README.md

ResNeSt: Split-Attention Networks

Introduction

[ALGORITHM]

@article{zhang2020resnest,
title={ResNeSt: Split-Attention Networks},
author={Zhang, Hang and Wu, Chongruo and Zhang, Zhongyue and Zhu, Yi and Zhang, Zhi and Lin, Haibin and Sun, Yue and He, Tong and Muller, Jonas and Manmatha, R. and Li, Mu and Smola, Alexander},
journal={arXiv preprint arXiv:2004.08955},
year={2020}
}

Results and models

Cityscapes

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	download
FCN	S-101-D8	512x1024	80000	11.4	2.39	77.56	78.98	model | log
PSPNet	S-101-D8	512x1024	80000	11.8	2.52	78.57	79.19	model | log
DeepLabV3	S-101-D8	512x1024	80000	11.9	1.88	79.67	80.51	model | log
DeepLabV3+	S-101-D8	512x1024	80000	13.2	2.36	79.62	80.27	model | log

ADE20k

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	download
FCN	S-101-D8	512x512	160000	14.2	12.86	45.62	46.16	model | log
PSPNet	S-101-D8	512x512	160000	14.2	13.02	45.44	46.28	model | log
DeepLabV3	S-101-D8	512x512	160000	14.6	9.28	45.71	46.59	model | log
DeepLabV3+	S-101-D8	512x512	160000	16.2	11.96	46.47	47.27	model | log