ADD: A Fine-grained Dynamic Inference Architecture for Semantic Image Segmentation
Chi-Hsi Kung,Che-Rung Lee,Chi-Hsi Kung,Che-Rung Lee
Dynamic inference that adaptively skips parts of model execution based on the complexity of input data can effectively reduce the computation cost of deep learning models during the inference. However, current architectures for dynamic inference only consider the exits at the block level, whose results may not be suitable for different applications. In this paper, we present the Auto-Dynamic-DeepL...
