Skip to content

Latest commit

 

History

History
 
 

psanet

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

PSANet

PSANet: Point-wise Spatial Attention Network for Scene Parsing

Introduction

Official Repo

Code Snippet

Abstract

We notice information flow in convolutional neural networksis restricted inside local neighborhood regions due to the physical de-sign of convolutional filters, which limits the overall understanding ofcomplex scenes. In this paper, we propose thepoint-wise spatial atten-tion network(PSANet) to relax the local neighborhood constraint. Eachposition on the feature map is connected to all the other ones througha self-adaptively learned attention mask. Moreover, information propa-gation in bi-direction for scene parsing is enabled. Information at otherpositions can be collected to help the prediction of the current positionand vice versa, information at the current position can be distributedto assist the prediction of other ones. Our proposed approach achievestop performance on various competitive scene parsing datasets, includ-ing ADE20K, PASCAL VOC 2012 and Cityscapes, demonstrating itseffectiveness and generality.

Citation

@inproceedings{zhao2018psanet,
  title={Psanet: Point-wise spatial attention network for scene parsing},
  author={Zhao, Hengshuang and Zhang, Yi and Liu, Shu and Shi, Jianping and Change Loy, Chen and Lin, Dahua and Jia, Jiaya},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={267--283},
  year={2018}
}

Results and models

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
PSANet R-50-D8 512x1024 40000 7 3.17 77.63 79.04 config model | log
PSANet R-101-D8 512x1024 40000 10.5 2.20 79.14 80.19 config model | log
PSANet R-50-D8 769x769 40000 7.9 1.40 77.99 79.64 config model | log
PSANet R-101-D8 769x769 40000 11.9 0.98 78.43 80.26 config model | log
PSANet R-50-D8 512x1024 80000 - - 77.24 78.69 config model | log
PSANet R-101-D8 512x1024 80000 - - 79.31 80.53 config model | log
PSANet R-50-D8 769x769 80000 - - 79.31 80.91 config model | log
PSANet R-101-D8 769x769 80000 - - 79.69 80.89 config model | log

ADE20K

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
PSANet R-50-D8 512x512 80000 9 18.91 41.14 41.91 config model | log
PSANet R-101-D8 512x512 80000 12.5 13.13 43.80 44.75 config model | log
PSANet R-50-D8 512x512 160000 - - 41.67 42.95 config model | log
PSANet R-101-D8 512x512 160000 - - 43.74 45.38 config model | log

Pascal VOC 2012 + Aug

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
PSANet R-50-D8 512x512 20000 6.9 18.24 76.39 77.34 config model | log
PSANet R-101-D8 512x512 20000 10.4 12.63 77.91 79.30 config model | log
PSANet R-50-D8 512x512 40000 - - 76.30 77.35 config model | log
PSANet R-101-D8 512x512 40000 - - 77.73 79.05 config model | log