FDLNet: Boosting Real-time Semantic Segmentation by Image-size Convolution via Frequency Domain Learning
Qingqing Yan,Shu Li,Chengju Liu,Ming Liu,Qijun Chen,Qingqing Yan,Shu Li,Chengju Liu,Ming Liu,Qijun Chen
This paper proposes a novel real-time semantic segmentation network via frequency domain learning, called FDLNet, which revisits the segmentation task from two critical perspectives: spatial structure description and multilevel feature fusion. We first devise an image-size convolution (IS-Conv) as a global frequency-domain learning operator to capture long-range dependency in a single shot. To mod...
