configs/psanet/README.md

PSANet: Point-wise Spatial Attention Network for Scene Parsing

Introduction

[ALGORITHM]

@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)	download
PSANet	R-50-D8	512x1024	40000	7	3.17	77.63	79.04	model | log
PSANet	R-101-D8	512x1024	40000	10.5	2.20	79.14	80.19	model | log
PSANet	R-50-D8	769x769	40000	7.9	1.40	77.99	79.64	model | log
PSANet	R-101-D8	769x769	40000	11.9	0.98	78.43	80.26	model | log
PSANet	R-50-D8	512x1024	80000	-	-	77.24	78.69	model | log
PSANet	R-101-D8	512x1024	80000	-	-	79.31	80.53	model | log
PSANet	R-50-D8	769x769	80000	-	-	79.31	80.91	model | log
PSANet	R-101-D8	769x769	80000	-	-	79.69	80.89	model | log

ADE20K

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

Pascal VOC 2012 + Aug

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