PSANet: Point-wise Spatial Attention Network for Scene Parsing
Published in
European Conference on Computer Vision(2018)External Links:
TL
TL;DR
The point-wise spatial attention network (PSANet) is proposed to relax the local neighborhood constraint and achieves top performance on various competitive scene parsing datasets, including ADE20K, PASCAL VOC 2012 and Cityscapes, demonstrating its effectiveness and generality.