeRF, a novel tomography approach that leverages gravitational lensing to recover the continuous 3D emission field near a black hole. Compared to other 3D reconstruction or tomography settings, this task poses two significant challenges: first, rays near black holes follow curved paths dictated by general relativity, and second, we only observe measurements from a single viewpoint. Our method captures the unknown emission field using a continuous volumetric function parameterized by a coordinate-based neural network, and uses knowledge of Keplerian orbital dynamics to establish correspondence between 3D points over time. Together, these enable BH-NeRF to recover accurate 3D emission fields, even in challenging situations with sparse measurements and uncertain orbital dynamics. This work takes the first steps in showing how future measurements from the Event Horizon Telescope could be used to recover evolving 3D emission around the supermassive black hole in our Galactic center.
-
Making generative models 3D-aware bridges the 2D image space and the 3D physical world yet remains challenging. Recent attempts equip a Generative Adversarial Network (GAN) with a Neural Radiance Field (NeRF), which maps 3D coordinates to pixel values, as a 3D prior. However, the implicit function in NeRF has a very local receptive field, making the generator hard to become aware of the global structure. Meanwhile, NeRF is built on volume rendering which can be too costly to produce high-resolution results, increasing the optimization difficulty. To alleviate these two problems, we propose a novel framework, termed as VolumeGAN, for high-fidelity 3D-aware image synthesis, through explicitly learning a structural representation and a textural representation. We first learn a feature volume to represent the underlying structure, which is then converted to a feature field using a NeRF-like model. The feature field is further accumulated into a 2D feature map as the textural representation, followed by a neural renderer for appearance synthesis. Such a design enables independent control of the shape and the appearance. Extensive experiments on a wide range of datasets confirm that, our approach achieves sufficiently higher image quality and better 3D control than the previous methods..
-
Object-guided text-to-image synthesis aims to generate images from natural language descriptions built by two-step frameworks, i.e., the model generates the layout and then synthesizes images from the layout and captions. However, such frameworks have two issues: 1) complex structure, since generating language-related layout is not a trivial task; 2) error propagation, because the inappropriate layout will mislead the image synthesis and is hard to be revised. In this paper, we propose an object-guided joint-decoding module to simultaneously generate the image and the corresponding layout. Specially, we present the joint-decoding transformer to model the joint probability on images tokens and the corresponding layouts tokens, where layout tokens provide additional observed data to model the complex scene better. Then, we describe a novel Layout-VQGAN for layout encoding and decoding to provide more information about the complex scene. After that, we present the detail-enhanced module to enrich the language-related details based on two facts: 1) visual details could be omitted in the compression of VQGANs; 2) the joint-decoding transformer would not have sufficient generating capacity. The experiments show that our approach is competitive with previous object-centered models and can generate diverse and high-quality objects under the given layouts.
-
Geometric verification is considered a de facto solution for the re-ranking task in image retrieval. In this study, we propose a novel image retrieval re-ranking network named Correlation Verification Networks (CVNet). Our proposed network, comprising deeply stacked 4D convolutional layers, gradually compresses dense feature correlation into image similarity while learning diverse geometric matching patterns from various image pairs. To enable cross-scale matching, it builds feature pyramids and constructs cross-scale feature correlations within a single inference, replacing costly multi-scale inferences. In addition, we use curriculum learning with the hard negative mining and Hide-and-Seek strategy to handle hard samples without losing generality. Our proposed re-ranking network shows state-of-the-art performance on several retrieval benchmarks with a significant margin (+12.6% in mAP on ROxford-Hard+1M set) over state-of-the-art methods. The source code and models are available online: https://github.com/sungonce/CVNet.
-
Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data, which is costly to collect, compared to image-only or text-only data. In this paper, we propose unsupervised Vision-and-Language pre-training (UVLP) to learn the cross-modal representation from non-parallel image and text datasets. We found two key factors that lead to good unsupervised V+L pre-training without parallel data: (i) joint image-and-text input (ii) overall image-text alignment (even for non-parallel data). Accordingly, we propose a novel unsupervised V+L pre-training curriculum for non-parallel texts and images. We first construct a weakly aligned image-text corpus via a retrieval-based approach, then apply a set of multi-granular alignment pre-training tasks, including region-to-tag, region-to-phrase, and image-to-sentence alignment, to bridge the gap between the two modalities. A comprehensive ablation study shows each granularity is helpful to learn a stronger pre-trained model. We adapt our pre-trained model to a set of V+L downstream tasks, including VQA, NLVR2, Visual Entailment, and RefCOCO+. Our model achieves the state-of-art performance in all these tasks under the unsupervised setting.
-
While deep face recognition (FR) systems have shown amazing performance in identification and verification, they also arouse privacy concerns for their excessive surveillance on users, especially for public face images widely spread on social networks. Recently, some studies adopt adversarial examples to protect photos from being identified by unauthorized face recognition systems. However, existing methods of generating adversarial face images suffer from many limitations, such as awkward visual, white-box setting, weak transferability, making them difficult to be applied to protect face privacy in reality. In this paper, we propose adversarial makeup transfer GAN (AMT-GAN), a novel face protection method aiming at constructing adversarial face images that preserve stronger black-box transferability and better visual quality simultaneously. AMT-GAN leverages generative adversarial networks (GAN) to synthesize adversarial face images with makeup transferred from reference images. In particular, we introduce a new regularization module along with a joint training strategy to reconcile the conflicts between the adversarial noises and the cycle consistence loss in makeup transfer, achieving a desirable balance between the attack strength and visual changes. Extensive experiments verify that compared with state of the arts, AMT-GAN can not only preserve a comfortable visual quality, but also achieve a higher attack success rate over commercial FR APIs, including Face++, Aliyun, and Microsoft.
-
State-of-the-art approaches to ObjectGoal navigation (ObjectNav) rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Potential functions for ObjectGoal Navigation with Interaction-free learning (PONI), a modular approach that disentangles the skills of 'where to look?' for an object and 'how to navigate to (x, y)?'. Our key insight is that 'where to look?' can be treated purely as a perception problem, and learned without environment interactions. To address this, we propose a network that predicts two complementary potential functions conditioned on a semantic map and uses them to decide where to look for an unseen object. We train the potential function network using supervised learning on a passive dataset of top-down semantic maps, and integrate it into a modular framework to perform ObjectNav. Experiments on Gibson and Matterport3D demonstrate that our method achieves the state-of-the-art for ObjectNav while incurring up to 1,600x less computational cost for training. Code and pre-trained models are available.
-
How to effectively handle label noise has been one of the most practical but challenging tasks in Deep Neural Networks (DNNs). Recent popular methods for training DNNs with noisy labels mainly focus on directly filtering out samples with low confidence or repeatedly mining valuable information from low-confident samples. %to further modify DNNs. However, they cannot guarantee the robust generalization of models due to the ignorance of useful information hidden in noisy data. To address this issue, we propose a new effective method named as LaCoL (Latent Contrastive Learning) to leverage the negative correlations from the noisy data. Specifically, in label space, we exploit the weakly-augmented data to filter samples and adopt classification loss on strong augmentations of the selected sample set, which can preserve the training diversity. While in metric space, we utilize weakly-supervised contrastive learning to excavate these negative correlations hidden in noisy data. Moreover, a cross-space similarity consistency regularization is provided to constrain the gap between label space and metric space. Extensive experiments have validated the superiority of our approach over existing state-of-the-art methods.
-
Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation
Multi-frame human pose estimation has long been a compelling and fundamental problem in computer vision. This task is challenging due to fast motion and pose occlusion that frequently occur in videos. State-of-the-art methods strive to incorporate additional visual evidences from neighboring frames (supporting frames) to facilitate the pose estimation of the current frame (key frame). One aspect that has been obviated so far, is the fact that current methods directly aggregate unaligned contexts across frames. The spatial-misalignment between pose features of the current frame and neighboring frames might lead to unsatisfactory results. More importantly, existing approaches build upon the straightforward pose estimation loss, which unfortunately cannot constrain the network to fully leverage useful information from neighboring frames. To tackle these problems, we present a novel hierarchical alignment framework, which leverages coarse-to-fine deformations to progressively update a neighboring frame to align with the current frame at the feature level. We further propose to explicitly supervise the knowledge extraction from neighboring frames, guaranteeing that useful complementary cues are extracted. To achieve this goal, we theoretically analyzed the mutual information between the frames and arrived at a loss that maximizes the taskrelevant mutual information. These allow us to rank No.1 in the Multi-frame Person Pose Estimation Challenge on benchmark dataset PoseTrack2017, and obtain state-of-the-art performance on benchmarks Sub-JHMDB and PoseTrack2018. Our code is released at https://github.com/Pose-Group/FAMI-Pose, hoping that it will be useful to the community.
-
Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the "invertibility" of different image segments and project each segment into a latent layer. Easier regions can be inverted into an earlier layer in the generator's latent space, while more challenging regions can be inverted into a later feature space. Experiments show that our method obtains better inversion results compared to the recent approaches on complex categories, while maintaining downstream editability. Please refer to our project page at gauravparmar.com/sam_ inversion.
-
Transformers trained with self-supervision using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we show a graph-based method that uses the self-supervised transformer features to discover an object from an image. Visual tokens are viewed as nodes in a weighted graph with edges representing a connectivity score based on the similarity of tokens. Foreground objects can then be segmented using a normalized graph-cut to group self-similar regions. We solve the graph-cut problem using spectral clustering with generalized eigen-decomposition and show that the second smallest eigenvector provides a cutting solution since its absolute value indicates the likelihood that a token belongs to a foreground object. Despite its simplicity, this approach significantly boosts the performance of unsupervised object discovery: we improve over the recent state-of-the-art LOST by a margin of 6.9%, 8.1%, and 8.1% respectively on the VOC07, VOC12, and COCO20K. The performance can be further improved by adding a second stage class-agnostic detector (CAD). Our proposed method can be easily extended to unsupervised saliency detection and weakly supervised object detection. For unsupervised saliency detection, we improve IoU for 4.9%, 5.2%, 12.9% on ECSSD, DUTS, DUTOMRON respectively compared to state-of-the-art. For weakly supervised object detection, we achieve competitive performance on CUB and ImageNet. Our code is available at: https://www.m-psi.fr/Papers/TokenCut2022/
-
Recent high-performing Human-Object Interaction (HOI) detection techniques have been highly influenced by Transformer-based object detector (i.e., DETR). Nevertheless, most of them directly map parametric interaction queries into a set of HOI predictions through vanilla Transformer in a one-stage manner. This leaves rich inter- or intra-interaction structure under-exploited. In this work, we design a novel Transformer-style HOI detector, i.e., Structure-aware Transformer over Interaction Proposals (STIP), for HOI detection. Such design decomposes the process of HOI set prediction into two subsequent phases, i.e., an interaction proposal generation is first performed, and then followed by transforming the non-parametric interaction proposals into HOI predictions via a structure-aware Transformer. The structure-aware Transformer upgrades vanilla Transformer by encoding additionally the holistically semantic structure among interaction proposals as well as the locally spatial structure of human/object within each interaction proposal, so as to strengthen HOI predictions. Extensive experiments conducted on V-COCO and HICO-DET benchmarks have demonstrated the effectiveness of STIP, and superior results are reported when comparing with the state-of-the-art HOI detectors. Source code is available at https://github.com/zyong812/STIP.
-
Domain Adaptive Object Detection (DAOD) models a joint distribution of images and labels from an annotated source domain and learns a domain-invariant transformation to estimate the target labels with the given target domain images. Existing methods assume that the source domain labels are completely clean, yet large-scale datasets often contain error-prone annotations due to instance ambiguity, which may lead to a biased source distribution and severely degrade the performance of the domain adaptive detector de facto. In this paper, we represent the first effort to formulate noisy DAOD and propose a Noise Latent Transferability Exploration (NLTE) framework to address this issue. It is featured with 1) Potential Instance Mining (PIM), which leverages eligible proposals to recapture the miss-annotated instances from the background; 2) Morphable Graph Relation Module (MGRM), which models the adaptation feasibility and transition probability of noisy samples with relation matrices; 3) Entropy-Aware Gradient Reconcilement (EAGR), which incorporates the semantic information into the discrimination process and enforces the gradients provided by noisy and clean samples to be consistent towards learning domain-invariant representations. A thorough evaluation on benchmark DAOD datasets with noisy source annotations validates the effectiveness of NLTE. In particular, NLTE improves the mAP by 8.4% under 60% corrupted annotations and even approaches the ideal upper bound of training on a clean source dataset.
-
This paper probes intrinsic factors behind typical failure cases (e.g spatial inconsistency and boundary confusion) produced by the existing state-of-the-art method in face parsing. To tackle these problems, we propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation (DML-CSR) for face parsing. Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection. These tasks only share low-level encoder weights without high-level interactions between each other, enabling to decouple auxiliary modules from the whole network at the inference stage. To address spatial inconsistency, we develop a dynamic dual graph convolutional network to capture global contextual information without using any extra pooling operation. To handle boundary confusion in both single and multiple face scenarios, we exploit binary and category edge detection to jointly obtain generic geometric structure and fine-grained semantic clues of human faces. Besides, to prevent noisy labels from degrading model generalization during training, cyclical self-regulation is proposed to self-ensemble several model instances to get a new model and the resulting model then is used to self-distill subsequent models, through alternating iterations. Experiments show that our method achieves the new state-of-the-art performance on the Helen, CelebAMask-HQ, and Lapa datasets. The source code is available at https://github.com/deepinsight/insightface/tree/master/parsing/dml_csr.
-
Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data. In this paper, we explore more challenging exemplar-based high-resolution portrait style transfer by introducing a novel DualStyleGAN with flexible control of dual styles of the original face domain and the extended artistic portrait domain. Different from StyleGAN, DualStyleGAN provides a natural way of style transfer by characterizing the content and style of a portrait with an intrinsic style path and a new extrinsic style path, respectively. The delicately designed extrinsic style path enables our model to modulate both the color and complex structural styles hierarchically to precisely pastiche the style example. Furthermore, a novel progressive fine-tuning scheme is introduced to smoothly transform the generative space of the model to the target domain, even with the above modifications on the network architecture. Experiments demonstrate the superiority of DualStyleGAN over state-of-the-art methods in high-quality portrait style transfer and flexible style control.
-
This paper studies the task of One-Shot image Generation (OSG), where generation network learned on base dataset should be generalizable to synthesize images of novel categories with only one available sample per novel category. Most existing methods for feature transfer in one-shot image generation only learn reusable features implicitly on pre-training tasks. Such methods would be likely to overfit pre-training tasks. In this paper, we propose a novel model to explicitly learn and memorize reusable features that can help hallucinate novel category images. To be specific, our algorithm learns to decompose image features into the Category-Related (CR) and Category-Independent (CI) features. Our model learning to memorize class-independent CI features which are further utilized by our feature hallucination component to generate target novel category images. We validate our model on several benchmarks. Extensive experiments demonstrate that our model effectively boosts the OSG performance and can generate compelling and diverse samples.
-
In this paper, we address the problem of texture representation for 3D shapes for the challenging and underexplored tasks of texture transfer and synthesis. Previous works either apply spherical texture maps which may lead to large distortions, or use continuous texture fields that yield smooth outputs lacking details. We argue that the traditional way of representing textures with images and linking them to a 3D mesh via UV mapping is more desirable, since synthesizing 2D images is a well-studied problem. We propose AUV-Net which learns to embed 3D surfaces into a 2D aligned UV space, by mapping the corresponding semantic parts of different 3D shapes to the same location in the UV space. As a result, textures are aligned across objects, and can thus be easily synthesized by generative models of images. Texture alignment is learned in an unsupervised manner by a simple yet effective texture alignment module, taking inspiration from traditional works on linear subspace learning. The learned UV mapping and aligned texture representations enable a variety of applications including texture transfer, texture synthesis, and textured single view 3D reconstruction. We conduct experiments on multiple datasets to demonstrate the effectiveness of our method.
-
Open-vocabulary object detection aims to detect novel object categories beyond the training set. The advanced open-vocabulary two-stage detectors employ instance-level visual-to-visual knowledge distillation to align the visual space of the detector with the semantic space of the Pre-trained Visual-Language Model (PVLM). However, in the more efficient one-stage detector, the absence of class-agnostic object proposals hinders the knowledge distillation on unseen objects, leading to severe performance degradation. In this paper, we propose a hierarchical visual-language knowledge distillation method, i.e., HierKD, for open-vocabulary one-stage detection. Specifically, a global-level knowledge distillation is explored to transfer the knowledge of unseen categories from the PVLM to the detector. Moreover, we combine the proposed global-level knowledge distillation and the common instance-level knowledge distillation in a hierarchical structure to learn the knowledge of seen and unseen categories simultaneously. Extensive experiments on MS-COCO show that our method significantly surpasses the previous best one-stage detector with 11.9% and 6.7% AP50 gains under the zero-shot detection and generalized zero-shot detection settings, and reduces the AP50 performance gap from 14% to 7.3% compared to the best two-stage detector. Code will be publicly available.
-
We investigate the problem of training generative models on very sparse collections of 3D models. Particularly, instead of using difficult-to-obtain large sets of 3D models, we demonstrate that geometrically-motivated energy functions can be used to effectively augment and boost only a sparse collection of example (training) models. Technically, we analyze the Hessian of the as-rigid-as-possible (ARAP) energy to adaptively sample from and project to the underlying (local) shape space, and use the augmented dataset to train a variational autoencoder (VAE). We iterate the process, of building latent spaces of VAE and augmenting the associated dataset, to progressively reveal a richer and more expressive generative space for creating geometrically and semantically valid samples. We evaluate our method against a set of strong baselines, provide ablation studies, and demonstrate application towards establishing shape correspondences. GLASS produces multiple interesting and meaningful shape variations even when starting from as few as 3-10 training shapes. Our code is available at https: //sanjeevmk.github.io/glass_webpage/.
-
We present a novel neural implicit representation for articulated human bodies. Compared to explicit template meshes, neural implicit body representations provide an efficient mechanism for modeling interactions with the environment, which is essential for human motion reconstruction and synthesis in 3D scenes. However, existing neural implicit bodies suffer from either poor generalization on highly articulated poses or slow inference time. In this work, we observe that prior knowledge about the human body's shape and kinematic structure can be leveraged to improve generalization and efficiency. We decompose the full-body geometry into local body parts and employ a part-aware encoder-decoder architecture to learn neural articulated occupancy that models complex deformations locally. Our local shape encoder represents the body deformation of not only the corresponding body part but also the neighboring body parts. The decoder incorporates the geometric constraints of local body shape which significantly improves pose generalization. We demonstrate that our model is suitable for resolving self-intersections and collisions with 3D environments. Quantitative and qualitative experiments show that our method largely outperforms existing solutions in terms of both efficiency and accuracy.
-
Since the rise of vision-language navigation (VLN), great progress has been made in instruction following -- building a follower to navigate environments under the guidance of instructions. However, far less attention has been paid to the inverse task: instruction generation -- learning a speaker to generate grounded descriptions for navigation routes. Existing VLN methods train a speaker independently and typically treat it as a data augmentation tool for strengthening the follower, while ignoring rich cross-task relations. Here we describe an approach that learns the two tasks simultaneously and exploits their intrinsic correlations to boost the training of each: the follower judges whether the speaker-created instruction explains the original navigation route correctly, and vice versa. Without the need of aligned instruction-path pairs, such cycle-consistent learning scheme is complementary to task-specific training objectives defined on labeled data, and can also be applied over unlabeled paths (sampled without paired instructions). Another agent, called creator, is added to generate counterfactual environments. It greatly changes current scenes yet leaves novel items -- which are crucial for the execution of original instructions -- unchanged. Thus more informative training scenes are synthesized and the three agents compose a powerful VLN learning system. Experiments on a standard benchmark show that our approach improves the performance of various follower models and produces accurate navigation instructions. Our code will be released.
-
Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution (OOD). The more complex the task to learn, the more likely it is that statistical artifacts (i.e. selection biases, spurious correlations) are simpler than the mechanisms to learn. We demonstrate that the simplicity bias can be mitigated and OOD generalization improved. We train a set of similar models to fit the data in different ways using a penalty on the alignment of their input gradients. We show theoretically and empirically that this induces the learning of more complex predictive patterns. OOD generalization fundamentally requires information beyond i.i.d. examples, such as multiple training environments, counterfactual examples, or other side information. Our approach shows that we can defer this requirement to an independent model selection stage. We obtain SOTA results in visual recognition on biased data and generalization across visual domains. The method - the first to evade the simplicity bias - highlights the need for a better understanding and control of inductive biases in deep learning.
-
Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles. Participants work without fixed instructions, and the sequences feature rich and natural variations in action ordering, mistakes, and corrections. Assembly101 is the first multi-view action dataset, with simultaneous static (8) and egocentric (4) recordings. Sequences are annotated with more than 100K coarse and 1M fine-grained action segments, and 18M 3D hand poses. We benchmark on three action understanding tasks: recognition, anticipation and temporal segmentation. Additionally, we propose a novel task of detecting mistakes. The unique recording format and rich set of annotations allow us to investigate generalization to new toys, cross-view transfer, long-tailed distributions, and pose vs. appearance. We envision that Assembly101 will serve as a new challenge to investigate various activity understanding problems.
-
Given a set of putative 3D-3D point correspondences, we aim to remove outliers and estimate rigid transformation with 6 degrees of freedom (DOF). Simultaneously estimating these 6 DOF is time-consuming due to high-dimensional parameter space. To solve this problem, it is common to decompose 6 DOF, i.e. independently compute 3-DOF rotation and 3-DOF translation. However, high non-linearity of 3-DOF rotation still limits the algorithm efficiency, especially when the number of correspondences is large. In contrast, we propose to decompose 6 DOF into (2+1) and (1+2) DOF. Specifically, (2+1) DOF represent 2-DOF rotation axis and 1-DOF displacement along this rotation axis. (1+2) DOF indicate 1-DOF rotation angle and 2-DOF displacement orthogonal to the above rotation axis. To compute these DOF, we design a novel two-stage strategy based on inlier set maximization. By leveraging branch and bound, we first search for (2+1) DOF, and then the remaining (1+2) DOF. Thanks to the proposed transformation decomposition and two-stage search strategy, our method is deterministic and leads to low computational complexity. We extensively compare our method with state-of-the-art approaches. Our method is more accurate and robust than the approaches that provide similar efficiency to ours. Our method is more efficient than the approaches whose accuracy and robustness are comparable to ours.
-
Implicit neural representation (INR) has been successful in representing static images. Contemporary image-based INR, with the use of Fourier-based positional encoding, can be viewed as a mapping from sinusoidal patterns with different frequencies to image content. Inspired by that view, we hypothesize that it is possible to generate temporally varying content with a single image-based INR model by displacing its input sinusoidal patterns over time. By exploiting the relation between the phase information in sinusoidal functions and their displacements, we incorporate into the conventional image-based INR model a phase-varying positional encoding module, and couple it with a phase-shift generation module that determines the phase-shift values at each frame. The model is trained end-to-end on a video to jointly determine the phase-shift values at each time with the mapping from the phase-shifted sinusoidal functions to the corresponding frame, enabling an implicit video representation. Experiments on a wide range of videos suggest that such a model is capable of learning to interpret phase-varying positional embeddings into the corresponding time-varying content. More importantly, we found that the learned phase-shift vectors tend to capture meaningful temporal and motion information from the video. In particular, manipulating the phase-shift vectors induces meaningful changes in the temporal dynamics of the resulting video, enabling non-trivial temporal and motion editing effects such as temporal interpolation, motion magnification, motion smoothing, and video loop detection.
-
Neural priors are a promising direction to capture low-level vision statistics without relying on handcrafted regularizers. Recent works have successfully shown the use of neural architecture biases to implicitly regularize image denoising, super-resolution, inpainting, synthesis, scene flow, among others. They do not rely on large-scale datasets to capture prior statistics and thus generalize well to out-of-the-distribution data. Inspired by such advances, we investigate neural priors for trajectory representation. Traditionally, trajectories have been represented by a set of handcrafted bases that have limited expressibility. Here, we propose a neural trajectory prior to capture continuous spatio-temporal information without the need for offline data. We demonstrate how our proposed objective is optimized during runtime to estimate trajectories for two important tasks: Non-Rigid Structure from Motion (NRSfM) and lidar scene flow integration for self-driving scenes. Our results are competitive to many state-of-the-art methods for both tasks.
-
We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer trit-planes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.
-
Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent shortcomings, e.g., regression methods tend to overfit due to the indirect learning cost volume, and classification methods cannot directly infer the exact depth due to its discrete prediction. In this paper, we propose a novel representation, termed Unification, to unify the advantages of regression and classification. It can directly constrain the cost volume like classification methods, but also realize the sub-pixel depth prediction like regression methods. To excavate the potential of unification, we design a new loss function named Unified Focal Loss, which is more uniform and reasonable to combat the challenge of sample imbalance. Combining these two unburdened modules, we present a coarse-to-fine framework, that we call UniMVSNet. The results of ranking first on both DTU and Tanks and Temples benchmarks verify that our model not only performs the best but also has the best generalization ability.
-
In the real open world, data tends to follow long-tailed class distributions, motivating the well-studied long-tailed recognition (LTR) problem. Naive training produces models that are biased toward common classes in terms of higher accuracy. The key to addressing LTR is to balance various aspects including data distribution, training losses, and gradients in learning. We explore an orthogonal direction, weight balancing , motivated by the empirical observation that the naively trained classifier has "artificially" larger weights in norm for common classes (because there exists abundant data to train them, unlike the rare classes). We investigate three techniques to balance weights, L2-normalization, weight decay, and MaxNorm. We first point out that L2-normalization "perfectly" balances per-class weights to be unit norm, but such a hard constraint might prevent classes from learning better classifiers. In contrast, weight decay penalizes larger weights more heavily and so learns small balanced weights; the MaxNorm constraint encourages growing small weights within a norm ball but caps all the weights by the radius. Our extensive study shows that both help learn balanced weights and greatly improve the LTR accuracy. Surprisingly, weight decay, although underexplored in LTR, significantly improves over prior work. Therefore, we adopt a two-stage training paradigm and propose a simple approach to LTR: (1) learning features using the cross-entropy loss by tuning weight decay, and (2) learning classifiers using class-balanced loss by tuning weight decay and MaxNorm. Our approach achieves the state-of-the-art accuracy on five standard benchmarks, serving as a future baseline for long-tailed recognition.
-
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an image from noise with sentence embedding, and then refine the features with fine-grained word embedding iteratively. A close inspection of their generated images reveals a major limitation: even though the generated image holistically matches the description, individual image regions or parts of somethings are often not recognizable or consistent with words in the sentence, e.g. "a white crown". To address this problem, we propose a novel framework Semantic-Spatial Aware GAN for synthesizing images from input text. Concretely, we introduce a simple and effective Semantic-Spatial Aware block, which (1) learns semantic-adaptive transformation conditioned on text to effectively fuse text features and image features, and (2) learns a semantic mask in a weakly-supervised way that depends on the current text-image fusion process in order to guide the transformation spatially. Experiments on the challenging COCO and CUB bird datasets demonstrate the advantage of our method over the recent state-of-the-art approaches, regarding both visual fidelity and alignment with input text description. Code available at https://github.com/wtliao/text2image.
-
Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of labeled or unlabeled data from the shifted domain. This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e.g. autonomous driving in challenging weather conditions. To address this problem of continuous adaptation to distribution shifts, we propose Dynamic Unsupervised Adaptation (DUA). By continuously adapting the statistics of the batch normalization layers we modify the feature representations of the model. We show that by sequentially adapting a model with only a fraction of unlabeled data, a strong performance gain can be achieved. With even less than 1% of unlabeled data from the target domain, DUA already achieves competitive results to strong baselines. In addition, the computational overhead is minimal in contrast to previous approaches. Our approach is simple, yet effective and can be applied to any architecture which uses batch normalization as one of its components. We show the utility of DUA by evaluating it on a variety of domain adaptation datasets and tasks including object recognition, digit recognition and object detection.
-
We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds. The resultant distribution can then be sampled to generate likely completions, each of which exhibits plausible shape details, while being faithful to the input. To facilitate the use of transformers for 3D, we introduce a compact 3D representation, vector quantized deep implicit function (VQDIF), that utilizes spatial sparsity to represent a close approximation of a 3D shape by a short sequence of discrete variables. Experiments demonstrate that ShapeFormer outperforms prior art for shape completion from ambiguous partial inputs in terms of both completion quality and diversity. We also show that our approach effectively handles a variety of shape types, incomplete patterns, and real-world scans.
-
In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy. These other goals include out-of-distribution (OOD) robustness, prediction consistency, resilience to adversaries, calibrated uncertainty estimates, and the ability to detect anomalous inputs. However, improving performance towards these goals is often a balancing act that today's methods cannot achieve without sacrificing performance on other safety axes. For instance, adversarial training improves adversarial robustness but sharply degrades other classifier performance metrics. Similarly, strong data augmentation and regularization techniques often improve OOD robustness but harm anomaly detection, raising the question of whether a Pareto improvement on all existing safety measures is possible. To meet this challenge, we design a new data augmentation strategy utilizing the natural structural complexity of pictures such as fractals, which outperforms numerous baselines, is near Pareto-optimal, and roundly improves safety measures.
-
Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, we represent an object boundary by a linear combination of the M eigencontours. We also incorporate the eigencontours into an instance segmentation framework. Experimental results demonstrate that the proposed eigencontours can represent object boundaries more effectively and more efficiently than existing descriptors in a low-dimensional space. Furthermore, the proposed algorithm yields meaningful performances on instance segmentation datasets.
-
For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain? This setting, namely generalizable cross-modality segmentation, owning its clinical potential, is much more challenging than other related settings, e.g., domain adaptation. To achieve this goal, we in this paper propose a novel dual-normalization model by leveraging the augmented source-similar and source-dissimilar images during our generalizable segmentation. To be specific, given a single source domain, aiming to simulate the possible appearance change in unseen target domains, we first utilize a nonlinear transformation to augment source-similar and source-dissimilar images. Then, to sufficiently exploit these two types of augmentations, our proposed dual-normalization based model employs a shared backbone yet independent batch normalization layer for separate normalization. Afterward, we put forward a style-based selection scheme to automatically choose the appropriate path in the test stage. Extensive experiments on three publicly available datasets, i.e., BraTS, Cross-Modality Cardiac, and Abdominal Multi-Organ datasets, have demonstrated that our method outperforms other state-of-the-art domain generalization methods. Code is available at https://github.com/zzzqzhou/Dual-Normalization.
-
Optical flow is a fundamental method used for quantitative motion estimation on the image plane. In the deep learning era, most works treat it as a task of 'matching of features', learning to pull matched pixels as close as possible in feature space and vice versa. However, spatial affinity (smoothness constraint), another important component for motion understanding, has been largely overlooked. In this paper, we introduce a novel approach, called kernel patch attention (KPA), to better resolve the ambiguity in dense matching by explicitly taking the local context relations into consideration. Our KPA operates on each local patch, and learns to mine the context affinities for better inferring the flow fields. It can be plugged into contemporary optical flow architecture and empower the model to conduct comprehensive motion analysis with both feature similarities and spatial relations. On Sintel dataset, the proposed KPA-Flow achieves the best performance with EPE of 1.35 on clean pass and 2.36 on final pass, and it sets a new record of 4.60% in F1-all on KITTI-15 benchmark.
-
Recently, vision-language pre-training shows great potential in open-vocabulary object detection, where detectors trained on base classes are devised for detecting new classes. The class text embedding is firstly generated by feeding prompts to the text encoder of a pre-trained vision-language model. It is then used as the region classifier to supervise the training of a detector. The key element that leads to the success of this model is the proper prompt, which requires careful words tuning and ingenious design. To avoid laborious prompt engineering, there are some prompt representation learning methods being proposed for the image classification task, which however can only be sub-optimal solutions when applied to the detection task. In this paper, we introduce a novel method, detection prompt (DetPro), to learn continuous prompt representations for open-vocabulary object detection based on the pre-trained vision-language model. Different from the previous classification-oriented methods, DetPro has two highlights: 1) a background interpretation scheme to include the proposals in image background into the prompt training; 2) a context grading scheme to separate proposals in image foreground for tailored prompt training. We assemble DetPro with ViLD, a recent state-of-the-art openworld object detector, and conduct experiments on the LVIS as well as transfer learning on the Pascal VOC, COCO, Objects365 datasets. Experimental results show that our DetPro outperforms the baseline ViLD [5] in all settings, e.g., +3.4 APbox and +3.0 APmask improvements on the novel classes of LVIS. Code and models are available at https://github.com/dyabel/detpro.
-
Recording fast motion in a high FPS (frame-per-second) requires expensive high-speed cameras. As an alternative, interpolating low-FPS videos from commodity cameras has attracted significant attention. If only low-FPS videos are available, motion assumptions (linear or quadratic) are necessary to infer intermediate frames, which fail to model complex motions. Event camera, a new camera with pixels producing events of brightness change at the temporal resolution of \mu s (10^ -6 second ), is a game-changing device to enable video interpolation at the presence of arbitrarily complex motion. Since event camera is a novel sensor, its potential has not been fulfilled due to the lack of processing algorithms. The pioneering work Time Lens introduced event cameras to video interpolation by designing optical devices to collect a large amount of paired training data of high-speed frames and events, which is too costly to scale. To fully unlock the potential of event cameras, this paper proposes a novel TimeReplayer algorithm to interpolate videos captured by commodity cameras with events. It is trained in an unsupervised cycle-consistent style, canceling the necessity of high-speed training data and bringing the additional ability of video extrapolation. Its state-of-the-art results and demo videos in supplementary reveal the promising future of event-based vision.
-
Continual learning is an important problem for achieving human-level intelligence in real-world applications as an agent must continuously accumulate knowledge in response to streaming data/tasks. In this work, we consider a general and yet under-explored incremental learning problem in which both the class distribution and class-specific domain distribution change over time. In addition to the typical challenges in class incremental learning, this setting also faces the intra-class stability-plasticity dilemma and intra-class domain imbalance problems. To address above issues, we develop a novel domain-aware continual learning method based on the EM framework. Specifically, we introduce a flexible class representation based on the von Mises-Fisher mixture model to capture the intra-class structure, using an expansion-and-reduction strategy to dynamically increase the number of components according to the class complexity. Moreover, we design a bi-level balanced memory to cope with data imbalances within and across classes, which combines with a distillation loss to achieve better inter- and intra-class stability-plasticity trade-off. We conduct exhaustive experiments on three benchmarks: iDigits, iDomainNet and iCIFAR-20. The results show that our approach consistently outperforms previous methods by a significant margin, demonstrating its superiority.
-
We introduce an interactive image segmentation and visualization framework for identifying, inspecting, and editing tiny objects (just a few pixels wide) in large multi-megapixel high-dynamic-range (HDR) images. Detecting cosmic rays (CRs) in astronomical observations is a cumbersome workflow that requires multiple tools, so we developed an interactive toolkit that unifies model inference, HDR image visualization, segmentation mask inspection and editing into a single graphical user interface. The feature set, initially designed for astronomical data, makes this work a useful research-supporting tool for human-in-the-loop tiny-object segmentation in scientific areas like biomedicine, materials science, remote sensing, etc., as well as computer vision. Our interface features mouse-controlled, synchronized, dual-window visualization of the image and the segmentation mask, a critical feature for locating tiny objects in multi-megapixel images. The browser-based tool can be readily hosted on the web to provide multi-user access and GPU acceleration for any device. The toolkit can also be used as a high-precision annotation tool, or adapted as the frontend for an interactive machine learning framework. Our open-source dataset, CR detection model, and visualization toolkit are available at https://github.com/cy-xu/cosmic-conn.
-
Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a method that leverages the best of both worlds. In this paper we present a new framework, ActiveZero, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. First, we demonstrate the transferability of our method to out-of-distribution real data by using a mixed domain learning strategy. In the simulation domain, we use a combination of supervised disparity loss and self-supervised losses on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised losses on a dataset that is out-of-distribution from either training simulation data or test real data. Second, our method introduces a novel self-supervised loss called temporal IR reprojection to increase the robustness and accuracy of our reprojections in hard-to-perceive regions. Finally, we show how the method can be trained end-to-end and that each module is important for attaining the end result. Extensive qualitative and quantitative evaluations on real data demonstrate state of the art results that can even beat a commercial depth sensor.
-
Transformers have been successfully applied to computer vision due to its powerful modelling capacity with self-attention. However, the good performance of transformers heavily depends on enormous training images. Thus, a data-efficient transformer solution is urgently needed. In this work, we propose an early knowledge distillation framework, which is termed as DearKD, to improvethe data-efficiency required by transformers. Our DearKD is a two-stage framework that first distills the inductive biases from the early intermediate layers of a CNN and then gives the transformer full play by training without distillation. Further, our DearKD can also be applied to the extreme data-free case where no real images are available, where we propose a boundary-preserving intra-divergence loss based on DeepInversion to further close the performance gap against the full-data counterpart. Extensive experiments on ImageNet, partial ImageNet, data-free setting and other downstream tasks prove the superiority of DearKD over its baselines and state-of-the-art methods.
-
We propose a novel method of registering less-overlap RGB-D scans. Our method learns global information of a scene to construct a panorama, and aligns RGB-D scans to the panorama to perform registration. Different from existing methods that use local feature points to register less-overlap RGB-D scans and mismatch too much, we use global information to guide the registration, thereby alleviating the mismatching problem by preserving global consistency of alignments. To this end, we build a scene inference network to construct the panorama representing global information. We introduce a reinforcement learning strategy to iteratively align RGB-D scans with the panorama and refine the panorama representation, which reduces the noise of global information and preserves global consistency of both geometric and photometric alignments. Experimental results on benchmark datasets including SUNCG, Matterport, and ScanNet show the superiority of our method.
-
Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We also devise a multi-task learning for better optimization convergence and depth accuracy. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving overall reconstruction score of 0.33mm on DTU and f-score of 59.48% on Tanks & Temples.
-
Partially-supervised instance segmentation is a task which requests segmenting objects from novel categories via learning on limited base categories with annotated masks thus eliminating demands of heavy annotation burden. The key to addressing this task is to build an effective class-agnostic mask segmentation model. Unlike previous methods that learn such models only on base categories, in this paper, we propose a new method, named ContrastMask, which learns a mask segmentation model on both base and novel categories under a unified pixel-level contrastive learning framework. In this framework, annotated masks of base categories and pseudo masks of novel categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa. Through this framework, feature discrimination between foreground and background is largely improved, facilitating learning of the class-agnostic mask segmentation model. Exhaustive experiments on the COCO dataset demonstrate the superiority of our method, which outperforms previous state-of-the-arts.
-
Recently deep learning methods have shown significant progress in data clustering tasks. Deep clustering methods (including distance-based methods and subspace-based methods) integrate clustering and feature learning into a unified framework, where there is a mutual promotion between clustering and representation. However, deep subspace clustering methods are usually in the framework of self-expressive model and hence have quadratic time and space complexities, which prevents their applications in large-scale clustering and real-time clustering. In this paper, we propose a new mechanism for deep clustering. We aim to learn the subspace bases from deep representation in an iterative refining manner while the refined subspace bases help learning the representation of the deep neural networks in return. The proposed method is out of the self-expressive framework, scales to the sample size linearly, and is applicable to arbitrarily large datasets and online clustering scenarios. More importantly, the clustering accuracy of the proposed method is much higher than its competitors. Extensive comparison studies with state-of-the-art clustering approaches on benchmark datasets demonstrate the superiority of the proposed method.
-
Due to the visual ambiguity, purely kinematic formulations on monocular human motion capture are often physically incorrect, biomechanically implausible, and can not reconstruct accurate interactions. In this work, we focus on exploiting the high-precision and non-differentiable physics simulator to incorporate dynamical constraints in motion capture. Our key-idea is to use real physical supervisions to train a target pose distribution prior for sampling-based motion control to capture physically plausible human motion. To obtain accurate reference motion with terrain interactions for the sampling, we first introduce an interaction constraint based on SDF (Signed Distance Field) to enforce appropriate ground contact modeling. We then design a novel two-branch decoder to avoid stochastic error from pseudo ground-truth and train a distribution prior with the non-differentiable physics simulator. Finally, we regress the sampling distribution from the current state of the physical character with the trained prior and sample satisfied target poses to track the estimated reference motion. Qualitative and quantitative results show that we can obtain physically plausible human motion with complex terrain interactions, human shape variations, and diverse behaviors. More information can be found at https://www.yangangwang.com/papers/HBZ-NM-2022-03.html
-
Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is helpful in modeling distant correspondences, error accumulation is inevitable due to the propagation mechanism. In this work, we present a novel, generic iterative alignment module which employs a gradual refinement scheme for sub-alignments, yielding more accurate motion compensation. To further enhance the alignment accuracy and temporal consistency, we develop a non-parametric re-weighting method, where the importance of each neighboring frame is adaptively evaluated in a spatial-wise way for aggregation. By virtue of the proposed strategies, our model achieves state-of-the-art performance on multiple benchmarks across a range of video restoration tasks including video super-resolution, denoising and deblurring.
-
Vision Transformers (ViTs) and their multi-scale and hierarchical variations have been successful at capturing image representations but their use has been generally studied for low-resolution images (e.g. - 256x256, 384x384). For gigapixel whole-slide imaging (WSI) in computational pathology, WSIs can be as large as 150000x150000 pixels at 20x magnification and exhibit a hierarchical structure of visual tokens across varying resolutions: from 16x16 images capture spatial patterns among cells, to 4096x4096 images characterizing interactions within the tissue microenvironment. We introduce a new ViT architecture called the Hierarchical Image Pyramid Transformer (HIPT), which leverages the natural hierarchical structure inherent in WSIs using two levels of self-supervised learning to learn high-resolution image representations. HIPT is pretrained across 33 cancer types using 10,678 gigapixel WSIs, 408,218 4096x4096 images, and 104M 256x256 images. We benchmark HIPT representations on 9 slide-level tasks, and demonstrate that: 1) HIPT with hierarchical pretraining outperforms current state-of-the-art methods for cancer subtyping and survival prediction, 2) self-supervised ViTs are able to model important inductive biases about the hierarchical structure of phenotypes in the tumor microenvironment.
-
This paper aims at recovering the shape of a scene with unknown, non-Lambertian, and possibly spatially-varying surface materials. When the shape of the object is highly complex and that shadows cast on the surface, the task becomes very challenging. To overcome these challenges, we propose a coordinate-based deep MLP (multilayer perceptron) to parameterize both the unknown 3D shape and the unknown reflectance at every surface point. This network is able to leverage the observed photometric variance and shadows on the surface, and recover both surface shape and general non-Lambertian reflectance. We explicitly predict cast shadows, mitigating possible artifacts on these shadowing regions, leading to higher estimation accuracy. Our framework is entirely self-supervised, in the sense that it requires neither ground truth shape nor BRDF. Tests on real-world images demonstrate that our method outperform existing methods by a significant margin. Thanks to the small size of the MLP-net, our method is an order of magnitude faster than previous CNN-based methods.
-
Transfer learning, where the goal is to transfer the well-trained deep learning models from a primary source task to a new task, is a crucial learning scheme for on-device machine learning, due to the fact that IoT/edge devices collect and then process massive data in our daily life. However, due to the tiny memory constraint in IoT/edge devices, such on-device learning requires ultra-small training memory footprint, bringing new challenges for memory-efficient learning. Many existing works solve this problem by reducing the number of trainable parameters. However, this doesn't directly translate to memory-saving since the major bottleneck is the activations, not parameters. To develop memory-efficient on-device transfer learning, in this work, we are the first to approach the concept of transfer learning from a new perspective of intermediate feature reprogramming of a pre-trained model (i.e., backbone). To perform this lightweight and memory-efficient reprogramming, we propose to train a tiny Reprogramming Network (Rep-Net) directly from the new task input data, while freezing the backbone model. The proposed Rep-Net model interchanges the features with the backbone model using an activation connector at regular intervals to mutually benefit both the backbone model and Rep-Net model features. Through extensive experiments, we validate each design specs of the proposed Rep-Net model in achieving highly memory-efficient on-device reprogramming. Our experiments establish the superior performance (i.e., low training memory and high accuracy) of Rep-Net compared to SOTA on-device transfer learning schemes across multiple benchmarks.
-
Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present RepSurf (representative surfaces), a novel representation of point clouds to explicitly depict the very local structure. We explore two variants of RepSurf, Triangular RepSurf and Umbrella RepSurf inspired by triangle meshes and umbrella curvature in computer graphics. We compute the representations of RepSurf by predefined geometric priors after surface reconstruction. RepSurf can be a plug-and-play module for most point cloud models thanks to its free collaboration with irregular points. Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. With an increase of around 0.008M number of parameters, 0.04G FLOPs, and 1.12ms inference time, our method achieves 94.7% (+0.5%) on ModelNet40, and 84.6% (+1.8%) on ScanObjectNN for classification, while 74.3% (+0.8%) mIoU on S3DIS 6-fold, and 70.0% (+1.6%) mIoU on ScanNet for segmentation. For detection, previous state-of-the-art detector with our RepSurf obtains 71.2% (+2.1%) mAP_25, 54.8% (+2.0%) mAP_50 on ScanNetV2, and 64.9% (+1.9%) mAP_25, 47.1% (+2.5%) mAP_50 on SUN RGB-D. Our lightweight Triangular RepSurf performs its excellence on these benchmarks as well. The code is publicly available at https://github.com/hancyran/RepSurf.
-
We propose a new video camouflaged object detection (VCOD) framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames. An essential property of camouflaged objects is that they usually exhibit patterns similar to the background and thus make them hard to identify from still images. Therefore, effectively handling temporal dynamics in videos becomes the key for the VCOD task as the camouflaged objects will be noticeable when they move. However, current VCOD methods often leverage homography or optical flows to represent motions, where the detection error may accumulate from both the motion estimation error and the segmentation error. On the other hand, our method unifies motion estimation and object segmentation within a single optimization framework. Specifically, we build a dense correlation volume to implicitly capture motions between neighbouring frames and utilize the final segmentation supervision to optimize the implicit motion estimation and segmentation jointly. Furthermore, to enforce temporal consistency within a video sequence, we jointly utilize a spatio-temporal transformer to refine the short-term predictions. Extensive experiments on VCOD benchmarks demonstrate the architectural effectiveness of our approach. We also provide a large-scale VCOD dataset named MoCA-Mask with pixel-level handcrafted ground-truth masks and construct a comprehensive VCOD benchmark with previous methods to facilitate research in this direction. Dataset Link: https://xueliancheng.github.io/SLT-Net-project.
-
This paper proposes a universal framework, called OVE6D, for model-based 6D object pose estimation from a single depth image and a target object mask. Our model is trained using purely synthetic data rendered from ShapeNet, and, unlike most of the existing methods, it generalizes well on new real-world objects without any fine-tuning. We achieve this by decomposing the 6D pose into viewpoint, in-plane rotation around the camera optical axis and translation, and introducing novel lightweight modules for estimating each component in a cascaded manner. The resulting network contains less than 4M parameters while demonstrating excellent performance on the challenging T-LESS and Occluded LINEMOD datasets without any dataset-specific training. We show that OVE6D outperforms some contemporary deep learning-based pose estimation methods specifically trained for individual objects or datasets with real-world training data.
-
In the clinic, resected tissue samples are stained with Hematoxylin-and-Eosin (H&E) and/or Immunhistochemistry (IHC) stains and presented to the pathologists on glass slides or as digital scans for diagnosis and assessment of disease progression. Cell-level quantification, e.g. in IHC protein expression scoring, can be extremely inefficient and subjective. We present DeepLIIF (https://deepliif.org), a first free online platform for efficient and reproducible IHC scoring. DeepLIIF outperforms current state-of-the-art approaches (relying on manual error-prone annotations) by virtually restaining clinical IHC slides with more informative multiplex immunofluorescence staining. Our DeepLIIF cloud-native platform supports (1) more than 150 proprietary/non-proprietary input formats via the Bio-Formats standard, (2) interactive adjustment, visualization, and downloading of the IHC quantification results and the accompanying restained images, (3) consumption of an exposed workflow API programmatically or through interactive plugins for open source whole slide image viewers such as QuPath/ImageJ, and (4) auto scaling to efficiently scale GPU resources based on user demand.
-
Video summarization has recently engaged increasing attention in computer vision communities. However, the scarcity of annotated data has been a key obstacle in this task. To address it, this work explores a new solution for video summarization by transferring samples from a correlated task (i.e., video moment localization) equipped with abundant training data. Our main insight is that the annotated video moments also indicate the semantic highlights of a video, essentially similar to video summary. Approximately, the video summary can be treated as a sparse, redundancy-free version of the video moments. Inspired by this observation, we propose an importance Propagation based collaborative Teaching Network (iPTNet). It consists of two separate modules that conduct video summarization and moment localization, respectively. Each module estimates a frame-wise importance map for indicating keyframes or moments. To perform cross-task sample transfer, we devise an importance propagation module that realizes the conversion between summarization-guided and localization-guided importance maps. This way critically enables optimizing one of the tasks using the data from the other task. Additionally, in order to avoid error amplification caused by batch-wise joint training, we devise a collaborative teaching scheme, which adopts a cross-task mean teaching strategy to realize the joint optimization of the two tasks and provide robust frame-level teaching signals. Extensive experiments on video summarization benchmarks demonstrate that iPTNet significantly outperforms previous state-of-the-art video summarization methods, serving as an effective solution that overcomes the data scarcity issue in video summarization.
-
Current methods for object detection, segmentation, and tracking fail in the presence of severe occlusions in busy urban environments. Labeled real data of occlusions is scarce (even in large datasets) and synthetic data leaves a domain gap, making it hard to explicitly model and learn occlusions. In this work, we present the best of both the real and synthetic worlds for automatic occlusion supervision using a large readily available source of data: time-lapse imagery from stationary webcams observing street intersections over weeks, months, or even years. We introduce a new dataset, Watch and Learn Time-lapse (WALT), consisting of 12 (4K and 1080p) cameras capturing urban environments over a year. We exploit this real data in a novel way to automatically mine a large set of unoccluded objects and then composite them in the same views to generate occlusions. This longitudinal self-supervision is strong enough for an amodal network to learn object-occluder-occluded layer representations. We show how to speed up the discovery of unoccluded objects and relate the confidence in this discovery to the rate and accuracy of training occluded objects. After watching and automatically learning for several days, this approach shows significant performance improvement in detecting and segmenting occluded people and vehicles, over human-supervised amodal approaches.
-
In this paper, we study an untouched problem in visible-infrared person re-identification (VI-ReID), namely, Twin Noise Labels (TNL) which refers to as noisy annotation and correspondence. In brief, on the one hand, it is inevitable to annotate some persons with the wrong identity due to the complexity in data collection and annotation, e.g., the poor recognizability in the infrared modality. On the other hand, the wrongly annotated data in a single modality will eventually contaminate the cross-modal correspondence, thus leading to noisy correspondence. To solve the TNL problem, we propose a novel method for robust VI-ReID, termed DuAlly Robust Training (DART). In brief, DART first computes the clean confidence of annotations by resorting to the memorization effect of deep neural networks. Then, the proposed method rectifies the noisy correspondence with the estimated confidence and further divides the data into four groups for further utilizations. Finally, DART employs a novel dually robust loss consisting of a soft identification loss and an adaptive quadruplet loss to achieve robustness on the noisy annotation and noisy correspondence. Extensive experiments on SYSU-MM01 and RegDB datasets verify the effectiveness of our method against the twin noisy labels compared with five state-of-the-art methods. The code could be accessed from https://github.com/XLearning-SCU/2022-CVPR-DART.
-
As a bio-inspired sensor with high temporal resolution, the spiking camera has an enormous potential in real applications, especially for motion estimation in high-speed scenes. However, frame-based and event-based methods are not well suited to spike streams from the spiking camera due to the different data modalities. To this end, we present, SCFlow, a tailored deep learning pipeline to estimate optical flow in high-speed scenes from spike streams. Importantly, a novel input representation is introduced which can adaptively remove the motion blur in spike streams according to the prior motion. Further, for training SCFlow, we synthesize two sets of optical flow data for the spiking camera, SPIkingly Flying Things and Photo-realistic High-speed Motion, denoted as SPIFT and PHM respectively, corresponding to random high-speed and well-designed scenes. Experimental results show that the SCFlow can predict optical flow from spike streams in different high-speed scenes. Moreover, SCFlow shows promising generalization on real spike streams. Codes and datasets refer to https://github.com/Acnext/Optical-Flow-For-Spiking-Camera.
-
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1% top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 49%/61% fewer MACs. The effectiveness of PoolFormer verifies our hypothesis and urges us to initiate the concept of "MetaFormer", a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.
-
In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce a method, named GradViT, that optimizes random noise into naturally looking images via an iterative process. The optimization objective consists of (i) a loss on matching the gradients, (ii) image prior in the form of distance to batch normalization statistics of a pretrained CNN model, and (iii) a total variation regularization on patches to guide correct recovery locations. We propose a unique loss scheduling function to overcome local minima during optimization. We evaluate GadViT on ImageNet1K and MS-Celeb-1M datasets, and observe unprecedentedly high fidelity and closeness to the original (hidden) data. During the analysis we find that vision transformers are significantly more vulnerable than previously studied CNNs due to the presence of the attention mechanism. Our method demonstrates new state-of-the-art results for gradient inversion in both qualitative and quantitative metrics. Project page at https://gradvit.github.io.
-
Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate super-resolved videos with higher resolution (HR) and higher frame rate (HFR). Quite intuitively, pioneering two-stage based methods complete ST-VSR directly combining two sub-tasks: Spatial Video Super-Resolution (S-VSR) and Temporal Video Super-Resolution (T-VSR) but ignore the reciprocal relations among them. Specifically, 1) T-VSR to S-VSR: temporal correlations help accurate spatial detail representation with more clues; 2) S-VSR to T-VSR: abundant spatial information contributes to the refinement of temporal prediction. To this end, we propose a one-stage based Cycle-projected Mutual learning network (CycMu-Net) for ST-VSR, which makes full use of spatial-temporal correlations via the mutual learning between S-VSR and T-VSR. Specifically, we propose to exploit the mutual information among them via iterative up-and-down projections, where the spatial and temporal features are fully fused and distilled, helping the high-quality video reconstruction. Besides extensive experiments on benchmark datasets, we also compare our proposed CycMu-Net with S-VSR and T-VSR tasks, demonstrating that our method significantly outperforms state-of-the-art methods. Codes are publicly available at: https://github.com/hhhhhumengshun/CycMuNet.
-
We present a novel Transformer-based network architecture for instance-aware image-to-image translation, dubbed InstaFormer, to effectively integrate global- and instance-level information. By considering extracted content features from an image as tokens, our networks discover global consensus of content features by considering context information through a self-attention module in Transformers. By augmenting such tokens with an instance-level feature extracted from the content feature with respect to bounding box information, our framework is capable of learning an interaction between object instances and the global image, thus boosting the instance-awareness. We replace layer normalization (LayerNorm) in standard Transformers with adaptive instance normalization (AdaIN) to enable a multi-modal translation with style codes. In addition, to improve the instance-awareness and translation quality at object regions, we present an instance-level content contrastive loss defined between input and translated image. We conduct experiments to demonstrate the effectiveness of our InstaFormer over the latest methods and provide extensive ablation studies.
-
This work addresses the task of overhead image segmentation when auxiliary ground-level images are available. Recent work has shown that performing joint inference over these two modalities, often called near/remote sensing, can yield significant accuracy improvements. Extending this line of work, we introduce the concept of geospatial attention, a geometry-aware attention mechanism that explicitly considers the geospatial relationship between the pixels in a ground-level image and a geographic location. We propose an approach for computing geospatial attention that incorporates geometric features and the appearance of the overhead and ground-level imagery. We introduce a novel architecture for near/remote sensing that is based on geospatial attention and demonstrate its use for five segmentation tasks. The results demonstrate that our method significantly outperforms the previous state-of-the-art methods.
-
Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG. One of the keys to this success is learned entropy models that estimate the probability distribution of the quantized latent representation. Like other vision tasks, most recent learned entropy models are based on convolutional neural networks (CNNs). However, CNNs have a limitation in modeling long-range dependencies due to their nature of local connectivity, which can be a significant bottleneck in image compression where reducing spatial redundancy is a key point. To overcome this issue, we propose a novel entropy model called Information Transformer (Informer) that exploits both global and local information in a content-dependent manner using an attention mechanism. Our experiments show that Informer improves rate-distortion performance over the state-of-the-art methods on the Kodak and Tecnick datasets without the quadratic computational complexity problem. Our source code is available at https://github.com/naver-ai/informer.
-
Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial matching fashion. However, people tend to overlook the fact that, due to the architecture differences, the semantic information on the same spatial location usually vary. This greatly undermines the underlying assumption of the one-to-one distillation approach. To this end, we propose a novel one-to-all spatial matching knowledge distillation approach. Specifically, we allow each pixel of the teacher feature to be distilled to all spatial locations of the student features given its similarity, which is generated from a target-aware transformer. Our approach surpasses the state-of-the-art methods by a significant margin on various computer vision benchmarks, such as ImageNet, Pascal VOC and COCOStuff10k. Code is available at https://github.com/sihaoevery/TaT.
-
Existing video understanding approaches, such as 3D convolutional neural networks and Transformer-Based methods, usually process the videos in a clip-wise manner. Hence huge GPU memory is needed, and fixed-length video clips are usually required. We introduce a novel Recurrent Vision Transformer (RViT) framework for spatial-temporal representation learning to achieve the video action recognition task. Specifically, the proposed RViT is equipped with an attention gate which is utilized to build interaction between current frame input and previous hidden state, thus aggregating the global level inter-frame features through the hidden state. RViT is executed recurrently to process a video clip by giving the current frame and previous hidden state. The RViT can capture both spatial and temporal features because of the attention gate and recurrent execution. Besides, the proposed RViT can work on both fixed-length and variant-length video clips properly without requiring large GPU memory thanks to the frame by frame processing flow. Our experiment results verify that RViT can achieve state-of-the-art performance on various datasets for the video recognition task. Specifically, RViT can achieve a top-1 accuracy of 81.5% on Kinetics-400, 92.31% on Jester, 67.9% on Something-Something-V2, and an mAP accuracy of 66.1% on Charades.
-
Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust. However, a serious problem of catastrophic overfitting exists, i.e., the robust accuracy against projected gradient descent (PGD) attack suddenly drops to 0% during the training. In this paper, we approach this problem from a novel perspective of optimization and firstly reveal the close link between the fast-growing gradient of each sample and overfitting, which can also be applied to understand robust overfitting in multi-step AT. To control the growth of the gradient, we propose a new AT method, Subspace Adversarial Training (Sub-AT), which constrains AT in a carefully extracted subspace. It successfully resolves both kinds of overfitting and significantly boosts the robustness. In subspace, we also allow single-step AT with larger steps and larger radius, further improving the robustness performance. As a result, we achieve state-of-the-art single-step AT performance. Without any regularization term, our single-step AT can reach over 51% robust accuracy against strong PGD-50 attack of radius 8/255 on CIFAR-10, reaching a competitive performance against standard multi-step PGD-10 AT with huge computational advantages. The code is released at https://github.com/nblt/Sub-AT.
-
3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection
As 3D object detection on point clouds relies on the geometrical relationships between the points, non-standard object shapes can hinder a method's detection capability. However, in safety-critical settings, robustness to out-of-domain and long-tail samples is fundamental to circumvent dangerous issues, such as the misdetection of damaged or rare cars. In this work, we substantially improve the generalization of 3D object detectors to out-of-domain data by deforming point clouds during training. We achieve this with 3D-VField: a novel data augmentation method that plausibly deforms objects via vector fields learned in an adversarial fashion. Our approach constrains 3D points to slide along their sensor view rays while neither adding nor removing any of them. The obtained vectors are transferable, sample-independent and preserve shape and occlusions. Despite training only on a standard dataset, such as KITTI, augmenting with our vector fields significantly improves the generalization to differently shaped objects and scenes. Towards this end, we propose and share CrashD: a synthetic dataset of realistic damaged and rare cars, with a variety of crash scenarios. Extensive experiments on KITTI, Waymo, our CrashD and SUN RGB-D show the generalizability of our techniques to out-of-domain data, different models and sensors, namely LiDAR and ToF cameras, for both indoor and outdoor scenes. Our CrashD dataset is available at https://crashd-cars.github.io.
-
Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses these expressions. Here we propose a system that can generate image segmentations based on arbitrary prompts at test time. A prompt can be either a text or an image. This approach enables us to create a unified model (trained once) for three common segmentation tasks, which come with distinct challenges: referring expression segmentation, zero-shot segmentation and one-shot segmentation. We build upon the CLIP model as a backbone which we extend with a transformer-based decoder that enables dense prediction. After training on an extended version of the PhraseCut dataset, our system generates a binary segmentation map for an image based on a free-text prompt or on an additional image expressing the query. We analyze different variants of the latter image-based prompts in detail. This novel hybrid input allows for dynamic adaptation not only to the three segmentation tasks mentioned above, but to any binary segmentation task where a text or image query can be formulated. Finally, we find our system to adapt well to generalized queries involving affordances or properties. Code is available at https://eckerlab.org/code/clipseg
-
Autonomous driving datasets have played an important role in validating the advancement of intelligent vehicle algorithms including localization, perception and prediction in academic areas. However, current existing datasets pay more attention to the structured urban road, which hampers the exploration on unstructured special scenarios. Moreover, the open-pit mine is one of the typical representatives for them. Therefore, we introduce the Autonomous driving dataset on the Mining scene (AutoMine) for positioning and perception tasks in this paper. The AutoMine is collected by multiple acquisition platforms including an SUV, a wide-body mining truck and an ordinary mining truck, depending on the actual mine operation scenarios. The dataset consists of 18+ driving hours, 18K annotated lidar and image frames for 3D perception with various mines, time-of-the-day and weather conditions. The main contributions of the AutoMine dataset are as follows: 1.The first autonomous driving dataset for perception and localization in mine scenarios. 2.There are abundant dynamic obstacles of 9 degrees of freedom with large dimension difference (mining trucks and pedestrians) and extreme climatic conditions (the dust and snow) in the mining area. 3.Multi-platform acquisition strategies could capture mining data from multiple perspectives that fit the actual operation. More details can be found in our website(https://automine.cc).
-
Learned image compression has achieved great success due to its excellent modeling capacity, but seldom further considers the Rate-Distortion Optimization (RDO) of each input image. To explore this potential in the learned codec, we make the first attempt to build a neural data-dependent transform and introduce a continuous online mode decision mechanism to jointly optimize the coding efficiency for each individual image. Specifically, apart from the image content stream, we employ an additional model stream to generate the transform parameters at the decoder side. The presence of a model stream enables our model to learn more abstract neural-syntax, which helps cluster the latent representations of images more compactly. Beyond the transform stage, we also adopt neural-syntax based post-processing for the scenarios that require higher quality reconstructions regardless of extra decoding overhead. Moreover, the involvement of the model stream further makes it possible to optimize both the representation and the decoder in an online way, i.e. RDO at the testing time. It is equivalent to a continuous online mode decision, like coding modes in the traditional codecs, to improve the coding efficiency based on the individual input image. The experimental results show the effectiveness of the proposed neural-syntax design and the continuous online mode decision mechanism, demonstrating the superiority of our method in coding efficiency.
-
Weakly supervised object localization (WSOL) aims to localize objects using only image-level labels. Recently a new paradigm has emerged by generating a foreground prediction map (FPM) to achieve localization task. Existing FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator. We argue for using activation value to achieve more efficient learning. It is based on the experimental observation that, for a trained network, CE converges to zero when the foreground mask covers only part of the object region. While activation value increases until the mask expands to the object boundary, which indicates that more object areas can be learned by using activation value. In this paper, we propose a Background Activation Suppression (BAS) method. Specifically, an Activation Map Constraint module (AMC) is designed to facilitate the learning of generator by suppressing the background activation value. Meanwhile, by using the foreground region guidance and the area constraint, BAS can learn the whole region of the object. In the inference phase, we consider the prediction maps of different categories together to obtain the final localization results. Extensive experiments show that BAS achieves significant and consistent improvement over the baseline methods on the CUB-200-2011 and ILSVRC datasets. Code and models are available at https://github.com/wpy1999/BAS.
-
Accurate prediction of future human positions is an essential task for modern video-surveillance systems. Current state-of-the-art models usually rely on a "history" of past tracked locations (e.g., 3 to 5 seconds) to predict a plausible sequence of future locations (e.g., up to the next 5 seconds). We feel that this common schema neglects critical traits of realistic applications: as the collection of input trajectories involves machine perception (i.e., detection and tracking), incorrect detection and fragmentation errors may accumulate in crowded scenes, leading to tracking drifts. On this account, the model would be fed with corrupted and noisy input data, thus fatally affecting its prediction performance. In this regard, we focus on delivering accurate predictions when only a few input observations are used, thus potentially lowering the risks associated with automatic perception. To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones). We show that a properly defined teacher supervision allows a student network to perform comparably to state-of-the-art approaches that demand more observations. Besides, extensive experiments on common trajectory forecasting datasets highlight that our student network better generalizes to unseen scenarios.
-
Knowledge distillation (KD) is a widely-used technique that utilizes large networks to improve the performance of compact models. Previous KD approaches usually aim to guide the student to mimic the teacher's behavior completely in the representation space. However, such one-to-one corresponding constraints may lead to inflexible knowledge transfer from the teacher to the student, especially those with low model capacities. Inspired by the ultimate goal of KD methods, we propose a novel Evaluation oriented KD method (EKD) for deep face recognition to directly reduce the performance gap between the teacher and student models during training. Specifically, we adopt the commonly used evaluation metrics in face recognition, i.e., False Positive Rate (FPR) and True Positive Rate (TPR) as the performance indicator. According to the evaluation protocol, the critical pair relations that cause the TPR and FPR difference between the teacher and student models are selected. Then, the critical relations in the student are constrained to approximate the corresponding ones in the teacher by a novel rank-based loss function, giving more flexibility to the student with low capacity. Extensive experimental results on popular benchmarks demonstrate the superiority of our EKD over state-of-the-art competitors.
-
Subgraph recognition aims at discovering a compressed substructure of a graph that is most informative to the graph property. It can be formulated by optimizing Graph Information Bottleneck (GIB) with a mutual information estimator. However, GIB suffers from training instability and degenerated results due to its intrinsic optimization process. To tackle these issues, we reformulate the subgraph recognition problem into two steps: graph perturbation and subgraph selection, leading to a novel Variational Graph Information Bottleneck (VGIB) framework. VGIB first employs the noise injection to modulate the information flow from the input graph to the perturbed graph. Then, the perturbed graph is encouraged to be informative to the graph property. VGIB further obtains the desired subgraph by filtering out the noise in the perturbed graph. With the customized noise prior for each input, the VGIB objective is endowed with a tractable variational upper bound, leading to a superior empirical performance as well as theoretical properties. Extensive experiments on graph interpretation, explainability of Graph Neural Networks, and graph classification show that VGIB finds better subgraphs than existing methods Extensive experiments on the explainability of Graph Neural Networks, graph interpretation, and graph classification show that VGIB finds better subgraphs than existing methods.
-
Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic solutions usually decompose the VPS task into several sub-tasks and utilize multiple surrogates (e.g. boxes and masks, centers and offsets) to represent objects. However, this divide-and-conquer strategy requires complex post-processing in both spatial and temporal domains and is vulnerable to failures from surrogate tasks. In this paper, inspired by object-centric learning which learns compact and robust object representations, we present Slot-VPS, the first end-to-end framework for this task. We encode all panoptic entities in a video, including both foreground instances and background semantics, in a unified representation called panoptic slots. The coherent spatio-temporal object's information is retrieved and encoded into the panoptic slots by the proposed Video Panoptic Retriever, enabling to localize, segment, differentiate, and associate objects in a unified manner. Finally, the output panoptic slots can be directly converted into the class, mask, and object ID of panoptic objects in the video. We conduct extensive ablation studies and demonstrate the effectiveness of our approach on two benchmark datasets, Cityscapes-VPS (val and test sets) and VIPER (val set), achieving new state-of-the-art performance of 63.7, 63.3 and 56.2 VPQ, respectively.
-
We propose a method for jointly estimating the 3D motion, 3D shape, and appearance of highly motion-blurred objects from a video. To this end, we model the blurred appearance of a fast moving object in a generative fashion by parametrizing its 3D position, rotation, velocity, acceleration, bounces, shape, and texture over the duration of a predefined time window spanning multiple frames. Using differentiable rendering, we are able to estimate all parameters by minimizing the pixel-wise reprojection error to the input video via backpropagating through a rendering pipeline that accounts for motion blur by averaging the graphics output over short time intervals. For that purpose, we also estimate the camera exposure gap time within the same optimization. To account for abrupt motion changes like bounces, we model the motion trajectory as a piece-wise polynomial, and we are able to estimate the specific time of the bounce at sub-frame accuracy. Experiments on established benchmark datasets demonstrate that our method outperforms previous methods for fast moving object deblurring and 3D reconstruction.
-
Video Instance Segmentation (VIS) aims to simultaneously classify, segment, and track multiple object instances in videos. Recent clip-level VIS takes a short video clip as input each time showing stronger performance than frame-level VIS (tracking-by-segmentation), as more temporal context from multiple frames is utilized. Yet, most clip-level methods are neither end-to-end learnable nor real-time. These limitations are addressed by the recent VIS transformer (VisTR) which performs VIS end-to-end within a clip. However, VisTR suffers from long training time due to its frame-wise dense attention. In addition, VisTR is not fully end-to-end learnable in multiple video clips as it requires a hand-crafted data association to link instance tracklets between successive clips. This paper proposes EfficientVIS, a fully end-to-end framework with efficient training and inference. At the core are tracklet query and tracklet proposal that associate and segment regions-of-interest (RoIs) across space and time by an iterative query-video interaction. We further propose a correspondence learning that makes tracklets linking between clips end-to-end learnable. Compared to VisTR, EfficientVIS requires 15x fewer training epochs while achieving state-of-the-art accuracy on the YouTube-VIS benchmark. Meanwhile, our method enables whole video instance segmentation in a single end-to-end pass without data association at all.
-
Accelerated by telemedicine, advances in Remote Photoplethysmography (rPPG) are beginning to offer a viable path toward non-contact physiological measurement. Unfortunately, the datasets for rPPG are limited as they require videos of the human face paired with ground-truth, synchronized heart rate data from a medical-grade health monitor. Also troubling is that the datasets are not inclusive of diverse populations, i.e., current real rPPG facial video datasets are imbalanced in terms of races or skin tones, leading to accuracy disparities on different demographic groups. This paper proposes a scalable biophysical learning based method to generate physio-realistic synthetic rPPG videos given any reference image and target rPPG signal and shows that it could further improve the state-of-the-art physiological measurement and reduce the bias among different groups. We also collect the largest rPPG dataset of its kind (UCLA-rPPG) with a diverse presence of subject skin tones, in the hope that this could serve as a benchmark dataset for different skin tones in this area and ensure that advances of the technique can benefit all people for healthcare equity. The dataset is available at https://visual.ee.ucla.edu/rppg_avatars.htm/.
-
TransRAC: Encoding Multi-Scale Temporal Correlation With Transformers for Repetitive Action Counting
Counting repetitive actions are widely seen in human activities such as physical exercise. Existing methods focus on performing repetitive action counting in short videos, which is tough for dealing with longer videos in more realistic scenarios. In the data-driven era, the degradation of such generalization capability is mainly attributed to the lack of long video datasets. To complement this margin, we introduce a new large-scale repetitive action counting dataset covering a wide variety of video lengths, along with more realistic situations where action interruption or action inconsistencies occur in the video. Besides, we also provide a fine-grained annotation of the action cycles instead of just counting annotation along with a numerical value. Such a dataset contains 1,451 videos with about 20,000 annotations, which is more challenging. For repetitive action counting towards more realistic scenarios, we further propose encoding multi-scale temporal correlation with transformers that can take into account both performance and efficiency. Furthermore, with the help of fine-grained annotation of action cycles, we propose a density map regression-based method to predict the action period, which yields better performance with sufficient interpretability. Our proposed method outperforms state-of-the-art methods on all datasets and also achieves better performance on the unseen dataset without fine-tuning. The dataset and code are available.
-
Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e., recovering a realistic NeRF at a different time of day from a group of tourism images. Existing solutions adopt NeRF with a controllable appearance embedding to render novel views under various conditions, but they cannot render view-consistent images with an unseen appearance. To solve this problem, we present an end-to-end framework for constructing a hallucinated NeRF, dubbed as Ha-NeRF. Specifically, we propose an appearance hallucination module to handle time-varying appearances and transfer them to novel views. Considering the complex occlusions of tourism images, we introduce an anti-occlusion module to decompose the static subjects for visibility accurately. Experimental results on synthetic data and real tourism photo collections demonstrate that our method can hallucinate the desired appearances and render occlusion-free images from different views. The project and supplementary materials are available at https://rover-xingyu.github.io/Ha-NeRF/.
-
Undoubtedly, high-fidelity 3D hair plays an indispensable role in digital humans. However, existing monocular hair modeling methods are either tricky to deploy in digital systems (e.g., due to their dependence on complex user interactions or large databases) or can produce only a coarse geometry. In this paper, we introduce NeuralHDHair, a flexible, fully automatic system for modeling high-fidelity hair from a single image. The key enablers of our system are two carefully designed neural networks: an IRHairNet (Implicit representation for hair using neural network) for inferring high-fidelity 3D hair geometric features (3D orientation field and 3D occupancy field) hierarchically and a GrowingNet (Growing hair strands using neural network) to efficiently generate 3D hair strands in parallel. Specifically, we perform a coarse-to-fine manner and propose a novel voxel-aligned implicit function (VIFu) to represent the global hair feature, which is further enhanced by the local details extracted from a hair luminance map. To improve the efficiency of a traditional hair growth algorithm, we adopt a local neural implicit function to grow strands based on the estimated 3D hair geometric features. Extensive experiments show that our method is capable of constructing a high-fidelity 3D hair model from a single image, both efficiently and effectively, and achieves the-state-of-the-art performance.
-
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e.g., generalization across distributions) is valued. Existing literature discussing this "hard-to-learn" concept are mainly expanded either along the dimension of the samples or the dimension of the features. In this paper, we aim to introduce a simple view merging these two dimensions, leading to a new, simple yet effective, heuristic to train machine learning models by emphasizing the worst-cases on both the sample and the feature dimensions. We name our method W2D following the concept of "Worst-case along Two Dimensions". We validate the idea and demonstrate its empirical strength over standard benchmarks.
-
We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all objects. The core component is a global tracking transformer that operates on objects from all frames in the sequence. The transformer encodes object features from all frames, and uses trajectory queries to group them into trajectories. The trajectory queries are object features from a single frame and naturally produce unique trajectories. Our global tracking transformer does not require intermediate pairwise grouping or combinatorial association, and can be jointly trained with an object detector. It achieves competitive performance on the popular MOT17 benchmark, with 75.3 MOTA and 59.1 HOTA. More importantly, our framework seamlessly integrates into state-of-the-art large-vocabulary detectors to track any objects. Experiments on the challenging TAO dataset show that our framework consistently improves upon baselines that are based on pairwise association, outperforming published work by a significant 7.7 tracking mAP. Code is available at https://github.com/xingyizhou/GTR.
-
Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use an inductive bias that random augmentations (e.g., random crops) of an image should produce similar embeddings. We show that such methods are vulnerable to backdoor attacks -- where an attacker poisons a small part of the unlabeled data by adding a trigger (image patch chosen by the attacker) to the images. The model performance is good on clean test images, but the attacker can manipulate the decision of the model by showing the trigger at test time. Backdoor attacks have been studied extensively in supervised learning and to the best of our knowledge, we are the first to study them for self-supervised learning. Backdoor attacks are more practical in self-supervised learning, since the use of large unlabeled data makes data inspection to remove poisons prohibitive. We show that in our targeted attack, the attacker can produce many false positives for the target category by using the trigger at test time. We also propose a defense method based on knowledge distillation that succeeds in neutralizing the attack. Our code is available here: https://github.com/UMBCvision/SSL-Backdoor
-
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers could improve the performance, yet the inner-modal attentive weights may be diluted, which could thus greatly undermine the final performance. In this paper, we propose a multimodal token fusion method (TokenFusion), tailored for transformer-based vision tasks. To effectively fuse multiple modalities, TokenFusion dynamically detects uninformative tokens and substitute these tokens with projected and aggregated inter-modal features. Residual positional alignment is also adopted to enable explicit utilization of the inter-modal alignments after fusion. The design of TokenFusion allows the transformer to learn correlations among multimodal features, while the single-modal transformer architecture remains largely intact. Extensive experiments are conducted on a variety of homogeneous and heterogeneous modalities and demonstrate that TokenFusion surpasses state-of-the-art methods in three typical vision tasks: multimodal image-to-image translation, RGB-depth semantic segmentation, and 3D object detection with point cloud and images.
-
Various facial manipulation techniques have drawn serious public concerns in morality, security, and privacy. Although existing face forgery classifiers achieve promising performance on detecting fake images, these methods are vulnerable to adversarial examples with injected imperceptible perturbations on the pixels. Meanwhile, many face forgery detectors always utilize the frequency diversity between real and fake faces as a crucial clue. In this paper, instead of injecting adversarial perturbations into the spatial domain, we propose a frequency adversarial attack method against face forgery detectors. Concretely, we apply discrete cosine transform (DCT) on the input images and introduce a fusion module to capture the salient region of adversary in the frequency domain. Compared with existing adversarial attacks (e.g. FGSM, PGD) in the spatial domain, our method is more imperceptible to human observers and does not degrade the visual quality of the original images. Moreover, inspired by the idea of meta-learning, we also propose a hybrid adversarial attack that performs attacks in both the spatial and frequency domains. Extensive experiments indicate that the proposed method fools not only the spatial-based detectors but also the state-of-the-art frequency-based detectors effectively. In addition, the proposed frequency attack enhances the transferability across face forgery detectors as black-box attacks.
-
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements. To alleviate this, the state-of-the-art framework RAFT gradually improves its prediction quality by using a large number of iterative refinements, achieving remarkable performance but introducing linearly increasing inference time. To enable both high accuracy and efficiency, we completely revamp the dominant flow regression pipeline by reformulating optical flow as a global matching problem, which identifies the correspondences by directly comparing feature similarities. Specifically, we propose a GMFlow framework, which consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. We further introduce a refinement step that reuses GMFlow at higher feature resolution for residual flow prediction. Our new framework outperforms 31-refinements RAFT on the challenging Sintel benchmark, while using only one refinement and running faster, suggesting a new paradigm for accurate and efficient optical flow estimation. Code is available at https://github.com/haofeixu/gmflow.
-
Generating speech-consistent body and gesture movements is a long-standing problem in virtual avatar creation. Previous studies often synthesize pose movement in a holistic manner, where poses of all joints are generated simultaneously. Such a straightforward pipeline fails to generate fine-grained co-speech gestures. One observation is that the hierarchical semantics in speech and the hierarchical structures of human gestures can be naturally described into multiple granularities and associated together. To fully utilize the rich connections between speech audio and human gestures, we propose a novel framework named Hierarchical Audio-to-Gesture (HA2G) for co-speech gesture generation. In HA2G, a Hierarchical Audio Learner extracts audio representations across semantic granularities. A Hierarchical Pose Inferer subsequently renders the entire human pose gradually in a hierarchical manner. To enhance the quality of synthesized gestures, we develop a contrastive learning strategy based on audio-text alignment for better audio representations. Extensive experiments and human evaluation demonstrate that the proposed method renders realistic co-speech gestures and outperforms previous methods in a clear margin. Project page: https://alvinliu0.github.io/projects/HA2G.
-
State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a "foundation", that targets all modalities at once---a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision and language tasks. We introduce FLAVA as such a model and demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities.
-
Sign languages are visual languages, with vocabularies as rich as their spoken language counterparts. However, current deep-learning based Sign Language Production (SLP) models produce under-articulated skeleton pose sequences from constrained vocabularies and this limits applicability. To be understandable and accepted by the deaf, an automatic SLP system must be able to generate co-articulated photo-realistic signing sequences for large domains of discourse. In this work, we tackle large-scale SLP by learning to co-articulate between dictionary signs, a method capable of producing smooth signing while scaling to unconstrained domains of discourse. To learn sign co-articulation, we propose a novel Frame Selection Network (FS-Net) that improves the temporal alignment of interpolated dictionary signs to continuous signing sequences. Additionally, we propose SignGAN, a pose-conditioned human synthesis model that produces photo-realistic sign language videos direct from skeleton pose. We propose a novel keypoint-based loss function which improves the quality of synthesized hand images. We evaluate our SLP model on the large-scale meineDGS (mDGS) corpus, conducting extensive user evaluation showing our FS-Net approach improves co-articulation of interpolated dictionary signs. Additionally, we show that SignGAN significantly outperforms all baseline methods for quantitative metrics, human perceptual studies and native deaf signer comprehension.
-
We endeavor on a rarely explored task named Insubstan-tial Object Detection (IOD), which aims to localize the object with following characteristics: (1) amorphous shape with indistinct boundary; (2) similarity to surroundings; (3) absence in color. Accordingly, it is far more challenging to distinguish insubstantial objects in a single static frame and the collaborative representation of spatial and tempo-ral information is crucial. Thus, we construct an IOD-Video dataset comprised of 600 videos (141,017 frames) covering various distances, sizes, visibility, and scenes captured by different spectral ranges. In addition, we develop a spatio-temporal aggregation framework for IOD, in which differ-ent backbones are deployed and a spatio-temporal aggregation loss (STAloss) is elaborately designed to leverage the consistency along the time axis. Experiments conducted on IOD-Video dataset demonstrate that spatio-temporal aggregation can significantly improve the performance of IOD. We hope our work will attract further researches into this valuable yet challenging task. The code will be available at: https://github.com/CalayZhou/IOD-Video.
-
Videos incorporate rich semantics as well as redundant information. Seeking a compact yet effective video representation, e.g., sample informative frames from the entire video, is critical to efficient video recognition. There have been works that formulate frame sampling as a sequential decision task by selecting frames one by one according to their importance. In this paper, we present a more efficient framework named OCSampler, which explores such a representation with one short clip. OCSampler designs a new paradigm of learning instance-specific video condensation policies to select frames only in a single step. Rather than picking up frames sequentially like previous methods, we simply process a whole sequence at once. Accordingly, these policies are derived from a light-weighted skim network together with a simple yet effective policy network. Moreover, we extend the proposed method with a frame number budget, enabling the framework to produce correct predictions in high confidence with as few frames as possible. Experiments on various benchmarks demonstrate the effectiveness of OCSampler over previous methods in terms of accuracy and efficiency. Specifically, it achieves 76.9% mAP and 21.7 GFLOPs on ActivityNet with an impressive throughput: 123.9 Video/s on a single TITAN Xp GPU.
-
Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. Despite their performance, they still suffer from interference across tasks which leads to catastrophic forgetting. To ameliorate this problem, we propose to only activate and select sparse neurons for learning current and past tasks at any stage. More parameters space and model capacity can thus be reserved for the future tasks. This minimizes the interference between parameters for different tasks. To do so, we propose a Sparse neural Network for Continual Learning (SNCL), which employs variational Bayesian sparsity priors on the activations of the neurons in all layers. Full Experience Replay (FER) provides effective supervision in learning the sparse activations of the neurons in different layers. A loss-aware reservoir-sampling strategy is developed to maintain the memory buffer. The proposed method is agnostic as to the network structures and the task boundaries. Experiments on different datasets show that SNCL achieves state-of-the-art result for mitigating forgetting.
-
Graph-Based Spatial Transformer With Memory Replay for Multi-Future Pedestrian Trajectory Prediction
Pedestrian trajectory prediction is an essential and challenging task for a variety of real-life applications such as autonomous driving and robotic motion planning. Besides generating a single future path, predicting multiple plausible future paths is becoming popular in some recent work on trajectory prediction. However, existing methods typically emphasize spatial interactions between pedestrians and surrounding areas but ignore the smoothness and temporal consistency of predictions. Our model aims to forecast multiple paths based on a historical trajectory by modeling multi-scale graph-based spatial transformers combined with a trajectory smoothing algorithm named "Memory Replay" utilizing a memory graph. Our method can comprehensively exploit the spatial information as well as correct the temporally inconsistent trajectories (e.g., sharp turns). We also propose a new evaluation metric named "Percentage of Trajectory Usage" to evaluate the comprehensiveness of diverse multi-future predictions. Our extensive experiments show that the proposed model achieves state-of-the-art performance on multi-future prediction and competitive results for single-future prediction. Code released at https://github.com/Jacobieee/ST-MR.
-
Cameras on portable devices are manufactured with a rolling-shutter (RS) mechanism, where the image rows (aka. scanlines) are read out sequentially. The unknown camera motions during the imaging process cause the so-called RS effects which are solved by motion assumptions in the literature. In this work, we give a solution to the absolute pose problem free of motion assumptions. We categorically demonstrate that the only requirement is motion smoothness instead of stronger constraints on the camera motion. To this end, we propose a novel mathematical abstraction for RS cameras observing a planar scene, called the scanline-homography, a 3x2 matrix with 5 DOFs. We establish the relationship between a scanline-homography and the corresponding plane-homography, a 3x3 matrix with 6 DOFs assuming the camera is calibrated. We estimate the scanline-homographies of an RS frame using a smooth image warp powered by B-Splines, and recover the plane-homographies afterwards to obtain the scanline-poses based on motion smoothness. We back our claims with various experiments. Code and new datasets: https://bitbucket.org/clermontferrand/planarscanlinehomography/src/master/.
-
Tables organize valuable content in a concise and compact representation. This content is extremely valuable for systems such as search engines, Knowledge Graph's, etc, since they enhance their predictive capabilities. Unfortunately, tables come in a large variety of shapes and sizes. Furthermore, they can have complex column/row-header configurations, multiline rows, different variety of separation lines, missing entries, etc. As such, the correct identification of the table-structure from an image is a non-trivial task. In this paper, we present a new table-structure identification model. The latter improves the latest end-to-end deep learning model (i.e. encoder-dual-decoder from PubTabNet) in two significant ways. First, we introduce a new object detection decoder for table-cells. In this way, we can obtain the content of the table-cells from programmatic PDF's directly from the PDF source and avoid the training of the custom OCR decoders. This architectural change leads to more accurate table-content extraction and allows us to tackle non-english tables. Second, we replace the LSTM decoders with transformer based decoders. This upgrade improves significantly the previous state-of-the-art tree-editing-distance-score (TEDS) from 91% to 98.5% on simple tables and from 88.7% to 95% on complex tables.
-
Synthesis of ergodic, stationary visual patterns is widely applicable in texturing, shape modeling, and digital content creation. The wide applicability of this technique thus requires the pattern synthesis approaches to be scalable, diverse, and authentic. In this paper, we propose an exemplar-based visual pattern synthesis framework that aims to model the inner statistics of visual patterns and generate new, versatile patterns that meet the aforementioned requirements. To this end, we propose an implicit network based on generative adversarial network (GAN) and periodic encoding, thus calling our network the Implicit Periodic Field Network (IPFN). The design of IPFN ensures scalability: the implicit formulation directly maps the input coordinates to features, which enables synthesis of arbitrary size and is computationally efficient for 3D shape synthesis. Learning with a periodic encoding scheme encourages diversity: the network is constrained to model the inner statistics of the exemplar based on spatial latent codes in a periodic field. Coupled with continuously designed GAN training procedures, IPFN is shown to synthesize tileable patterns with smooth transitions and local variations. Last but not least, thanks to both the adversarial training technique and the encoded Fourier features, IPFN learns high-frequency functions that produce authentic, high-quality results. To validate our approach, we present novel experimental results on various applications in 2D texture synthesis and 3D shape synthesis.
-
This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representations semantic-rich. In our experiments, we pre-train GLIP on 27M grounding data, including 3M human-annotated and 24M web-crawled image-text pairs. The learned representations demonstrate strong zero-shot and few-shot transferability to various object-level recognition tasks. 1) When directly evaluated on COCO and LVIS (without seeing any images in COCO during pre-training), GLIP achieves 49.8 AP and 26.9 AP, respectively, surpassing many supervised baselines. 2) After fine-tuned on COCO, GLIP achieves 60.8 AP on val and 61.5 AP on test-dev, surpassing prior SoTA. 3) When transferred to 13 downstream object detection tasks, a 1-shot GLIP rivals with a fully-supervised Dynamic Head.
-
Though unsupervised domain adaptation (UDA) has achieved very impressive progress recently, it remains a great challenge due to missing target annotations and the rich discrepancy between source and target distributions. We propose Spectral UDA (SUDA), an effective and efficient UDA technique that works in the spectral space and can generalize across different visual recognition tasks. SUDA addresses the UDA challenges from two perspectives. First, it introduces a spectrum transformer (ST) that mitigates inter-domain discrepancies by enhancing domain-invariant spectra while suppressing domain-variant spectra of source and target samples simultaneously. Second, it introduces multi-view spectral learning that learns useful unsupervised representations by maximizing mutual information among multiple ST-generated spectral views of each target sample. Extensive experiments show that SUDA achieves superior accuracy consistently across different visual tasks in image classification, semantic segmentation, and object detection. Additionally, SUDA also works with the transformer-based network and achieves state-of-the-art performance on object detection.
-
The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time image enhancement tasks, which models a non-linear 3D color transform by sparsely sampling it into a discretized 3D lattice. Previous works have made efforts to learn image-adaptive output color values of LUTs for flexible enhancement but neglect the importance of sampling strategy. They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform. Focusing on this problem, we present AdaInt (Adaptive Intervals Learning), a novel mechanism to achieve a more flexible sampling point allocation by adaptively learning the non-uniform sampling intervals in the 3D color space. In this way, a 3D LUT can increase its capability by conducting dense sampling in color ranges requiring highly non-linear transforms and sparse sampling for near-linear transforms. The proposed AdaInt could be implemented as a compact and efficient plug-and-play module for a 3D LUT-based method. To enable the end-to-end learning of AdaInt, we design a novel differentiable operator called AiLUT-Transform (Adaptive Interval LUT Transform) to locate input colors in the non-uniform 3D LUT and provide gradients to the sampling intervals. Experiments demonstrate that methods equipped with AdaInt can achieve state-of-the-art performance on two public benchmark datasets with a negligible overhead increase. Our source code is available at https://github.com/ImCharlesY/AdaInt.
-
The point cloud learning community is witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are computationally expensive since they need to generate a large attention map, which has quadratic complexity (both in space and time) with respect to input size. To solve this shortcoming, we introduce patch-attention (PAT) to adaptively learn a much smaller set of bases upon which the attention maps are computed. By a weighted summation upon these bases, PAT not only captures the global shape context but also achieves linear complexity to input size. In addition, we propose a lightweight Multi-Scale Attention (MST) block to build attentions among features of different scales, providing the model with multi-scale features. Equipped with the PAT and MST, we construct our neural architecture called PatchFormer that integrates both modules into a joint framework for point cloud learning. Extensive experiments demonstrate that our network achieves comparable accuracy on general point cloud learning tasks with 9.2x speed-up than previous point Transformers.
-
Although detection with Transformer (DETR) is increasingly popular, its global attention modeling requires an extremely long training period to optimize and achieve promising detection performance. Alternative to existing studies that mainly develop advanced feature or embedding designs to tackle the training issue, we point out that the Region-of-Interest (RoI) based detection refinement can easily help mitigate the difficulty of training for DETR methods. Based on this, we introduce a novel REcurrent Glimpse-based decOder (REGO) in this paper. In particular, the REGO employs a multi-stage recurrent processing structure to help the attention of DETR gradually focus on foreground objects more accurately. In each processing stage, visual features are extracted as glimpse features from RoIs with enlarged bounding box areas of detection results from the previous stage. Then, a glimpse-based decoder is introduced to provide refined detection results based on both the glimpse features and the attention modeling outputs of the previous stage. In practice, REGO can be easily embedded in representative DETR variants while maintaining their fully end-to-end training and inference pipelines. In particular, REGO helps Deformable DETR achieve 44.8 AP on the MSCOCO dataset with only 36 training epochs, compared with the first DETR and the Deformable DETR that require 500 and 50 epochs to achieve comparable performance, respectively. Experiments also show that REGO consistently boosts the performance of different DETR detectors by up to 7% relative gain at the same setting of 50 training epochs. Code is available via https://github.com/zhechen/Deformable-DETR-REGO.
-
We introduce AiD Regen, a novel system that generates 3D wound models combining 2D semantic segmentation with 3D reconstruction so that they can be printed via 3D bio-printers during the surgery to treat diabetic foot ulcers (DFUs). AiD Regen seamlessly binds the full pipeline, which includes RGB-D image capturing, semantic segmentation, boundary-guided point-cloud processing, 3D model reconstruction, and 3D printable G-code generation, into a single system that can be used out of the box. We developed a multi-stage data preprocessing method to handle small and unbalanced DFU image datasets. AiD Regen's human-in-the-loop machine learning interface enables clinicians to not only create 3D regenerative patches with just a few touch interactions but also customize and confirm wound boundaries. As evidenced by our experiments, our model outperforms prior wound segmentation models and our reconstruction algorithm is capable of generating 3D wound models with compelling accuracy. We further conducted a case study on a real DFU patient and demonstrated the effectiveness of AiD Regen in treating DFU wounds.
-
This paper presents SimMIM, a simple framework for masked image modeling. We have simplified recently proposed relevant approaches, without the need for special designs, such as block-wise masking and tokenization via discrete VAE or clustering. To investigate what makes a masked image modeling task learn good representations, we systematically study the major components in our framework, and find that the simple designs of each component have revealed very strong representation learning performance: 1) random masking of the input image with a moderately large masked patch size (e.g., 32) makes a powerful pre-text task; 2) predicting RGB values of raw pixels by direct regression performs no worse than the patch classification approaches with complex designs; 3) the prediction head can be as light as a linear layer, with no worse performance than heavier ones. Using ViT-B, our approach achieves 83.8% top-1 fine-tuning accuracy on ImageNet-1K by pre-training also on this dataset, surpassing previous best approach by +0.6%. When applied to a larger model with about 650 million parameters, SwinV2-H, it achieves 87.1% top-1 accuracy on ImageNet-1K using only ImageNet-1K data. We also leverage this approach to address the data-hungry issue faced by large-scale model training, that a 3B model (SwinV2-G) is successfully trained to achieve state-of-the-art accuracy on four representative vision benchmarks using 40x less labeled data than that in previous practice (JFT-3B). The code is available at https://github.com/microsoft/SimMIM.
-
A well-known challenge in applying deep-learning methods to omnidirectional images is spherical distortion. In dense regression tasks such as depth estimation, where structural details are required, using a vanilla CNN layer on the distorted 360 image results in undesired information loss. In this paper, we propose a 360 monocular depth estimation pipeline, OmniFusion, to tackle the spherical distortion issue. Our pipeline transforms a 360 image into less-distorted perspective patches (i.e. tangent images) to obtain patch-wise predictions via CNN, and then merge the patch-wise results for final output. To handle the discrepancy between patch-wise predictions which is a major issue affecting the merging quality, we propose a new framework with the following key components. First, we propose a geometry-aware feature fusion mechanism that combines 3D geometric features with 2D image features to compensate for the patch-wise discrepancy. Second, we employ the self-attention-based transformer architecture to conduct a global aggregation of patch-wise information, which further improves the consistency. Last, we introduce an iterative depth refinement mechanism, to further refine the estimated depth based on the more accurate geometric features. Experiments show that our method greatly mitigates the distortion issue, and achieves state-of-the-art performances on several 360 monocular depth estimation benchmark datasets.
-
Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to severe confirmation bias during self-training. In this paper, we delve into this problem and propose a simple yet effective LabelMatch framework from two different yet complementary perspectives, i.e., distribution-level and instance-level. For the former one, it is reasonable to approximate the class distribution of the unlabeled data from that of the labeled data according to Monte Carlo Sampling. Guided by this weakly supervision cue, we introduce a re-distribution mean teacher, which leverages adaptive label-distribution-aware confidence thresholds to generate unbiased pseudo labels to drive student learning. For the latter one, there exists an overlooked label assignment ambiguity problem across teacher-student models. To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly. Experiments on both MS-COCO and PASCAL-VOC datasets demonstrate the considerable superiority of our proposed framework to other state-of-the-arts. Code will be available at https://github.com/HIK-LAB/SSOD.
-
Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to unsatisfactory performance due to a major domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans. To mitigate this issue, we propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visual representations, thus enabling fine-grained alignment between image regions and textual concepts. Our method leverages a CLIP model to match image regions with template captions, and then pretrains our model to align these region-text pairs in the feature space. When transferring our pretrained model to the open-vocabulary object detection task, our method outperforms the state of the art by 3.8 AP50 and 2.2 AP for novel categories on COCO and LVIS datasets, respectively. Further, the learned region representations support zero-shot inference for object detection, showing promising results on both COCO and LVIS datasets. Our code is available at https://github.com/microsoft/RegionCLIP.
-
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we propose a Transformer-based video interpolation framework that allows content-aware aggregation weights and considers long-range dependencies with the self-attention operations. To avoid the high computational cost of global self-attention, we introduce the concept of local attention into video interpolation and extend it to the spatial-temporal domain. Furthermore, we propose a space-time separation strategy to save memory usage, which also improves performance. In addition, we develop a multi-scale frame synthesis scheme to fully realize the potential of Transformers. Extensive experiments demonstrate the proposed model performs favorably against the state-of-the-art methods both quantitatively and qualitatively on a variety of benchmark datasets. The code and models are released at https://github.com/zhshi0816/ Video-Frame-Interpolation-Transformer.
-
We address weakly supervised point cloud segmentation by proposing a new model, MIL-derived transformer, to mine additional supervisory signals. First, the transformer model is derived based on multiple instance learning (MIL) to explore pair-wise cloud-level supervision, where two clouds of the same category yield a positive bag while two of different classes produce a negative bag. It leverages not only individual cloud annotations but also pair-wise cloud semantics for model optimization. Second, Adaptive global weighted pooling (AdaGWP) is integrated into our transformer model to replace max pooling and average pooling. It introduces learnable weights to re-scale logits in the class activation maps. It is more robust to noise while discovering more complete foreground points under weak supervision. Third, we perform point subsampling and enforce feature equivariance between the original and subsampled point clouds for regularization. The proposed method is end-to-end trainable and is general because it can work with different backbones with diverse types of weak supervision signals, including sparsely annotated points and cloud-level labels. The experiments show that it achieves state-of-the-art performance on the S3DIS and ScanNet benchmarks.
-
We introduce the first end-to-end learning-based solution to near-field Photometric Stereo (PS), where the light sources are close to the object of interest. This setup is especially useful for reconstructing large immobile objects. Our method is fast, producing a mesh from 52 512x384 resolution images in about 1 second on a commodity GPU, thus potentially unlocking several AR/VR applications. Existing approaches rely on optimization coupled with a far-field PS network operating on pixels or small patches. Using optimization makes these approaches slow and memory intensive (requiring 17GB GPU and 27GB of CPU memory) while using only pixels or patches makes them highly susceptible to noise and calibration errors. To address these issues, we develop a recursive multi-resolution scheme to estimate surface normal and depth maps of the whole image at each step. The predicted depth map at each scale is then used to estimate 'per-pixel lighting' for the next scale. This design makes our approach almost 45x faster and 2 degrees more accurate (11.3 vs. 13.3 degrees Mean Angular Error) than the state-of-the-art near-field PS reconstruction technique, which uses iterative optimization.
-
Template-based 3D object tracking still lacks a high-precision benchmark of real scenes due to the difficulty of annotating the accurate 3D poses of real moving video objects without using markers. In this paper, we present a multi-view approach to estimate the accurate 3D poses of real moving objects, and then use binocular data to construct a new benchmark for monocular textureless 3D object tracking. The proposed method requires no markers, and the cameras only need to be synchronous, relatively fixed as cross-view and calibrated. Based on our object-centered model, we jointly optimize the object pose by minimizing shape re-projection constraints in all views, which greatly improves the accuracy compared with the single-view approach, and is even more accurate than the depth-based method. Our new benchmark dataset contains 20 textureless objects, 22 scenes, 404 video sequences and 126K images captured in real scenes. The annotation error is guaranteed to be less than 2mm, according to both theoretical analysis and validation experiments. We re-evaluate the state-of-the-art 3D object tracking methods with our dataset, reporting their performance ranking in real scenes. Our BCOT benchmark and code can be found at https://ar3dv.github.io/BCOT-Benchmark/.
-
We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for object detection. This is enabled by a unified architecture, Omni-DETR, based on the recent progress on student-teacher framework and end-to-end transformer based object detection. Under this unified architecture, different types of weak labels can be leveraged to generate accurate pseudo labels, by a bipartite matching based filtering mechanism, for the model to learn. In the experiments, Omni-DETR has achieved state-of-the-art results on multiple datasets and settings. And we have found that weak annotations can help to improve detection performance and a mixture of them can achieve a better trade-off between annotation cost and accuracy than the standard complete annotation. These findings could encourage larger object detection datasets with mixture annotations. The code is available at https://github.com/amazon-research/omni-detr.
-
Omnidirectional cameras have been used widely to better understand surrounding environments. They are often configured as stereo to estimate depth. However, due to the optics of the fisheye lens, conventional epipolar geometry is inapplicable directly to omnidirectional camera images. Intermediate formats of omnidirectional images, such as equirectangular images, have been used. However, stereo matching performance on these image formats has been lower than the conventional stereo due to severe image distortion near pole regions. In this paper, to address the distortion problem of omnidirectional images, we devise a novel subdivision scheme of a spherical geodesic grid. This enables more isotropic patch sampling of spherical image information in the omnidirectional camera space. Our spherical geodesic grid is tessellated with an equal-arc subdivision, making the cell sizes and in-between distances as uniform as possible, i.e., the arc length of the spherical grid cell's edges is well regularized. Also, our uniformly tessellated coordinates in a 2D image can be transformed into spherical coordinates via one-to-one mapping, allowing for analytical forward/backward transformation. Our uniform tessellation scheme achieves a higher accuracy of stereo matching than the traditional cylindrical and cubemap-based approaches, reducing the memory footage required for stereo matching by 20 %.
-
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve new state of the art scores for image inpainting and class-conditional image synthesis and highly competitive performance on various tasks, including unconditional image generation, text-to-image synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.
-
Few-Shot Image Classification (FSIC) aims to recognize novel image classes with limited data, which is significant in practice. In this paper, we consider the FSIC problem in the case of adversarial examples. This is an extremely challenging issue because current deep learning methods are still vulnerable when handling adversarial examples, even with massive labeled training samples. For this problem, existing works focus on training a network in the meta-learning fashion that depends on numerous sampled few-shot tasks. In comparison, we propose a simple but effective baseline through directly learning generalizable representations without tedious task sampling, which is robust to unforeseen adversarial FSIC tasks. Specifically, we introduce an adversarial-aware mechanism to establish auxiliary supervision via feature-level differences between legitimate and adversarial examples. Furthermore, we design a novel adversarial-reweighted training manner to alleviate the imbalance among adversarial examples. The feature purifier is also employed as post-processing for adversarial features. Moreover, our method can obtain generalizable representations to remain superior transferability, even facing cross-domain adversarial examples. Extensive experiments show that our method can significantly outperform state-of-the-art adversarially robust FSIC methods on two standard benchmarks.
-
Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus on the most discriminative parts of an object (i.e., incomplete localization problem). In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background. To address it, we propose Class RE-Activation Mapping (CREAM), a novel clustering-based approach to boost the activation values of the integral object regions. To this end, we introduce class-specific foreground and background context embeddings as cluster centroids. A CAM-guided momentum preservation strategy is developed to learn the context embeddings during training. At the inference stage, the re-activation mapping is formulated as a parameter estimation problem under Gaussian Mixture Model, which can be solved by deriving an unsupervised Expectation-Maximization based soft-clustering algorithm. By simply integrating CREAM into various WSOL approaches, our method significantly improves their performance. CREAM achieves the state-of-the-art performance on CUB, ILSVRC and OpenImages benchmark datasets. Code is available at https://github.com/JLRepo/CREAM.
-
We address the problem of action segmentation in instructional task videos with a small number of weakly-labeled training videos and a large number of unlabeled videos, which we refer to as Semi-Weakly-Supervised Learning (SWSL) of actions. We propose a general SWSL framework that can efficiently learn from both types of videos and can leverage any of the existing weakly-supervised action segmentation methods. Our key observation is that the distance between the transcript of an unlabeled video and those of the weakly-labeled videos from the same task is small yet often nonzero. Therefore, we develop a Soft Restricted Edit (SRE) loss to encourage small variations between the predicted transcripts of unlabeled videos and ground-truth transcripts of the weakly-labeled videos of the same task. To compute the SRE loss, we develop a flexible transcript prediction (FTP) method that uses the output of the action classifier to find both the length of the transcript and the sequence of actions occurring in an unlabeled video. We propose an efficient learning scheme in which we alternate between minimizing our proposed loss and generating pseudo-transcripts for unlabeled videos. By experiments on two benchmark datasets, we demonstrate that our approach can significantly improve the performance by using unlabeled videos, especially when the number of weakly-labeled videos is small.
-
Federated learning frameworks typically require collaborators to share their local gradient updates of a common model instead of sharing training data to preserve privacy. However, prior works on Gradient Leakage Attacks showed that private training data can be revealed from gradients. So far almost all relevant works base their attacks on fully-connected or convolutional neural networks. Given the recent overwhelmingly rising trend of adapting Transformers to solve multifarious vision tasks, it is highly important to investigate the privacy risk of vision transformers. In this paper, we analyse the gradient leakage risk of self-attention based mechanism in both theoretical and practical manners. Particularly, we propose APRIL - Attention PRIvacy Leakage, which poses a strong threat to self-attention inspired models such as ViT. Showing how vision Transformers are at the risk of privacy leakage via gradients, we urge the significance of designing privacy-safer Transformer models and defending schemes.
-
In this paper, we present TExt Spotting TRansformers (TESTR), a generic end-to-end text spotting framework using Transformers for text detection and recognition in the wild. TESTR builds upon a single encoder and dual decoders for the joint text-box control point regression and character recognition. Other than most existing literature, our method is free from Region-of-Interest operations and heuristics-driven post-processing procedures; TESTR is particularly effective when dealing with curved text-boxes where special cares are needed for the adaptation of the traditional bounding-box representations. We show our canonical representation of control points suitable for text instances in both Bezier curve and polygon annotations. In addition, we design a bounding-box guided polygon detection (box-to-polygon) process. Experiments on curved and arbitrarily shaped datasets demonstrate state-of-the-art performances of the proposed TESTR algorithm.
-
Though neural radiance fields ("NeRF") have demonstrated impressive view synthesis results on objects and small bounded regions of space, they struggle on "unbounded" scenes, where the camera may point in any direction and content may exist at any distance. In this setting, existing NeRF-like models often produce blurry or low-resolution renderings (due to the unbalanced detail and scale of nearby and distant objects), are slow to train, and may exhibit artifacts due to the inherent ambiguity of the task of reconstructing a large scene from a small set of images. We present an extension of mip-NeRF (a NeRF variant that addresses sampling and aliasing) that uses a non-linear scene parameterization, online distillation, and a novel distortion-based regularizer to overcome the challenges presented by unbounded scenes. Our model, which we dub "mip-NeRF 360" as we target scenes in which the camera rotates 360 degrees around a point, reduces mean-squared error by 57% compared to mip-NeRF, and is able to produce realistic synthesized views and detailed depth maps for highly intricate, unbounded real-world scenes.
-
Designing better machine translation systems by considering auxiliary inputs such as images has attracted much attention in recent years. While existing methods show promising performance over the conventional text-only translation systems, they typically require paired text and image as input during inference, which limits their applicability to real-world scenarios. In this paper, we introduce a visual hallucination framework, called VALHALLA, which requires only source sentences at inference time and instead uses hallucinated visual representations for multimodal machine translation. In particular, given a source sentence an autoregressive hallucination transformer is used to predict a discrete visual representation from the input text, and the combined text and hallucinated representations are utilized to obtain the target translation. We train the hallucination transformer jointly with the translation transformer using standard backpropagation with cross-entropy losses while being guided by an additional loss that encourages consistency between predictions using either ground-truth or hallucinated visual representations. Extensive experiments on three standard translation datasets with a diverse set of language pairs demonstrate the effectiveness of our approach over both text-only baselines and state-of-the-art methods. Our codes and models will be publicly available. Project page: http://www.svcl.ucsd.edu/projects/valhalla.
-
We introduce a high resolution, 3D-consistent image and shape generation technique which we call StyleSDF. Our method is trained on single view RGB data only, and stands on the shoulders of StyleGAN2 for image generation, while solving two main challenges in 3D-aware GANs: 1) high-resolution, view-consistent generation of the RGB images, and 2) detailed 3D shape. We achieve this by merging an SDF-based 3D representation with a style-based 2D generator. Our 3D implicit network renders low-resolution feature maps, from which the style-based network generates view-consistent, 1024x1024 images. Notably, our SDF-based 3D modeling defines detailed 3D surfaces, leading to consistent volume rendering. Our method shows higher quality results compared to state of the art in terms of visual and geometric quality.
-
Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency between labeled and unlabeled data, outliers may occur in unlabeled data, further increasing the training difficulty. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers. Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i.e., outliers) from unlabeled data. Semi-supervised learning (SSL) is further deployed to exploit positive unlabeled data by dynamically generating pseudo-MOS. We adopt a dual-branch network including reference and distortion branches. Furthermore, spatial attention is introduced in the reference branch to concentrate more on the informative regions, and sliced Wasserstein distance is used for robust difference map computation to address the misalignment issues caused by images recovered by GAN models. Extensive experiments show that our method performs favorably against state-of-the-arts on the benchmark datasets PIPAL, KADID-10k, TID2013, LIVE and CSIQ.
-
We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions and tracks human bodies even when they go outside the camera's field of view. To achieve this, we first propose a deep generative motion infiller, which autoregressively infills the body motions of occluded humans based on visible motions. Additionally, in contrast to prior work, our approach reconstructs human meshes in consistent global coordinates even with dynamic cameras. Since the joint reconstruction of human motions and camera poses is underconstrained, we propose a global trajectory predictor that generates global human trajectories based on local body movements. Using the predicted trajectories as anchors, we present a global optimization framework that refines the predicted trajectories and optimizes the camera poses to match the video evidence such as 2D keypoints. Experiments on challenging indoor and in-the-wild datasets with dynamic cameras demonstrate that the proposed approach outperforms prior methods significantly in terms of motion infilling and global mesh recovery.
-
To interpret deep networks, one main approach is to associate neurons with human-understandable concepts. However, existing methods often ignore the inherent connections of different concepts (e.g., dog and cat both belong to animals), and thus lose the chance to explain neurons responsible for higher-level concepts (e.g., animal). In this paper, we study hierarchical concepts inspired by the hierarchical cognition process of human beings. To this end, we propose HIerarchical Neuron concepT explainer (HINT) to effectively build bidirectional associations between neurons and hierarchical concepts in a low-cost and scalable manner. HINT enables us to systematically and quantitatively study whether and how the implicit hierarchical relationships of concepts are embedded into neurons. Specifically, HINT identifies collaborative neurons responsible for one concept and multimodal neurons pertinent to different concepts, at different semantic levels from concrete concepts (e.g., dog) to more abstract ones (e.g., animal). Finally, we verify the faithfulness of the associations using Weakly Supervised Object Localization, and demonstrate its applicability in various tasks, such as discovering saliency regions and explaining adversarial attacks. Code is available on https://github.com/AntonotnaWang/HINT.
-
Inferring human-scene contact (HSC) is the first step toward understanding how humans interact with their surroundings. While detecting 2D human-object interaction (HOI) and reconstructing 3D human pose and shape (HPS) have enjoyed significant progress, reasoning about 3D human-scene contact from a single image is still challenging. Existing HSC detection methods consider only a few types of predefined contact, often reduce body and scene to a small number of primitives, and even overlook image evidence. To predict human-scene contact from a single image, we address the limitations above from both data and algorithmic perspectives. We capture a new dataset called RICH for "Real scenes, Interaction, Contact and Humans." RICH contains multiview outdoor/indoor video sequences at 4K resolution, ground-truth 3D human bodies captured using markerless motion capture, 3D body scans, and high resolution 3D scene scans. A key feature of RICH is that it also contains accurate vertex-level contact labels on the body. Using RICH, we train a network that predicts dense body-scene contacts from a single RGB image. Our key insight is that regions in contact are always occluded so the network needs the ability to explore the whole image for evidence. We use a transformer to learn such non-local relationships and propose a new Body-Scene contact TRansfOrmer (BSTRO). Very few methods explore 3D contact; those that do focus on the feet only, detect foot contact as a post-processing step, or infer contact from body pose without looking at the scene. To our knowledge, BSTRO is the first method to directly estimate 3D body-scene contact from a single image. We demonstrate that BSTRO significantly outperforms the prior art. The code and dataset will be available for research purposes.
-
We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that high-resolution videos and diversified semantics can significantly improve cross-modality learning. In this paper, we propose a novel High-resolution and Diversified VIdeo-LAnguage pre-training model (HD-VILA) for many visual tasks. In particular, we collect a large dataset with two distinct properties: 1) the first high-resolution dataset including 371.5k hours of 720p videos, and 2) the most diversified dataset covering 15 popular YouTube categories. To enable VL pre-training, we jointly optimize the HD-VILA model by a hybrid Transformer that learns rich spatiotemporal features, and a multimodal Transformer that enforces interactions of the learned video features with diversified texts. Our pre-training model achieves new state-of-the-art results in 10 VL understanding tasks and 2 more novel text-to-visual generation tasks. For example, we outperform SOTA models with relative increases of 40.4% R@1 in zero-shot MSR-VTT text-to-video retrieval task, and 55.4% in high-resolution dataset LSMDC. The learned VL embedding is also effective in generating visually pleasing and semantically relevant results in text-to-visual editing and super-resolution tasks.
-
This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Aiming at generating an image of high visual quality, previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. These approaches neglect that modality differences implying the complementary information are extremely important for both fusion and subsequent detection task. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to a target-aware Dual Adversarial Learning (TarDAL) network for fusion and a commonly used detection network. The fusion network with one generator and dual discriminators seeks commons while learning from differences, which preserves structural information of targets from the infrared and textural details from the visible. Furthermore, we build a synchronized imaging system with calibrated infrared and optical sensors, and collect currently the most comprehensive benchmark covering a wide range of scenarios. Extensive experiments on several public datasets and our benchmark demonstrate that our method outputs not only visually appealing fusion but also higher detection mAP than the state-of-the-art approaches.
-
Generalized zero-shot learning (GZSL) requires a classifier trained on seen classes that can recognize objects from both seen and unseen classes. Due to the absence of unseen training samples, the classifier tends to bias towards seen classes. To mitigate this problem, feature generation based models are proposed to synthesize visual features for unseen classes. However, these features are generated in the visual feature space which lacks of discriminative ability. Therefore, some methods turn to find a better embedding space for the classifier training. They emphasize the inter-class relationships of seen classes, leading the embedding space overfitted to seen classes and unfriendly to unseen classes. Instead, in this paper, we propose an Intra-Class Compactness Enhancement method (ICCE) for GZSL. Our ICCE promotes intra-class compactness with inter-class separability on both seen and unseen classes in the embedding space and visual feature space. By promoting the intra-class relationships but the inter-class structures, we can distinguish different classes with better generalization. Specifically, we propose a Self-Distillation Embedding (SDE) module and a Semantic-Visual Contrastive Generation (SVCG) module. The former promotes intra-class compactness in the embedding space, while the latter accomplishes it in the visual feature space. The experiments demonstrate that our ICCE outperforms the state-of-the-art methods on four datasets and achieves competitive results on the remaining dataset.
-
In computer-aided design (CAD) systems, 2D line drawings are commonly used to illustrate 3D object designs. To reconstruct the 3D models depicted by a single 2D line drawing, an important key is finding the edge loops in the line drawing which correspond to the actual faces of the 3D object. In this paper, we approach the classical problem of face identification from a novel data-driven point of view. We cast it as a sequence generation problem: starting from an arbitrary edge, we adopt a variant of the popular Transformer model to predict the edges associated with the same face in a natural order. This allows us to avoid searching the space of all possible edge loops with various hand-crafted rules and heuristics as most existing methods do, deal with challenging cases such as curved surfaces and nested edge loops, and leverage additional cues such as face types. We further discuss how possibly imperfect predictions can be used for 3D object reconstruction. The project page is at https://manycore-research.github.io/faceformer.
-
Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in the high-frequency region, giving equal consideration to the low and high-frequency areas. In this paper, we propose a new lossless image compression method that proceeds the encoding in a coarse-to-fine manner to separate and process low and high-frequency regions differently. We initially compress the low-frequency components and then use them as additional input for encoding the remaining high-frequency region. The low-frequency components act as a strong prior in this case, which leads to improved estimation in the high-frequency area. In addition, we design the frequency decomposition process to be adaptive to color channel, spatial location, and image characteristics. As a result, our method derives an image-specific optimal ratio of low/high-frequency components. Experiments show that the proposed method achieves state-of-the-art performance for benchmark high-resolution datasets.
-
The nonuniform quantization strategy for compressing neural networks usually achieves better performance than its counterpart, i.e., uniform strategy, due to its superior representational capacity. However, many nonuniform quantization methods overlook the complicated projection process in implementing the nonuniformly quantized weights/activations, which incurs non-negligible time and space overhead in hardware deployment. In this study, we propose Nonuniform-to-Uniform Quantization (N2UQ), a method that can maintain the strong representation ability of nonuniform methods while being hardware-friendly and efficient as the uniform quantization for model inference. We achieve this through learning the flexible in-equidistant input thresholds to better fit the underlying distribution while quantizing these real-valued inputs into equidistant output levels. To train the quantized network with learnable input thresholds, we introduce a generalized straight-through estimator (G-STE) for intractable backward derivative calculation w.r.t. threshold parameters. Additionally, we consider entropy preserving regularization to further reduce information loss in weight quantization. Even under this adverse constraint of imposing uniformly quantized weights and activations, our N2UQ outperforms state-of-the-art nonuniform quantization methods by 0.5 1.7% on ImageNet, demonstrating the contribution of N2UQ design. Code and models are available at: https://github.com/liuzechun/Nonuniform-to-Uniform-Quantization.
-
Stitched images provide a wide field-of-view (FoV) but suffer from unpleasant irregular boundaries. To deal with this problem, existing image rectangling methods devote to searching an initial mesh and optimizing a target mesh to form the mesh deformation in two stages. Then rectangular images can be generated by warping stitched images. However, these solutions only work for images with rich linear structures, leading to noticeable distortions for portraits and landscapes with non-linear objects. In this paper, we address these issues by proposing the first deep learning solution to image rectangling. Concretely, we predefine a rigid target mesh and only estimate an initial mesh to form the mesh deformation, contributing to a compact one-stage solution. The initial mesh is predicted using a fully convolutional network with a residual progressive regression strategy. To obtain results with high content fidelity, a comprehensive objective function is proposed to simultaneously encourage the boundary rectangular, mesh shape-preserving, and content perceptually natural. Besides, we build the first image stitching rectangling dataset with a large diversity in irregular boundaries and scenes. Extensive experiments demonstrate our superiority over traditional methods both quantitatively and qualitatively. The codes and dataset will be available.
-
Domain generalization refers to the problem of training a model from a collection of different source domains that can directly generalize to the unseen target domains. A promising solution is contrastive learning, which attempts to learn domain-invariant representations by exploiting rich semantic relations among sample-to-sample pairs from different domains. A simple approach is to pull positive sample pairs from different domains closer while pushing other negative pairs further apart. In this paper, we find that directly applying contrastive-based methods (e.g., supervised contrastive learning) are not effective in domain generalization. We argue that aligning positive sample-to-sample pairs tends to hinder the model generalization due to the significant distribution gaps between different domains. To address this issue, we propose a novel proxy-based contrastive learning method, which replaces the original sample-to-sample relations with proxy-to-sample relations, significantly alleviating the positive alignment issue. Experiments on the four standard benchmarks demonstrate the effectiveness of the proposed method. Furthermore, we also consider a more complex scenario where no ImageNet pre-trained models are provided. Our method consistently shows better performance.
-
We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry. We also present a new method for 6D pose estimation of rigid objects using the learnt distributions to sample, score and refine pose hypotheses. The correspondence distributions are learnt with a contrastive loss, represented in object-specific latent spaces by an encoder-decoder query model and a small fully connected key model. Our method is unsupervised with respect to visual ambiguities, yet we show that the query- and key models learn to represent accurate multi-modal surface distributions. Our pose estimation method improves the state-of-the-art significantly on the comprehensive BOP Challenge, trained purely on synthetic data, even compared with methods trained on real data. The project site is at surfemb.github.io.
-
We address the problem of generating a 360-degree image from a single image with a narrow field of view by estimating its surroundings. Previous methods suffered from overfitting to the training resolution and deterministic generation. This paper proposes a completion method using a transformer for scene modeling and novel methods to improve the properties of a 360-degree image on the output image. Specifically, we use CompletionNets with a transformer to perform diverse completions and AdjustmentNet to match color, stitching, and resolution with an input image, enabling inference at any resolution. To improve the properties of a 360-degree image on an output image, we also propose WS-perceptual loss and circular inference. Thorough experiments show that our method outperforms state-of-the-art (SOTA) methods both qualitatively and quantitatively. For example, compared to SOTA methods, our method completes images 16 times larger in resolution and achieves 1.7 times lower Frechet inception distance (FID). Furthermore, we propose a pipeline that uses the completion results for lighting and background of 3DCG scenes. Our plausible background completion enables perceptually natural results in the application of inserting virtual objects with specular surfaces.
-
A 3D scene consists of a set of objects, each with a shape and a layout giving their position in space. Understanding 3D scenes from 2D images is an important goal, with applications in robotics and graphics. While there have been recent advances in predicting 3D shape and layout from a single image, most approaches rely on 3D ground truth for training which is expensive to collect at scale. We overcome these limitations and propose a method that learns to predict 3D shape and layout for objects without any ground truth shape or layout information: instead we rely on multi-view images with 2D supervision which can more easily be collected at scale. Through extensive experiments on ShapeNet, Hypersim, and ScanNet we demonstrate that our approach scales to large datasets of realistic images, and compares favorably to methods relying on 3D ground truth. On Hypersim and ScanNet where reliable 3D ground truth is not available, our approach outperforms supervised approaches trained on smaller and less diverse datasets.
-
Temporal action detection (TAD) is an important yet challenging task in video understanding. It aims to simultaneously predict the semantic label and the temporal interval of every action instance in an untrimmed video. Rather than end-to-end learning, most existing methods adopt a head-only learning paradigm, where the video encoder is pre-trained for action classification, and only the detection head upon the encoder is optimized for TAD. The effect of end-to-end learning is not systematically evaluated. Besides, there lacks an in-depth study on the efficiency-accuracy trade-off in end-to-end TAD. In this paper, we present an empirical study of end-to-end temporal action detection. We validate the advantage of end-to-end learning over head-only learning and observe up to 11% performance improvement. Besides, we study the effects of multiple design choices that affect the TAD performance and speed, including detection head, video encoder, and resolution of input videos. Based on the findings, we build a mid-resolution baseline detector, which achieves the state-of-the-art performance of end-to-end methods while running more than 4x faster. We hope that this paper can serve as a guide for end-to-end learning and inspire future research in this field. Code and models are available at https://github.com/xlliu7/E2E-TAD.
-
From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies. We admire these progresses but are confused about the necessity: is there a simple method that can perform comparably well? This paper proposes SimVP, a simple video prediction model that is completely built upon CNN and trained by MSE loss in an end-to-end fashion. Without introducing any additional tricks and complicated strategies, we can achieve state-of-the-art performance on five benchmark datasets. Through extended experiments, we demonstrate that SimVP has strong generalization and extensibility on real-world datasets. The significant reduction of training cost makes it easier to scale to complex scenarios. We believe SimVP can serve as a solid baseline to stimulate the further development of video prediction.
-
Point-based object localization (POL), which pursues high-performance object sensing under low-cost data annotation, has attracted increased attention. However, the point annotation mode inevitably introduces semantic variance for the inconsistency of annotated points. Existing POL methods heavily reply on accurate key-point annotations which are difficult to define. In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points. To this end, we propose a coarse point refinement (CPR) approach, which to our best knowledge is the first attempt to alleviate semantic variance from the perspective of algorithm. CPR constructs point bags, selects semantic-correlated points, and produces semantic center points through multiple instance learning (MIL). In this way, CPR defines a weakly supervised evolution procedure, which ensures training high-performance object localizer under coarse point supervision. Experimental results on COCO, DOTA and our proposed SeaPerson dataset validate the effectiveness of the CPR approach. The dataset and code will be available at https://github.com/ucas-vg/PointTinyBenchmark/
-
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable to track objects with strong variation over a long time span. As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward. We present a novel unsupervised tracking framework, in which we can learn temporal correspondence both on the classification branch and regression branch. Specifically, to propagate reliable template feature in the forward propagation process so that the tracker can be trained in the cycle, we first propose a consistency propagation transformation. We then identify an ill-posed penalty problem in conventional cycle training in backward propagation process. Thus, a differentiable region mask is proposed to select features as well as to implicitly penalize tracking errors on intermediate frames. Moreover, since noisy labels may degrade training, we propose a mask-guided loss reweighting strategy to assign dynamic weights based on the quality of pseudo labels. In extensive experiments, our tracker outperforms preceding unsupervised methods by a substantial margin, performing on par with supervised methods on large-scale datasets such as TrackingNet and LaSOT. Code is available at https://github.com/FlorinShum/ULAST.
-
Multiple-instance learning (MIL) provides an effective way to tackle the video anomaly detection problem by modeling it as a weakly supervised problem as the labels are usually only available at the video level while missing for frames due to expensive labeling cost. We propose to conduct novel Bayesian non-parametric submodular video partition (BN-SVP) to significantly improve MIL model training that can offer a highly reliable solution for robust anomaly detection in practical settings that include outlier segments or multiple types of abnormal events. BN-SVP essentially performs dynamic non-parametric hierarchical clustering with an enhanced self-transition that groups segments in a video into temporally consistent and semantically coherent hidden states that can be naturally interpreted as scenes. Each segment is assumed to be generated through a non-parametric mixture process that allows variations of segments within the same scenes to accommodate the dynamic and noisy nature of many real-world surveillance videos. The scene and mixture component assignment of BN-SVP also induces a pairwise similarity among segments, resulting in non-parametric construction of a submodular set function. Integrating this function with an MIL loss effectively exposes the model to a diverse set of potentially positive instances to improve its training. A greedy algorithm is developed to optimize the submodular function and support efficient model training. Our theoretical analysis ensures a strong performance guarantee of the proposed algorithm. The effectiveness of the proposed approach is demonstrated over multiple real-world anomaly video datasets with robust detection performance.
-
Despite recent advances in deep neural models for semantic image editing, present approaches are dependent on explicit human input. Previous work assumes the availability of manually curated datasets for supervised learning, while for unsupervised approaches the human inspection of discovered components is required to identify those which modify worthwhile semantic features. Here, we present a novel alternative: the utilization of brain responses as a supervision signal for learning semantic feature representations. Participants (N=30) in a neurophysiological experiment were shown artificially generated faces and instructed to look for a particular semantic feature, such as "old" or "smiling", while their brain responses were recorded via electroencephalography (EEG). Using supervision signals inferred from these responses, semantic features within the latent space of a generative adversarial network (GAN) were learned and then used to edit semantic features of new images. We show that implicit brain supervision achieves comparable semantic image editing performance to explicit manual labeling. This work demonstrates the feasibility of utilizing implicit human reactions recorded via brain-computer interfaces for semantic image editing and interpretation.
-
Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this paper, we propose an intuitive yet effective self-supervised approach to train a 3D shape variational autoencoder (VAE) which encourages a disentangled latent representation of identity features. Curating the mini-batch generation by swapping arbitrary features across different shapes allows to define a loss function leveraging known differences and similarities in the latent representations. Experimental results conducted on 3D meshes show that state-of-the-art methods for latent disentanglement are not able to disentangle identity features of faces and bodies. Our proposed method properly decouples the generation of such features while maintaining good representation and reconstruction capabilities. Our code and pre-trained models are available at github.com/simofoti/3DVAE-SwapDisentangled.
-
As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not easily adapted to the other due to the divergent training datasets and tracking objects of both tasks. Although UniTrack demonstrates that a shared appearance model with multiple heads can be used to tackle individual tracking tasks, it fails to exploit the large-scale tracking datasets for training and performs poorly on single object tracking. In this work, we present the Unified Transformer Tracker (UTT) to address tracking problems in different scenarios with one paradigm. A track transformer is developed in our UTT to track the target in both SOT and MOT where the correlation between the target feature and the tracking frame feature is exploited to localize the target. We demonstrate that both SOT and MOT tasks can be solved within this framework, and the model can be simultaneously end-to-end trained by alternatively optimizing the SOT and MOT objectives on the datasets of individual tasks. Extensive experiments are conducted on several benchmarks with a unified model trained on both SOT and MOT datasets.
-
Recent cost volume pyramid based deep neural networks have unlocked the potential of efficiently leveraging high-resolution images for depth inference from multi-view stereo. In general, those approaches assume that the depth of each pixel follows a unimodal distribution. Boundary pixels usually follow a multi-modal distribution as they represent different depths; Therefore, the assumption results in an erroneous depth prediction at the coarser level of the cost volume pyramid and can not be corrected in the refinement levels leading to wrong depth predictions. In contrast, we propose constructing the cost volume by non-parametric depth distribution modeling to handle pixels with unimodal and multi-modal distributions. Our approach outputs multiple depth hypotheses at the coarser level to avoid errors in the early stage. As we perform local search around these multiple hypotheses in subsequent levels, our approach does not maintain the rigid depth spatial ordering and, therefore, we introduce a sparse cost aggregation network to derive information within each volume. We evaluate our approach extensively on two benchmark datasets: DTU and Tanks & Temples. Our experimental results show that our model outperforms existing methods by a large margin and achieves superior performance on boundary regions. Code is available at https://github.com/NVlabs/NP-CVP-MVSNet
-
Despite the recent success of long-tailed object detection, almost all long-tailed object detectors are developed based on the two-stage paradigm. In practice, one-stage detectors are more prevalent in the industry because they have a simple and fast pipeline that is easy to deploy. However, in the long-tailed scenario, this line of work has not been explored so far. In this paper, we investigate whether one-stage detectors can perform well in this case. We discover the primary obstacle that prevents one-stage detectors from achieving excellent performance is: categories suffer from different degrees of positive-negative imbalance problems under the long-tailed data distribution. The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem. To address this issue, we propose the Equalized Focal Loss (EFL) that rebalances the loss contribution of positive and negative samples of different categories independently according to their imbalance degrees. Specifically, EFL adopts a category-relevant modulating factor which can be adjusted dynamically by the training status of different categories. Extensive experiments conducted on the challenging LVIS v1 benchmark demonstrate the effectiveness of our proposed method. With an end-to-end training pipeline, EFL achieves 29.2% in terms of overall AP and obtains significant performance improvements on rare categories, surpassing all existing state-of-the-art methods. The code is available at https://github.com/ModelTC/EOD.
-
Our work focuses on addressing sample deficiency from low-density regions of data manifold in common image datasets. We leverage diffusion process based generative models to synthesize novel images from low-density regions. We observe that uniform sampling from diffusion models predominantly samples from high-density regions of the data manifold. Therefore, we modify the sampling process to guide it towards low-density regions while simultaneously maintaining the fidelity of synthetic data. We rigorously demonstrate that our process successfully generates novel high fidelity samples from low-density regions. We further examine generated samples and show that the model does not memorize low-density data and indeed learns to generate novel samples from low-density regions.
-
Deep Learning (DL) has shown great promise in the unsupervised task of clustering. That said, while in classical (i.e., non-deep) clustering the benefits of the nonparametric approach are well known, most deep-clustering methods are parametric: namely, they require a predefined and fixed number of clusters, denoted by K. When K is unknown, however, using model-selection criteria to choose its optimal value might become computationally expensive, especially in DL as the training process would have to be repeated numerous times. In this work, we bridge this gap by introducing an effective deep-clustering method that does not require knowing the value of K as it infers it during the learning. Using a split/merge framework, a dynamic architecture that adapts to the changing K, and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones). While the very few existing deep nonparametric methods lack scalability, we demonstrate ours by being the first to report the performance of such a method on ImageNet. We also demonstrate the importance of inferring K by showing how methods that fix it deteriorate in performance when their assumed K value gets further from the ground-truth one, especially on imbalanced datasets. Our code is available at https://github.com/BGU-CS-VIL/DeepDPM.
-
Event-based cameras bring a unique capability to tracking, being able to function in challenging real-world conditions as a direct result of their high temporal resolution and high dynamic range. These imagers capture events asynchronously that encode rich temporal and spatial information. However, effectively extracting this information from events remains an open challenge. In this work, we propose a spiking transformer network, STNet, for single object tracking. STNet dynamically extracts and fuses information from both temporal and spatial domains. In particular, the proposed architecture features a transformer module to provide global spatial information and a spiking neural network (SNN) module for extracting temporal cues. The spiking threshold of the SNN module is dynamically adjusted based on the statistical cues of the spatial information, which we find essential in providing robust SNN features. We fuse both feature branches dynamically with a novel cross-domain attention fusion algorithm. Extensive experiments on three event-based datasets, FE240hz, EED and VisEvent validate that the proposed STNet outperforms existing state-of-the-art methods in both tracking accuracy and speed with a significant margin.
-
Interactive segmentation allows users to extract target masks by making positive/negative clicks. Although explored by many previous works, there is still a gap between academic approaches and industrial needs: first, existing models are not efficient enough to work on low power devices; second, they perform poorly when used to refine preexisting masks as they could not avoid destroying the correct part. FocalClick solves both issues at once by predicting and updating the mask in localized areas. For higher efficiency, we decompose the slow prediction on the entire image into two fast inferences on small crops: a coarse segmentation on the Target Crop, and a local refinement on the Focus Crop. To make the model work with preexisting masks, we formulate a sub-task termed Interactive Mask Correction, and propose Progressive Merge as the solution. Progressive Merge exploits morphological information to decide where to preserve and where to update, enabling users to refine any preexisting mask effectively. FocalClick achieves competitive results against SOTA methods with significantly smaller FLOPs. It also shows significant superiority when making corrections on preexisting masks. Code and data will be released at github.com/XavierCHEN34/ClickSEG
-
The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation. To tackle these issues, most of the previous works follow the global-local refinement pipeline, which pays more attention to the memory consumption but neglects the inference speed. In comparison to the pipeline that partitions the large image into small local regions, we focus on inferring the whole image directly. In this paper, we propose ISDNet, a novel ultra-high resolution segmentation framework that integrates the shallow and deep networks in a new manner, which significantly accelerates the inference speed while achieving accurate segmentation. To further exploit the relationship between the shallow and deep features, we propose a novel Relational-Aware feature Fusion module, which ensures high performance and robustness of our framework. Extensive experiments on Deepglobe, Inria Aerial, and Cityscapes datasets demonstrate our performance is consistently superior to state-of-the-arts. Specifically, it achieves 73.30 mIoU with a speed of 27.70 FPS on Deepglobe, which is more accurate and 172 x faster than the recent competitor. Code available at https://github.com/cedricgsh/ISDNet.
-
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications. This work instead develops a novel unsupervised domain adaptation framework for nighttime aerial tracking (named UDAT). Specifically, a unique object discovery approach is provided to generate training patches from raw nighttime tracking videos. To tackle the domain discrepancy, we employ a Transformer-based bridging layer post to the feature extractor to align image features from both domains. With a Transformer day/night feature discriminator, the daytime tracking model is adversarially trained to track at night. Moreover, we construct a pioneering benchmark namely NAT2021 for unsupervised domain adaptive nighttime tracking, which comprises a test set of 180 manually annotated tracking sequences and a train set of over 276k unlabelled nighttime tracking frames. Exhaustive experiments demonstrate the robustness and domain adaptability of the proposed framework in nighttime aerial tracking. The code and benchmark are available at https://github.com/vision4robotics/UDAT.
-
Audio-visual learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not fully exploited even when the multi-modal model outperforms its uni-modal counterpart. Specifically, in this paper we point out that existing audio-visual discriminative models, in which uniform objective is designed for all modalities, could remain under-optimized uni-modal representations, caused by another dominated modality in some scenarios, e.g., sound in blowing wind event, vision in drawing picture event, etc. To alleviate this optimization imbalance, we propose on-the-fly gradient modulation to adaptively control the optimization of each modality, via monitoring the discrepancy of their contribution towards the learning objective. Further, an extra Gaussian noise that changes dynamically is introduced to avoid possible generalization drop caused by gradient modulation. As a result, we achieve considerable improvement over common fusion methods on different audio-visual tasks, and this simple strategy can also boost existing multi-modal methods, which illustrates its efficacy and versatility.
-
Blind face restoration is to recover a high-quality face image from unknown degradations. As face image contains abundant contextual information, we propose a method, RestoreFormer, which explores fully-spatial attentions to model contextual information and surpasses existing works that use local convolutions. RestoreFormer has several benefits compared to prior arts. First, unlike the conventional multi-head self-attention in previous Vision Transformers (ViTs), RestoreFormer incorporates a multi-head cross-attention layer to learn fully-spatial interactions between corrupted queries and high-quality key-value pairs. Second, the key-value pairs in ResotreFormer are sampled from a reconstruction-oriented high-quality dictionary, whose elements are rich in high-quality facial features specifically aimed for face reconstruction, leading to superior restoration results. Third, RestoreFormer outperforms advanced state-of-the-art methods on one synthetic dataset and three real-world datasets, as well as produces images with better visual quality. Code is available at https://github.com/wzhouxiff/RestoreFormer.git.
-
Quantitative descriptions of confidence intervals and uncertainties of the predictions of a model are needed in many applications in vision and machine learning. Mechanisms that enable this for deep neural network (DNN) models are slowly becoming available, and occasionally, being integrated within production systems. But the literature is sparse in terms of how to perform statistical tests with the uncertainties produced by these overparameterized models. For two models with a similar accuracy profile, is the former model's uncertainty behavior better in a statistically significant sense compared to the second model? For high resolution images, performing hypothesis tests to generate meaningful actionable information (say, at a user specified significance level 0.05) is difficult but needed in both mission critical settings and elsewhere. In this paper, specifically for uncertainties defined on images, we show how revisiting results from Random Field theory (RFT) when paired with DNN tools (to get around computational hurdles) leads to efficient frameworks that can provide a hypothesis test capabilities, not otherwise available, for uncertainty maps from models used in many vision tasks. We show via many different experiments the viability of this framework.
-
Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients between the real and synthetic data batches. Despite the intuitive motivation and promising results, such gradient-based methods, by nature, easily overfit to a biased set of samples that produce dominant gradients, and thus lack a global supervision of data distribution. In this paper, we propose a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures. At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales, while accounting for the classification of real samples. Our scheme is further backed up by a novel dynamic bi-level optimization, which adaptively adjusts parameter updates to prevent over-/under-fitting. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art: on the SVHN dataset, for example, the performance gain is up to 11%. Extensive experiments and analysis verify the effectiveness and necessity of proposed designs.
-
Domain generalization (DG) is essentially an out-of-distribution problem, aiming to generalize the knowledge learned from multiple source domains to an unseen target domain. The mainstream is to leverage statistical models to model the dependence between data and labels, intending to learn representations independent of domain. Nevertheless, the statistical models are superficial descriptions of reality since they are only required to model dependence instead of the intrinsic causal mechanism. When the dependence changes with the target distribution, the statistic models may fail to generalize. In this regard, we introduce a general structural causal model to formalize the DG problem. Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments. Our goal is to extract the causal factors from inputs and then reconstruct the invariant causal mechanisms. However, the theoretical idea is far from practical of DG since the required causal/non-causal factors are unobserved. We highlight that ideal causal factors should meet three basic properties: separated from the non-causal ones, jointly independent, and causally sufficient for the classification. Based on that, we propose a Causality Inspired Representation Learning (CIRL) algorithm that enforces the representation to satisfy the above properties and then uses them to simulate the causal factors, which yields improved generalization ability. Extensive experimental results on several widely used datasets verify the effectiveness of our approach.
-
Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement in the coded aperture snapshot spectral imaging (CASSI) system. The HSI representations are highly similar and correlated across the spectral dimension. Modeling the inter-spectra interactions is beneficial for HSI reconstruction. However, existing CNN-based methods show limitations in capturing spectral-wise similarity and long-range dependencies. Besides, the HSI information is modulated by a coded aperture (physical mask) in CASSI. Nonetheless, current algorithms have not fully explored the guidance effect of the mask for HSI restoration. In this paper, we propose a novel framework, Mask-guided Spectral-wise Transformer (MST), for HSI reconstruction. Specifically, we present a Spectral-wise Multi-head Self-Attention (S-MSA) that treats each spectral feature as a token and calculates self-attention along the spectral dimension. In addition, we customize a Mask-guided Mechanism (MM) that directs S-MSA to pay attention to spatial regions with high-fidelity spectral representations. Extensive experiments show that our MST significantly outperforms state-of-the-art (SOTA) methods on simulation and real HSI datasets while requiring dramatically cheaper computational and memory costs. https://github.com/caiyuanhao1998/MST/
-
We propose a novel variational Bayesian formulation for diffeomorphic non-rigid registration of medical images, which learns in an unsupervised way a data-specific similarity metric. The proposed framework is general and may be used together with many existing image registration models. We evaluate it on brain MRI scans from the UK Biobank and show that use of the learnt similarity metric, which is parametrised as a neural network, leads to more accurate results than use of traditional functions, e.g. SSD and LCC, to which we initialise the model, without a negative impact on image registration speed or transformation smoothness. In addition, the method estimates the uncertainty associated with the transformation. The code and the trained models are available in a public repository: https://github.com/dgrzech/learnsim.
-
Online class-incremental continual learning aims to learn new classes continually from a never-ending and single-pass data stream, while not forgetting the learned knowledge of old classes. Existing replay-based methods have shown promising performance by storing a subset of old class data. Unfortunately, these methods only focus on selecting samples from the memory bank for replay and ignore the adequate exploration of semantic information in the single-pass data stream, leading to poor classification accuracy. In this paper, we propose a novel yet effective framework for online class-incremental continual learning, which considers not only the selection of stored samples, but also the full exploration of the data stream. Specifically, we propose a gradient-based sample selection strategy, which selects the stored samples whose gradients generated in the network are most interfered by the new incoming samples. We believe such samples are beneficial for updating the neural network based on back gradient propagation. More importantly, we seek to explore the semantic information between two different views of training images by maximizing their mutual information, which is conducive to the improvement of classification accuracy. Extensive experimental results demonstrate that our method achieves state-of-the-art performance on a variety of benchmark datasets. Our code is available on https://github.com/YananGu/DVC.
-
Scene Graph Generation (SGG) has attracted more and more attention from visual researchers in recent years, since Scene Graph (SG) is valuable in many downstream tasks due to its rich structural-semantic details. However, the application value of SG on downstream tasks is severely limited by the predicate classification bias, which is caused by long-tailed data and presented as semantic bias of predicted relation predicates. Existing methods mainly reduce the prediction bias by better aggregating contexts and integrating external priori knowledge, but rarely take the semantic similarities between predicates into account. In this paper, we propose a Predicate Probability Distribution based Loss (PPDL) to train the biased SGG models and obtain unbiased Scene Graphs ultimately. Firstly, we propose a predicate probability distribution as the semantic representation of a particular predicate class. Afterwards, we re-balance the biased training loss according to the similarity between the predicted probability distribution and the estimated one, and eventually eliminate the long-tailed bias on predicate classification. Notably, the PPDL training method is model-agnostic, and extensive experiments and qualitative analyses on the Visual Genome dataset reveal significant performance improvements of our method on tail classes compared to the state-of-the-art methods.
-
We present Block-NeRF, a variant of Neural Radiance Fields that can represent large-scale environments. Specifically, we demonstrate that when scaling NeRF to render city-scale scenes spanning multiple blocks, it is vital to decompose the scene into individually trained NeRFs. This decomposition decouples rendering time from scene size, enables rendering to scale to arbitrarily large environments, and allows per-block updates of the environment. We adopt several architectural changes to make NeRF robust to data captured over months under different environmental conditions. We add appearance embeddings, learned pose refinement, and controllable exposure to each individual NeRF, and introduce a procedure for aligning appearance between adjacent NeRFs so that they can be seamlessly combined. We build a grid of Block-NeRFs from 2.8 million images to create the largest neural scene representation to date, capable of rendering an entire neighborhood of San Francisco.
-
We exploit the complementary strengths of vision and proprioception to develop a point-goal navigation system for legged robots, called VP-Nav. Legged systems are capable of traversing more complex terrain than wheeled robots, but to fully utilize this capability, we need a high-level path planner in the navigation system to be aware of the walking capabilities of the low-level locomotion policy in varying environments. We achieve this by using proprioceptive feedback to ensure the safety of the planned path by sensing unexpected obstacles like glass walls, terrain properties like slipperiness or softness of the ground and robot properties like extra payload that are likely missed by vision. The navigation system uses onboard cameras to generate an occupancy map and a corresponding cost map to reach the goal. A fast marching planner then generates a target path. A velocity command generator takes this as input to generate the desired velocity for the walking policy. A safety advisor module adds sensed unexpected obstacles to the occupancy map and environment-determined speed limits to the velocity command generator. We show superior performance compared to wheeled robot baselines, and ablation studies which have disjoint high-level planning and low-level control. We also show the real-world deployment of VP-Nav on a quadruped robot with onboard sensors and computation. Videos at https://navigation-locomotion.github.io
-
The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e.g., "woman-on/standing on/walking on-beach" or "woman-near/looking at/in front of-child". While general SGG models are prone to predict head predicates and existing re-balancing strategies prefer tail categories, none of them can appropriately handle these hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating among hard-to-distinguish object classes, we propose a method named Fine-Grained Predicates Learning (FGPL) which aims at differentiating among hard-to-distinguish predicates for Scene Graph Generation task. Specifically, we first introduce a Predicate Lattice that helps SGG models to figure out fine-grained predicate pairs. Then, utilizing the Predicate Lattice, we propose a Category Discriminating Loss and an Entity Discriminating Loss, which both contribute to distinguishing fine-grained predicates while maintaining learned discriminatory power over recognizable ones. The proposed model-agnostic strategy significantly boosts the performances of three benchmark models (Transformer, VCTree, and Motif) by 22.8%, 24.1% and 21.7% of Mean Recall (mR@100) on the Predicate Classification sub-task, respectively. Our model also outperforms state-of-the-art methods by a large margin (i.e., 6.1%, 4.6%, and 3.2% of Mean Recall (mR@100)) on the Visual Genome dataset.
-
Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Segmentation (FS-Seg) tackles this problem with many constraints. In this paper, we introduce a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS-Seg), to analyze the generalization ability of simultaneously segmenting the novel categories with very few examples and the base categories with sufficient examples. It is the first study showing that previous representative state-of-the-art FS-Seg methods fall short in GFS-Seg and the performance discrepancy mainly comes from the constrained setting of FS-Seg. To make GFS-Seg tractable, we set up a GFS-Seg baseline that achieves decent performance without structural change on the original model. Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image. Both two contributions are experimentally shown to have substantial practical merit. Extensive experiments on Pascal-VOC and COCO manifest the effectiveness of CAPL, and CAPL generalizes well to FS-Seg by achieving competitive performance. Code will be made publicly available.
-
Previous LiDAR scene flow estimation methods, especially recurrent neural networks, usually suffer from structure distortion in challenging cases, such as sparse reflection and motion occlusions. In this paper, we propose a novel optimization method based on a recurrent neural network to predict LiDAR scene flow in a weakly supervised manner. Specifically, our neural recurrent network exploits direct rigidity constraints to preserve the geometric structure of the warped source scene during an iterative alignment procedure. An error awarded optimization strategy is proposed to update the LiDAR scene flow by minimizing the point measurement error instead of reconstructing the cost volume multiple times. Trained on two autonomous driving datasets, our network outperforms recent state-of-the-art networks on lidarKITTI by a large margin. The code and models will be available at https://github. com/gtdong-ustc/LiDARSceneFlow.
-
We present Neural Head Avatars, a novel neural representation that explicitly models the surface geometry and appearance of an animatable human avatar that can be used for teleconferencing in AR/VR or other applications in the movie or games industry that rely on a digital human. Our representation can be learned from a monocular RGB portrait video that features a range of different expressions and views. Specifically, we propose a hybrid representation consisting of a morphable model for the coarse shape and expressions of the face, and two feed-forward networks, predicting vertex offsets of the underlying mesh as well as a view- and expression-dependent texture. We demonstrate that this representation is able to accurately extrapolate to unseen poses and view points, and generates natural expressions while providing sharp texture details. Compared to previous works on head avatars, our method provides a disentangled shape and appearance model of the complete human head (including hair) that is compatible with the standard graphics pipeline. Moreover, it quantitatively and qualitatively outperforms current state of the art in terms of reconstruction quality and novel-view synthesis.
-
We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. For this, we propose to replace the linear transforms in DNNs by our B-cos transform. As we show, a sequence (network) of such transforms induces a single linear transform that faithfully summarises the full model computations. Moreover, the B-cos transform introduces alignment pressure on the weights during optimisation. As a result, those induced linear transforms become highly interpretable and align with task-relevant features. Importantly, the B-cos transform is designed to be compatible with existing architectures and we show that it can easily be integrated into common models such as VGGs, ResNets, InceptionNets, and DenseNets, whilst maintaining similar performance on ImageNet. The resulting explanations are of high visual quality and perform well under quantitative metrics for interpretability. Code available at github.com/moboehle/B-cos.
-
As 3D facial avatars become more widely used for communication, it is critical that they faithfully convey emotion. Unfortunately, the best recent methods that regress parametric 3D face models from monocular images are unable to capture the full spectrum of facial expression, such as subtle or extreme emotions. We find the standard reconstruction metrics used for training (landmark reprojection error, photometric error, and face recognition loss) are insufficient to capture high-fidelity expressions. The result is facial geometries that do not match the emotional content of the input image. We address this with EMOCA (EMOtion Capture and Animation), by introducing a novel deep perceptual emotion consistency loss during training, which helps ensure that the reconstructed 3D expression matches the expression depicted in the input image. While EMOCA achieves 3D reconstruction errors that are on par with the current best methods, it significantly outperforms them in terms of the quality of the reconstructed expression and the perceived emotional content. We also directly regress levels of valence and arousal and classify basic expressions from the estimated 3D face parameters. On the task of in-the-wild emotion recognition, our purely geometric approach is on par with the best image-based methods, highlighting the value of 3D geometry in analyzing human behavior. The model and code are publicly available at https://emoca.is.tue.mpg.de.
-
Modern handheld devices can acquire burst image sequence in a quick succession. However, the individual acquired frames suffer from multiple degradations and are misaligned due to camera shake and object motions. The goal of Burst Image Restoration is to effectively combine complimentary cues across multiple burst frames to generate high-quality outputs. Towards this goal, we develop a novel approach by solely focusing on the effective information exchange between burst frames, such that the degradations get filtered out while the actual scene details are preserved and enhanced. Our central idea is to create a set of pseudo-burst features that combine complimentary information from all the input burst frames to seamlessly exchange information. The pseudo-burst representations encode channel-wise features from the original burst images, thus making it easier for the model to learn distinctive information offered by multiple burst frames. However, the pseudo-burst cannot be successfully created unless the individual burst frames are properly aligned to discount inter-frame movements. Therefore, our approach initially extracts preprocessed features from each burst frame and matches them using an edge-boosting burst alignment module. The pseudo-burst features are then created and enriched using multi-scale contextual information. Our final step is to adaptively aggregate information from the pseudo-burst features to progressively increase resolution in multiple stages while merging the pseudo-burst features. In comparison to existing works that usually follow a late fusion scheme with single-stage upsampling, our approach performs favorably, delivering state-of-the-art performance on burst super-resolution, burst low-light image enhancement and burst denoising tasks. Our codes will be publicly released.
-
Transfer learning is a standard technique to transfer knowledge from one domain to another. For applications in medical imaging, transfer from ImageNet has become the de-facto approach, despite differences in the tasks and image characteristics between the domains. However, it is unclear what factors determine whether - and to what extent - transfer learning to the medical domain is useful. The long-standing assumption that features from the source domain get reused has recently been called into question. Through a series of experiments on several medical image benchmark datasets, we explore the relationship between transfer learning, data size, the capacity and inductive bias of the model, as well as the distance between the source and target domain. Our findings suggest that transfer learning is beneficial in most cases, and we characterize the important role feature reuse plays in its success.
-
The ability to synthesize long-term human motion sequences in real-world scenes can facilitate numerous applications. Previous approaches for scene-aware motion synthesis are constrained by pre-defined target objects or positions and thus limit the diversity of human-scene interactions for synthesized motions. In this paper, we focus on the problem of synthesizing diverse scene-aware human motions under the guidance of target action sequences. To achieve this, we first decompose the diversity of scene aware human motions into three aspects, namely interaction diversity (e.g. sitting on different objects with different poses in the given scenes), path diversity (e.g. moving to the target locations following different paths), and the motion diversity (e.g. having various body movements during moving). Based on this factorized scheme, a hierarchical framework is proposed with each sub-module responsible for modeling one aspect. We assess the effectiveness of our framework on two challenging datasets for scene-aware human motion synthesis. The experiment results show that the proposed framework remarkably outperforms the previous methods in terms of diversity and naturalness.
-
Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a particular trigger. Several works attempt to detect whether a given DNN has been injected with a specific trigger during the training. In a parallel line of research, the lottery ticket hypothesis reveals the existence of sparse subnetworks which are capable of reaching competitive performance as the dense network after independent training. Connecting these two dots, we investigate the problem of Trojan DNN detection from the brand new lens of sparsity, even when no clean training data is available. Our crucial observation is that the Trojan features are significantly more stable to network pruning than benign features. Leveraging that, we propose a novel Trojan network detection regime: first locating a "winning Trojan lottery ticket" which preserves nearly full Trojan information yet only chance-level performance on clean inputs; then recovering the trigger embedded in this already isolated subnetwork. Extensive experiments on various datasets, i.e., CIFAR-10, CIFAR-100, and ImageNet, with different network architectures, i.e., VGG-16, ResNet-18, ResNet-20s, and DenseNet-100 demonstrate the effectiveness of our proposal. Codes are available at https://github.com/VITA-Group/Backdoor-LTH.
-
Since facial actions such as lip movements contain significant information about speech content, it is not surprising that audio-visual speech enhancement methods are more accurate than their audio-only counterparts. Yet, state-of-the-art approaches still struggle to generate clean, realistic speech without noise artifacts and unnatural distortions in challenging acoustic environments. In this paper, we propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR. Our approach leverages audio-visual speech cues to generate the codes of a neural speech codec, enabling efficient synthesis of clean, realistic speech from noisy signals. Given the importance of speaker-specific cues in speech, we focus on developing personalized models that work well for individual speakers. We demonstrate the efficacy of our approach on a new audio-visual speech dataset collected in an unconstrained, large vocabulary setting, as well as existing audio-visual datasets, outperforming speech enhancement baselines on both quantitative metrics and human evaluation studies. Please see the supplemental video for qualitative results.
-
Deep learning methods can struggle to handle domain shifts not seen in training data, which can cause them to not generalize well to unseen domains. This has led to research attention on domain generalization (DG), which aims to the model's generalization ability to out-of-distribution. Adversarial domain generalization is a popular approach to DG, but conventional approaches (1) struggle to sufficiently align features so that local neighborhoods are mixed across domains; and (2) can suffer from feature space over collapse which can threaten generalization performance. To address these limitations, we propose localized adversarial domain generalization with space compactness maintenance (LADG) which constitutes two major contributions. First, we propose an adversarial localized classifier as the domain discriminator, along with a principled primary branch. This constructs a min-max game whereby the aim of the featurizer is to produce locally mixed domains. Second, we propose to use a coding-rate loss to alleviate feature space over collapse. We conduct comprehensive experiments on the Wilds DG benchmark to validate our approach, where LADG outperforms leading competitors on most datasets.
-
3D dense captioning aims to describe individual objects by natural language in 3D scenes, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only exploiting single modal information, e.g., point cloud, previous approaches fail to produce faithful descriptions. Though aggregating 2D features into point clouds may be beneficial, it introduces an extra computational burden, especially in inference phases. In this study, we investigate a cross-modal knowledge transfer using Transformer for 3D dense captioning, X-Trans2Cap, to effectively boost the performance of single-modal 3D caption through knowledge distillation using a teacher-student framework. In practice, during the training phase, the teacher network exploits auxiliary 2D modality and guides the student network that only takes point clouds as input through the feature consistency constraints. Owing to the well-designed cross-modal feature fusion module and the feature alignment in the training phase, X-Trans2Cap acquires rich appearance information embedded in 2D images with ease. Thus, a more faithful capti
Introduction
Conference CVPR2022 accepted paper complete List. Top ranking conferences for AI and Robotics communities. Total Accepted Paper Count 3106