annnet

Introduction

Official Repo

Code Snippet

ANN (ICCV'2019)

@inproceedings{zhu2019asymmetric,
    title={Asymmetric non-local neural networks for semantic segmentation},
    author={Zhu, Zhen and Xu, Mengde and Bai, Song and Huang, Tengteng and Bai, Xiang},
    booktitle={Proceedings of the IEEE International Conference on Computer Vision},
    pages={593--602},
    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	76.68%	cfg | model | log
R-50-D16	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/60	trainaug/val	75.30%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/60	trainaug/val	78.15%	cfg | model | log
R-101-D16	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/60	trainaug/val	77.16%	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	41.75%	cfg | model | log
R-50-D16	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/130	train/val	39.55%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/130	train/val	43.98%	cfg | model | log
R-101-D16	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/130	train/val	42.22%	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	78.36%	cfg | model | log
R-50-D16	ImageNet-1k-224x224	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	76.20%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	79.34%	cfg | model | log
R-101-D16	ImageNet-1k-224x224	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	78.10%	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