AI Paper Atlas

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

GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts

Haoran Geng, Helin Xu, Chengyang Zhao, Chao Xu, Li Yi, Siyuan Huang, He Wang

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 77 citations (OpenAlex)

Read the paperCheck 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
Use GAPartNet domain-generalizable segmentation3D part segmentation · GAPartNet seen and unseen categoriesAP50: 76.5 vs 68.8 (seen); 37.2 vs 27.7 (unseen)Improved
Use domain-invariant perception with GAPart posesPart pose estimation · GAPartNet unseen categories3D mIoU: 36.3 -> 40.6Improved
Use GAPart-pose-based manipulation heuristicsCross-category manipulation · SAPIEN unseen drawer, door, handle, and button taskssuccess rate: drawer 90.0; door 55.0; handle 85.0; button 95.0Improved
add domain adversarial learning (ablation)GAPart segmentation · Seen categoriesAP50: 71.1 -> 70.6Hurt
add domain adversarial learning (ablation)GAPart segmentation · Unseen categoriesAP50: 28.1 -> 29.8Improved
add part-oriented feature query (ablation)Domain-adversarial GAPart segmentation · Seen categoriesAP50: 70.6 -> 71.6Improved
add part-oriented feature query (ablation)Domain-adversarial GAPart segmentation · Unseen categoriesAP50: 29.8 -> 32.3Improved
add multi-resolution features (ablation)Part-oriented adversarial GAPart segmentation · Seen categoriesAP50: 71.6 -> 73.7Improved
add multi-resolution features (ablation)Part-oriented adversarial GAPart segmentation · Unseen categoriesAP50: 32.3 -> 35.0Improved
add distribution-balancing focal loss (ablation)Part-oriented multi-resolution adversarial GAPart segmentation · Seen categoriesAP50: 73.7 -> 76.5Improved
add distribution-balancing focal loss (ablation)Part-oriented multi-resolution adversarial GAPart segmentation · Unseen categoriesAP50: 35.0 -> 37.2Improved

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