Mask R-CNN

ICCV 2017 Kaiming HeGeorgia GkioxariPiotr DollárRoss 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


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Nuclear Segmentation Cell17 Mask R-CNN F1-score 0.8004 # 3
Dice 0.707 # 3
Hausdorff 12.6723 # 3
Panoptic Segmentation Cityscapes val Mask R-CNN+COCO PQth 54.0 # 12
Real-Time Object Detection COCO Mask R-CNN X-152-32x8d MAP 45.2 # 3
APbb75 45.2 # 1
Keypoint Detection COCO Mask R-CNN Validation AP 69.2 # 6
Test AP 63.1 # 8
Real-Time Object Detection COCO minival Mask R-CNN X-152-32x8d APbb75 45.2 # 1
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN) box AP 37.7 # 56
Object Detection COCO minival Mask R-CNN (ResNet-101-FPN) box AP 40.0 # 42
Object Detection COCO minival Mask R-CNN (ResNeXt-101-FPN) box AP 36.7 # 57
AP50 59.5 # 28
AP75 38.9 # 39
Real-Time Object Detection COCO minival Mask R-CNN X-101-FPN MAP 37.6 # 1
Keypoint Detection COCO test-challenge Mask R-CNN* AR 75.4 # 4
ARM 70.2 # 4
AP 68.9 # 5
AP50 89.2 # 4
AP75 75.2 # 4
APL 82.6 # 4
AR50 93.2 # 4
AR75 81.2 # 4
ARL 76.8 # 4
Instance Segmentation COCO test-dev Mask R-CNN (ResNeXt-101-FPN) mask AP 37.1 # 18
AP50 60.0 # 11
AP75 39.4 # 10
APS 16.9 # 12
APM 39.9 # 10
APL 53.5 # 7
Object Detection COCO test-dev Mask R-CNN (ResNeXt-101-FPN) box AP 39.8 # 55
AP50 62.3 # 40
AP75 43.4 # 52
APS 22.1 # 54
APM 43.2 # 48
APL 51.2 # 53
Pose Estimation COCO test-dev Mask-RCNN AP 63.1 # 10
AP50 87.3 # 7
AP75 68.7 # 10
APL 71.4 # 8
Keypoint Detection COCO test-dev Mask R-CNN APL 71.4 # 10
APM 57.8 # 12
AP50 87.3 # 9
AP75 68.7 # 11
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN) box AP 38.2 # 63
AP50 60.3 # 49
AP75 41.7 # 58
APS 20.1 # 64
APM 41.1 # 56
APL 50.2 # 58
Multi-Person Pose Estimation CrowdPose Mask R-CNN mAP @0.5:0.95 60.3 # 4
Multi-tissue Nucleus Segmentation Kumar Mask R-CNN (e) Dice 0.760 # 13
Hausdorff Distance (mm) 50.9 # 11
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 14.9% # 3
3D Instance Segmentation ScanNet(v2) Mask R-CNN [[He et al.2017]] Mean AP @ 0.5 5.8 # 9
Mean AP 5.8 # 1