mask_rcnn

Mask R-CNN

Introduction

@article{He_2017,
   title={Mask R-CNN},
   journal={2017 IEEE International Conference on Computer Vision (ICCV)},
   publisher={IEEE},
   author={He, Kaiming and Gkioxari, Georgia and Dollar, Piotr and Girshick, Ross},
   year={2017},
   month={Oct}
}

Results and models

Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Download
R-50-FPN	caffe	1x	4.3		38.0	34.4	model | log
R-50-FPN	pytorch	1x	4.4	16.1	38.2	34.7	model | log
R-50-FPN	pytorch	2x	-	-	39.2	35.4	model | log
R-101-FPN	caffe	1x			40.4	36.4	model | log
R-101-FPN	pytorch	1x	6.4	13.5	40.0	36.1	model | log
R-101-FPN	pytorch	2x	-	-	40.8	36.6	model | log
X-101-32x4d-FPN	pytorch	1x	7.6	11.3	41.9	37.5	model | log
X-101-32x4d-FPN	pytorch	2x	-	-	42.2	37.8	model | log
X-101-64x4d-FPN	pytorch	1x	10.7	8.0	42.8	38.4	model | log
X-101-64x4d-FPN	pytorch	2x	-	-	42.7	38.1	model | log
X-101-32x8d-FPN	pytorch	1x	-	-	42.8	38.3

Pre-trained Models

We also train some models with longer schedules and multi-scale training. The users could finetune them for downstream tasks.

Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Download
R-50-FPN	caffe	2x	4.3		40.3	36.5	model | log
R-50-FPN	caffe	3x	4.3		40.8	37.0	model | log
X-101-32x8d-FPN	pytorch	1x	-		43.6	39.0
X-101-32x8d-FPN	pytorch	3x	-		44.0	39.3