Long and short-range relevance context network for semantic segmentation

• DOI: 10.1007/s40747-023-01103-6
• Publication Date: 2023-06-21T04:14:23Z
• Authors: Qing Liu; Yongsheng Dong; Yuanhua Pei; Lintao Zheng; Lei Zhang
• Keywords: Relevance; Spatial contextual awareness; Feature (linguistics)

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