PSANet: Point-wise Spatial Attention Network for Scene Parsing
PSANet: Point-wise Spatial Attention Network for Scene Parsing
Hengshuang Zhao,Yi Zhang,4 Autori,Jiaya Jia
2018 · DOI: 10.1007/978-3-030-01240-3_17
European Conference on Computer Vision · 1,006 citazioni
TLDR
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.