PSANet: Point-wise Spatial Attention Network for Scene Parsing

ECCV 2018 Hengshuang ZhaoYi ZhangShu LiuJianping ShiChen Change LoyDahua LinJiaya Jia

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

Evaluation results from the paper


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