Skip to content

Latest commit

 

History

History

psanet

Folders and files

NameName
Last commit message
Last commit date

parent directory

..

README.md

README.md

 
 

README.md

Introduction

Official Repo

Code Snippet

PSANet (ECCV'2018) 
@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

PASCAL VOC

Backbone Pretrain Crop Size Schedule Train/Eval Set mIoU Download
R-50-D8 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 77.06% cfg | model | log
R-50-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 76.92% cfg | model | log
R-101-D8 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 78.97% cfg | model | log
R-101-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 77.90% cfg | model | log

ADE20k

Backbone Pretrain Crop Size Schedule Train/Eval Set mIoU Download
R-50-D8 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 41.99% cfg | model | log
R-50-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 40.26% cfg | model | log
R-101-D8 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 43.85% cfg | model | log
R-101-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 42.05% cfg | model | log

CityScapes

Backbone Pretrain Crop Size Schedule Train/Eval Set mIoU Download
R-50-D8 ImageNet-1k-224x224 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 78.88% cfg | model | log
R-50-D16 ImageNet-1k-224x224 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 76.66% cfg | model | log
R-101-D8 ImageNet-1k-224x224 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 79.65% cfg | model | log
R-101-D16 ImageNet-1k-224x224 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 77.04% cfg | model | log

More

You can also download the model weights from following sources: