Skip to content

Latest commit

 

History

History

ce2p

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 

README.md

Introduction

Official Repo

Code Snippet

CE2P (AAAI'2019) 
@inproceedings{ruan2019devil,
    title={Devil in the details: Towards accurate single and multiple human parsing},
    author={Ruan, Tao and Liu, Ting and Huang, Zilong and Wei, Yunchao and Wei, Shikui and Zhao, Yao},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    volume={33},
    pages={4814--4821},
    year={2019}
}

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 75.69% cfg | model | log
R-50-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 74.58% cfg | model | log
R-101-D8 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 77.77% cfg | model | log
R-101-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 76.84% cfg | model | log

LIP

Backbone Pretrain Crop Size Schedule Train/Eval Set mIoU Download
R-50-D8 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 52.42% cfg | model | log
R-50-D16 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 51.98% cfg | model | log
R-101-D8 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 54.79% cfg | model | log
R-101-D16 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 54.02% cfg | model | log

CIHP

Backbone Pretrain Crop Size Schedule Train/Eval Set mIoU Download
R-50-D8 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 61.15% cfg | model | log
R-50-D16 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 60.15% cfg | model | log
R-101-D8 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 63.83% cfg | model | log
R-101-D16 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 62.25% cfg | model | log

ATR

Backbone Pretrain Crop Size Schedule Train/Eval Set mIoU Download
R-50-D8 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 78.02% cfg | model | log
R-50-D16 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 77.62% cfg | model | log
R-101-D8 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 78.57% cfg | model | log
R-101-D16 ImageNet-1k-224x224 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 78.25% cfg | model | log

More

You can also download the model weights from following sources: