AI Paper Atlas

Research map / Detection and segmentation / CNN features

Mask Scoring R-CNN

Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, Xinggang Wang

CVPR 2019 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 1,092 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add a MaskIoU head to calibrate mask confidenceMask R-CNN with ResNet-18/50/101 FPN · COCO 2017 valAP_m: 27.7 -> 29.3; 34.5 -> 36.0; 36.6 -> 38.2Improved
Add a MaskIoU head to calibrate mask confidenceMask R-CNN with ResNet-18/50/101 FPN · COCO 2017 valAP_m@0.75: 29.0 -> 31.3; 36.7 -> 38.8; 39.0 -> 41.5Improved
Add a MaskIoU headMask R-CNN with ResNet-101 · COCO 2017 valAP_m: 33.9 -> 35.0; 36.6 -> 38.2; 37.7 -> 39.1Improved
Add a MaskIoU head and calibrate mask scoreMask R-CNN · COCO 2017 test-devAP: 34.3 -> 35.4; 37.0 -> 38.3; 38.4 -> 39.6Improved
Use target mask concatenated with RoI features rather than target-mask multiplication (ablation)MaskIoU head · COCO 2017 valAP: 29.1 -> 29.3Improved
Use target mask concatenated with RoI features rather than all class masks concatenated with RoI (ablation)MaskIoU head · COCO 2017 valAP: 29.1 -> 29.3Improved
Use target mask with standard RoI features rather than high-resolution RoI features (ablation)MaskIoU head · COCO 2017 valAP: 29.1 -> 29.3Improved
Regress MaskIoU for the target category only instead of all categories, including absent ones (ablation)MaskIoU head · COCO 2017 valAP: 24.5 -> 29.3Improved
Regress MaskIoU for the target category only instead of all positive categories (ablation)MaskIoU head · COCO 2017 valAP: 28.2 -> 29.3Improved
Train on all examples rather than filtering to MaskIoU above 0.3 (ablation)MaskIoU head · COCO 2017 valAP: 29.2 -> 29.3Improved
Train on all examples rather than filtering to MaskIoU above 0.5 (ablation)MaskIoU head · COCO 2017 valAP: 29.0 -> 29.3Improved
Train on all examples rather than filtering to MaskIoU above 0.7 (ablation)MaskIoU head · COCO 2017 valAP: 28.8 -> 29.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy