Research map / Label-efficient and robust learning / Domain adaptation and generalization
Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds
Zicheng Wang, Zhen Zhao, Yiming Wu, Luping Zhou, Dong Xu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add progressive target-approaching (PTA) to TSFA + IDFA (ablation) | PCFEA · PointDA-10 | average accuracy (%): 68.6 -> 76.5 | Improved |
| combine TSFA and IDFA directly without intermediate domains (ablation) | PCFEA · PointDA-10 | average accuracy (%): 74.3 -> 68.6 | Hurt |
| add target-styled feature augmentation (TSFA) to DGCNN (ablation) | DGCNN baseline · PointDA-10 | average accuracy (%): 62.2 -> 74.3 | Improved |
| add IDFA alone to DGCNN (ablation) | DGCNN baseline · PointDA-10 | average accuracy (%): 62.2 -> 69.2 | Improved |
| add PTA to TSFA (ablation) | PCFEA · PointDA-10 | average accuracy (%): 74.3 -> 75.7 | Improved |
| add PTA to IDFA (ablation) | PCFEA · PointDA-10 | average accuracy (%): 69.2 -> 74.0 | Improved |
| add IDFA to TSFA + PTA (ablation) | PCFEA · PointDA-10 | average accuracy (%): 75.7 -> 76.5 | Improved |
| progressively decrease selected source samples (ablation) | PTA · PointDA-10 | average accuracy (%): 74.3 -> 75.4 | Improved |
| progressively increase selected target samples (ablation) | PTA · PointDA-10 | average accuracy (%): 74.3 -> 74.7 | Mixed |
| shorten intermediate domain stage length tau (more frequent updates) (ablation) | PCFEA · PointDA-10 | average accuracy (%) | Improved |
| PCFEA vs DAPS without pseudo-label fine-tuning | PCFEA · GraspNetPC-10 | average accuracy (%): 80.7 -> 87.6 | Improved |
Closest papers by meaning
- PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label (ICCV 2023 · similarity 0.89)
- Progressive Feature Alignment for Unsupervised Domain Adaptation (CVPR 2019 · similarity 0.88)
- Multi-Modal Assistance for Unsupervised Domain Adaptation on Point Cloud 3D Object Detection (AAAI 2026 · similarity 0.88)
- Structure-Aware Feature Fusion for Unsupervised Domain Adaptation (AAAI 2020 · similarity 0.88)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.86)
- DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion (AAAI 2025 · similarity 0.86)
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.
