Skip to content

Latest commit

 

History

History

encnet

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 

README.md

Introduction

Official Repo

Code Snippet

EncNet (CVPR'2018) 
@InProceedings{Zhang_2018_CVPR,
    author = {Zhang, Hang and Dana, Kristin and Shi, Jianping and Zhang, Zhongyue and Wang, Xiaogang and Tyagi, Ambrish and Agrawal, Amit},
    title = {Context Encoding for Semantic Segmentation},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    month = {June},
    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 75.53% cfg | model | log
R-50-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 74.55% cfg | model | log
R-101-D8 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 77.61% cfg | model | log
R-101-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 76.41% 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 40.60% cfg | model | log
R-50-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 39.70% cfg | model | log
R-101-D8 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 43.43% cfg | model | log
R-101-D16 ImageNet-1k-224x224 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 41.65% 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 77.98% cfg | model | log
R-50-D16 ImageNet-1k-224x224 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 75.98% cfg | model | log
R-101-D8 ImageNet-1k-224x224 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 78.70% cfg | model | log
R-101-D16 ImageNet-1k-224x224 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 77.46% cfg | model | log

More

You can also download the model weights from following sources: