AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

UDA-COPE: Unsupervised Domain Adaptation for Category-Level Object Pose Estimation

Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin, Jaesung Choe, Ukcheol Shin, In So Kweon, Kuk-Jin Yoon

CVPR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 55 citations (OpenAlex)

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
Train with unlabeled REAL data using the proposed pseudo-label adaptationUDA-COPE RGB · REAL2755°5cm: 18.3 -> 27.0 (+8.7)Improved
Train with unlabeled REAL data using the proposed pseudo-label adaptationUDA-COPE RGB · REAL2753D50: 79.9 -> 82.0 (+2.1)Improved
Add unlabeled REAL training data with rendered-depth self-supervisionCPS++ RGB · REAL2755°5cm: 25.8 -> 25.2 (-0.6)Hurt
Add momentum update to naive pseudo-label training (ablation)UDA-COPE · REAL2755°5cm: 28.2 -> 27.8Hurt
Add all-modality loss to pseudo-label training (ablation)UDA-COPE RGB-D · REAL2755°5cm: 28.2 -> 29.2Improved
Use xMUDA consistency instead of all-modality loss (ablation)UDA-COPE RGB-D · REAL2755°5cm: 28.2 -> 30.3Improved
Add bidirectional point filtering to pseudo-label training (ablation)UDA-COPE RGB-D · REAL2755°5cm: 29.2 -> 32.9Improved
Add teacher self-supervised learning using filtered depth points (ablation)UDA-COPE RGB-D · REAL2755°5cm: 32.9 -> 34.8 (+6.9)Improved
Use bidirectional point filtering instead of confidence, entropy, or prediction-agreement filtering (ablation)UDA-COPE · REAL2755°5cm: RGB: 25.0 -> 26.1; Depth: 26.1 -> 27.3; RGB-D: 30.3 -> 32.9Mixed

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