isanet

Introduction

Official Repo

Code Snippet

ISANet (ArXiv'2019/IJCV'2021)

@article{huang2019isa,
    title={Interlaced Sparse Self-Attention for Semantic Segmentation},
    author={Huang, Lang and Yuan, Yuhui and Guo, Jianyuan and Zhang, Chao and Chen, Xilin and Wang, Jingdong},
    journal={arXiv preprint arXiv:1907.12273},
    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	76.99%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/60	trainaug/val	78.60%	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	42.60%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x512	LR/POLICY/BS/EPOCH: 0.01/poly/16/130	train/val	44.08%	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	79.34%	cfg | model | log
R-101-D8	ImageNet-1k-224x224	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	80.58%	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