ResNeSt: Split-Attention Networks

Introduction

@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

Faster R-CNN

Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP	Config	Download
S-50-FPN	pytorch	1x	4.8	-	42.0	config	model | log
S-101-FPN	pytorch	1x	7.1	-	44.5	config	model | log

Mask R-CNN

Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Config	Download
S-50-FPN	pytorch	1x	5.5	-	42.6	38.1	config	model | log
S-101-FPN	pytorch	1x	7.8	-	45.2	40.2	config	model | log

Cascade R-CNN

Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP	Config	Download
S-50-FPN	pytorch	1x	-	-	44.5	config	model | log
S-101-FPN	pytorch	1x	8.4	-	46.8	config	model | log

Cascade Mask R-CNN

Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Config	Download
S-50-FPN	pytorch	1x	-	-	45.4	39.5	config	model | log
S-101-FPN	pytorch	1x	10.5	-	47.7	41.4	config	model | log