Research map / Label-efficient and robust learning / Domain adaptation and generalization
Partial Domain Adaptation Without Domain Alignment
Weikai Li, Songcan Chen
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 JDA domain alignment term (ablation) | IDSP · Office-Home UDA closed-set | accuracy (%): 67.0 -> 68.0 | Improved |
| add JDA domain alignment term (ablation) | IDSP · Image-Clef UDA closed-set | accuracy (%): 87.9 -> 89.3 | Improved |
| add JDA domain alignment term (ablation) | IDSP · Office-Home PDA | accuracy (%): 74.9 -> 63.3 | Hurt |
| add JDA domain alignment term (ablation) | IDSP · Office-31 PDA | accuracy (%): 98.3 -> 89.3 | Hurt |
| remove domain alignment (IDSP) versus MEDA with manifold regularization plus alignment (ablation) | IDSP vs MEDA · Office-Home PDA | accuracy (%): 65.1 -> 74.9 | Improved |
| remove domain alignment (IDSP) versus MEDA (ablation) | IDSP vs MEDA · Office-31 PDA | accuracy (%): 90.7 -> 98.3 | Improved |
| add domain alignment (MEDA) versus IDSP (ablation) | MEDA vs IDSP · Office-Home UDA closed-set | accuracy (%): 67.0 -> 67.5 | No clear effect |
| add Laplacian structure preserving on target domain (gamma>0 instead of nP) (ablation) | IDSP · Office-Home, Image-Clef and Office-31 | accuracy (%) | Improved |
| also preserve source domain structure (ST or CST) instead of target only (ablation) | IDSP · UDA and PDA benchmarks | accuracy (%) | Hurt |
Closest papers by meaning
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.92)
- Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation (NeurIPS 2023 · similarity 0.91)
- Improving Unsupervised Domain Adaptation: A Pseudo-Candidate Set Approach (ECCV 2024 · similarity 0.91)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.91)
- Prior Knowledge Guided Unsupervised Domain Adaptation (ECCV 2022 · similarity 0.91)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · similarity 0.90)
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.
