AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Pose2Seg: Detection Free Human Instance Segmentation

Song-Hai Zhang, Ruilong Li, Xin Dong, Paul Rosin, Zixi Cai, Xi Han, Dingcheng Yang, Haozhi Huang, Shi-Min Hu

CVPR 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 233 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
Replace detection-based Mask R-CNN with pose-based Pose2Seghuman instance segmentation · OCHuman valAP: 0.163 -> 0.222Improved
Replace detection-based Mask R-CNN with pose-based Pose2Seghuman instance segmentation · OCHuman testAP: 0.169 -> 0.238Improved
Replace detection-based Mask R-CNN with pose-based Pose2Seghuman instance segmentation · COCOPerson valAP: 0.532 -> 0.555Improved
Use ground-truth rather than predicted keypointsPose2Seg · OCHuman valAP: 0.222 -> 0.544Improved
Replace GT-box RoI-Align with pose-based Affine-Align (ablation)human instance segmentation · OCHuman valAP: 0.476 -> 0.544Improved
Add skeleton features to GT-box RoI-Align (ablation)human instance segmentation · COCOPerson valAP: 0.568 -> 0.648Improved
Add skeleton features to GT-box RoI-Align (ablation)human instance segmentation · OCHuman valAP: 0.133 -> 0.476Improved
Replace Affine-Align with keypoint-derived boxes and RoI-Align (ablation)Pose2Seg · OCHuman valAP: 0.544 -> 0.441Hurt
Increase SegModule residual units from 5 to 10 (ablation)Pose2Seg · COCOPerson valAP: 0.545 -> 0.555Improved
Increase SegModule residual units beyond 10 (ablation)Pose2Seg · COCOPerson valAP: 0.555 -> 0.555; 0.555 -> 0.556No clear effect
Use keypoint-derived boxes expanded by different amounts instead of Affine-Align (ablation)Pose2Seg · COCOPerson valAP: 0.431; 0.460; 0.477; 0.489; 0.497; 0.501; 0.500Mixed

Later papers that compared with this method

2 later accepted papers report Pose2Seg as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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