HCNet: Hierarchical Context Network for Semantic Segmentation
HCNet: Hierarchical Context Network for Semantic Segmentation
Global context information is vital in visual understanding problems, especially in pixel-level semantic segmentation. The mainstream methods adopt the self-attention mechanism to model global context information. However, pixels belonging to different classes usually have weak feature correlation. Modeling the global pixel-level correlation matrix indiscriminately is extremely redundant in the self-attention …