PSANet: Point-wise Spatial Attention Network for Scene Parsing

We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes. In this paper, we propose the point-wise spatial attention network (PSANet) to relax the local neighborhood constraint. Each position on the feature map is connected to all the other ones through a self-adaptively learned attention mask. Moreover, information propagation in bi-direction for scene parsing is enabled. Information at other positions can be collected to help the prediction of the current position and vice versa, information at the current position can be distributed to assist the prediction of other ones. Our proposed approach achieves top performance on various competitive scene parsing datasets, including ADE20K, PASCAL VOC 2012 and Cityscapes, demonstrating its effectiveness and generality.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Semantic Segmentation ADE20K PSANet (ResNet-101) Validation mIoU 43.77 # 198
Semantic Segmentation ADE20K val PSANet (ResNet-101) mIoU 43.77 # 83

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Semantic Segmentation Cityscapes test PSANet (ResNet-101) Mean IoU (class) 80.1% # 51

Methods