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... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Semantic Segmentation ADE20K val PSANet (ResNet-101) mIoU 43.77% # 17
Semantic Segmentation Cityscapes test PSANet (ResNet-101) Mean IoU (class) 81.4% # 22
Semantic Segmentation Cityscapes test PSANet (ResNet-101) Mean IoU (class) 80.1% # 29

Methods used in the Paper