Task	Dataset	Model	Metric name	Metric value	Global rank
Nuclear Segmentation	Cell17	Mask R-CNN	F1-score	0.8004	# 3
Nuclear Segmentation	Cell17	Mask R-CNN	Dice	0.7070	# 3
Nuclear Segmentation	Cell17	Mask R-CNN	Hausdorff	12.6723	# 3
Instance Segmentation	Cityscapes	Mask R-CNN	Average Precision	26.2	# 2
Instance Segmentation	Cityscapes	Mask R-CNN + Coco	Average Precision	32.0	# 1
Keypoint Detection	COCO	Mask R-CNN	Validation AP	69.2	# 6
Keypoint Detection	COCO	Mask R-CNN	Test AP	63.1	# 7
Instance Segmentation	COCO	Mask R-CNN	Average Precision	37.1%	# 8
Object Detection	COCO minival	Mask R-CNN (ResNet-101-FPN)	box AP	35.4	# 47
Object Detection	COCO minival	Mask R-CNN (ResNet-101-FPN)	AP50	57.3	# 32
Object Detection	COCO minival	Mask R-CNN (ResNet-101-FPN)	AP75	37.5	# 35
Object Detection	COCO minival	Mask R-CNN (ResNeXt-101-FPN)	box AP	36.7	# 41
Object Detection	COCO minival	Mask R-CNN (ResNeXt-101-FPN)	AP50	59.5	# 20
Object Detection	COCO minival	Mask R-CNN (ResNeXt-101-FPN)	AP75	38.9	# 31
Object Detection	COCO minival	Mask R-CNN (ResNet-50-FPN)	box AP	33.6	# 49
Object Detection	COCO minival	Mask R-CNN (ResNet-50-FPN)	AP50	55.2	# 35
Object Detection	COCO minival	Mask R-CNN (ResNet-50-FPN)	AP75	35.3	# 36
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	box AP	38.2	# 44
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	AP50	60.3	# 36
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	AP75	41.7	# 43
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	APS	20.1	# 48
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	APM	41.1	# 38
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	APL	50.2	# 40
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	box AP	39.8	# 37
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	AP50	62.3	# 27
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	AP75	43.4	# 35
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	APS	22.1	# 38
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	APM	43.2	# 30
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	APL	51.2	# 37
Multi-Human Parsing	MHP v1.0	Mask R-CNN	AP 0.5	52.68%	# 2
Multi-Human Parsing	MHP v2.0	Mask R-CNN	AP 0.5	14.90%	# 3

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn/instance-segmentation-on-cityscapes)](https://paperswithcode.com/sota/instance-segmentation-on-cityscapes?p=mask-r-cnn)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn/multi-human-parsing-on-mhp-v10)](https://paperswithcode.com/sota/multi-human-parsing-on-mhp-v10?p=mask-r-cnn)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn/nuclear-segmentation-on-cell17)](https://paperswithcode.com/sota/nuclear-segmentation-on-cell17?p=mask-r-cnn)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn/multi-human-parsing-on-mhp-v20)](https://paperswithcode.com/sota/multi-human-parsing-on-mhp-v20?p=mask-r-cnn)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn/keypoint-detection-on-coco)](https://paperswithcode.com/sota/keypoint-detection-on-coco?p=mask-r-cnn)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn/instance-segmentation-on-coco)](https://paperswithcode.com/sota/instance-segmentation-on-coco?p=mask-r-cnn)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn/object-detection-on-coco)](https://paperswithcode.com/sota/object-detection-on-coco?p=mask-r-cnn)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn/object-detection-on-coco-minival)](https://paperswithcode.com/sota/object-detection-on-coco-minival?p=mask-r-cnn)`

Mask R-CNN

ICCV 2017 • Kaiming He • Georgia Gkioxari • Piotr Dollár • Ross Girshick

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance... (read more)

PDF Abstract

Code

Add Remove

tensorflow/models

57,559

facebookresearch/detectron

21,801

matterport/Mask_RCNN

13,974

facebookresearch/maskrcnn-benchmark

6,443

tensorpack/tensorpack

4,785

See all 70 implementations

Tasks

Add Remove

HUMAN PART SEGMENTATION

INSTANCE SEGMENTATION

KEYPOINT DETECTION

MULTI-HUMAN PARSING

NUCLEAR SEGMENTATION

OBJECT DETECTION

SEMANTIC SEGMENTATION

Evaluation results from the paper

Add Remove

SOTA for Instance Segmentation on Cityscapes (using extra training data)

Get a GitHub badge

Task	Dataset	Model	Metric name	Metric value	Global rank	Compare
Nuclear Segmentation	Cell17	Mask R-CNN	F1-score	0.8004	# 3	See all
Nuclear Segmentation	Cell17	Mask R-CNN	Dice	0.7070	# 3	See all
Nuclear Segmentation	Cell17	Mask R-CNN	Hausdorff	12.6723	# 3	See all
Instance Segmentation	Cityscapes	Mask R-CNN	Average Precision	26.2	# 2	See all
Instance Segmentation	Cityscapes	Mask R-CNN + Coco	Average Precision	32.0	# 1	See all
Keypoint Detection	COCO	Mask R-CNN	Validation AP	69.2	# 6	See all
Keypoint Detection	COCO	Mask R-CNN	Test AP	63.1	# 7	See all
Instance Segmentation	COCO	Mask R-CNN	Average Precision	37.1%	# 8	See all
Object Detection	COCO minival	Mask R-CNN (ResNet-101-FPN)	box AP	35.4	# 47	See all
Object Detection	COCO minival	Mask R-CNN (ResNet-101-FPN)	AP50	57.3	# 32	See all
Object Detection	COCO minival	Mask R-CNN (ResNet-101-FPN)	AP75	37.5	# 35	See all
Object Detection	COCO minival	Mask R-CNN (ResNeXt-101-FPN)	box AP	36.7	# 41	See all
Object Detection	COCO minival	Mask R-CNN (ResNeXt-101-FPN)	AP50	59.5	# 20	See all
Object Detection	COCO minival	Mask R-CNN (ResNeXt-101-FPN)	AP75	38.9	# 31	See all
Object Detection	COCO minival	Mask R-CNN (ResNet-50-FPN)	box AP	33.6	# 49	See all
Object Detection	COCO minival	Mask R-CNN (ResNet-50-FPN)	AP50	55.2	# 35	See all
Object Detection	COCO minival	Mask R-CNN (ResNet-50-FPN)	AP75	35.3	# 36	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	box AP	38.2	# 44	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	AP50	60.3	# 36	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	AP75	41.7	# 43	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	APS	20.1	# 48	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	APM	41.1	# 38	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNet-101-FPN)	APL	50.2	# 40	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	box AP	39.8	# 37	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	AP50	62.3	# 27	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	AP75	43.4	# 35	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	APS	22.1	# 38	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	APM	43.2	# 30	See all
Object Detection	COCO test-dev	Mask R-CNN (ResNeXt-101-FPN)	APL	51.2	# 37	See all
Multi-Human Parsing	MHP v1.0	Mask R-CNN	AP 0.5	52.68%	# 2	See all
Multi-Human Parsing	MHP v2.0	Mask R-CNN	AP 0.5	14.90%	# 3	See all

Mask R-CNN

Code Edit Add Remove

Tasks Edit Add Remove

Evaluation results from the paper Edit Add Remove

Code

Add Remove

Tasks

Add Remove

Evaluation results from the paper

Add Remove