Channelized Axial Attention – considering Channel Relation within Spatial Attention for Semantic Segmentation

Spatial and channel attentions, modelling the semantic interdependencies in spatial and channel dimensions respectively, have recently been widely used for semantic segmentation. However, computing spatial and channel attentions separately sometimes causes errors, especially for those difficult cases. In this paper, we propose Channelized Axial Attention (CAA) to seamlessly integrate channel attention and spatial attention into a single operation with negligible computation overhead. Specifically, we break down the dot-product operation of the spatial attention into two parts and insert channel relation in between, allowing for independently optimized channel attention on each spatial location. We further develop grouped vectorization, which allows our model to run with very little memory consumption without slowing down the running speed. Comparative experiments conducted on multiple benchmark datasets, including Cityscapes, PAS- CAL Context, and COCO-Stuff, demonstrate that our CAA outperforms many state-of-the-art segmentation models (including dual attention) on all tested datasets.

Authors

• Ye Huang Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China
• Di Kang Tencent
• Wenjing Jia
• Liu Liu Tencent AI Lab
• Xiangjian He The Digital Port Technologies Lab, School of Computer Science, University of Nottingham Ningbo China Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute, University of Nottingham Ningbo China

Keywords

No keywords are indexed for this paper.