pspnet

Introduction

Official Repo

Code Snippet

PSPNet (CVPR'2017)

@inproceedings{zhao2017pyramid,
    title={Pyramid scene parsing network},
    author={Zhao, Hengshuang and Shi, Jianping and Qi, Xiaojuan and Wang, Xiaogang and Jia, Jiaya},
    booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
    pages={2881--2890},
    year={2017}
}

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	77.93%	cfg | model | log
R-50-D16	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/60	trainaug/val	76.29%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/60	trainaug/val	79.04%	cfg | model | log
R-101-D16	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/60	trainaug/val	77.92%	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	42.64%	cfg | model | log
R-50-D16	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/130	train/val	40.23%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/130	train/val	44.55%	cfg | model | log
R-101-D16	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/130	train/val	43.40%	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	79.05%	cfg | model | log
R-50-D16	ImageNet-1k-224x224	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	77.13%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	79.94%	cfg | model | log
R-101-D16	ImageNet-1k-224x224	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	77.43%	cfg | model | log

More

You can also download the model weights from following sources:

• BaiduNetdisk: https://pan.baidu.com/s/1gD-NJJWOtaHCtB0qHE79rA with access code s757