Long and short-range relevance context network for semantic segmentation

The semantic information can ensure better pixel classification, and the spatial information of the low-level feature map can ensure the detailed location of the pixels. However, this part of spatial information is often ignored in capturing semantic information, it is a huge loss for the spatial location of the image semantic category itself. To better alleviate this problem, we propose a Long and Short-Range Relevance Context Network. Specifically, we first construct a Long-Range Relevance Context Module to capture the global semantic context of the high-level feature and the ignored local spatial context information. At the same time, we build a Short-Range Relevance Context Module to capture the piecewise spatial context information in each stage of the low-level features in the form of jump connections. The whole network adopts a coding and decoding structure to better improve the segmentation results. Finally, we conduct a large number of experiments on three semantic segmentation datasets (PASCAL VOC2012, Cityscapes and ADE20K datasets) to verify the effectiveness of the network.

Automated summary

In this paper, a Long and Short-Range Relevance Context Network is proposed to capture global semantic context and local spatial context information. The network utilizes Long-Range Relevance Context Module and Short-Range Relevance Context Module to improve the accuracy of pixel classification and detailed pixel location. A coding and decoding structure is adopted to enhance the segmentation results, and experiments on multiple datasets validate the effectiveness of the network.