Mask Scoring R-CNN

Introduction

@inproceedings{huang2019msrcnn,
    title={Mask Scoring R-CNN},
    author={Zhaojin Huang and Lichao Huang and Yongchao Gong and Chang Huang and Xinggang Wang},
    booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
    year={2019},
}

Results and Models

Backbone	style	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Download
R-50-FPN	caffe	1x	4.5		38.2	36.0	model | log
R-50-FPN	caffe	2x	-	-	38.8	36.3	model | log
R-101-FPN	caffe	1x	6.5		40.4	37.6	model | log
R-101-FPN	caffe	2x	-	-	41.1	38.1	model | log
R-X101-32x4d	pytorch	2x	7.9	11.0	41.8	38.7	model | log
R-X101-64x4d	pytorch	1x	11.0	8.0	43.0	39.5	model | log
R-X101-64x4d	pytorch	2x	11.0	8.0	42.6	39.5	model | log