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


Evaluation results from the paper


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

     Get a GitHub badge
Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Compare
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
Object Detection COCO Mask R-CNN Bounding Box AP 39.8 # 28
Instance Segmentation COCO Mask R-CNN Average Precision 37.1% # 8
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