AI Paper Atlas

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

CounterPC: Counterfactual Feature Realignment for Unsupervised Domain Adaptation on Point Clouds

Feng Yang, Yichao Cao, Xiu Su, Dan Niu, Xuanpeng Li

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 0 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
add self-supervised autoregressive generation (SSG) (ablation)PointGPT-S · PointDA-10 Avg.accuracy (%): 73.4 -> 73.9Improved
add counterfactual feature generation (CFG) (ablation)CounterPC-S · PointDA-10 Avg.accuracy (%): 73.9 -> 75.5Improved
add estimation of target domain distribution (ETD) (ablation)CounterPC-S · PointDA-10 Avg.accuracy (%): 75.5 -> 77.5Improved
add CFG to pseudo-label self-training (ablation)CounterPC-S · PointDA-10 M→Saccuracy (%): 85.72 -> 86.24Improved
add ETD to pseudo-label self-training (ablation)CounterPC-S · PointDA-10 M→Saccuracy (%): 85.72 -> 89.04Improved
add ETD to pseudo-label self-training (ablation)CounterPC-S · GraspNetPC-10 K→Raccuracy (%): 76.53 -> 83.74Improved
raise source CE weight from 0.5 to 2 (ablation)CounterPC-S · PointDA-10 M→Saccuracy (%): 86.54 -> 89.23Improved
raise source CE weight from 2 to 4 (ablation)CounterPC-S · PointDA-10 S→Maccuracy (%): 89.87 -> 86.54Hurt
raise source CD weight from 5 to 10 (ablation)CounterPC-S · PointDA-10 S→Maccuracy (%): 88.37 -> 85.47Hurt
raise target CE weight from 1 to 4 (ablation)CounterPC-S · PointDA-10 S→Maccuracy (%): 89.87 -> 86.72Hurt
raise target CD weight from 5 to 10 (ablation)CounterPC-S · PointDA-10 S→Maccuracy (%): 89.87 -> 86.30Hurt
CounterPC-S vs MLGR on PointDA-10CounterPC · PointDA-10 Avg.accuracy (%): 2.3 and 2.7Improved

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