Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unified Optimal Transport Framework for Universal Domain Adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 L_global and L_local (PCD) on top of L_CCD (ablation) | UniOT · Office-Home (12 tasks) | H-score (%): 69.73 -> 76.57 | Helped |
| Add L_global to L_CCD + L_local (ablation) | UniOT · Office-Home (12 tasks) | H-score (%): 71.40 -> 76.57 | Helped |
| Add L_local to L_CCD + L_global (ablation) | UniOT · Office-Home (12 tasks) | H-score (%): 76.07 -> 76.57 | Helped |
| Add L_CCD to L_global + L_local (ablation) | UniOT · Office (6 tasks) | H-score (%): 79.74 -> 91.13 | Helped |
| Use adaptive filling in CCD (ablation) | UniOT · Office-Home (12 tasks) | H-score (%): 72.65 -> 76.57 | Helped |
| Use adaptive filling in CCD (ablation) | UniOT · Office (6 tasks) | H-score (%): 89.86 -> 91.13 | Helped |
| Replace local-neighbor loss with SwAV loss (ablation) | UniOT · VisDA | H-score (%): 57.32 -> 44.57 | Hurt |
| Replace L_PCD with SimSiam loss (ablation) | UniOT · VisDA | H-score (%): 57.32 -> 53.49 | Hurt |
| Disable adaptive update of marginal vector (mu=1) (ablation) | UniOT · Office | H-score (%) | Hurt |
| Vary rough boundary gamma and loss weight lambda (0.1 to 0.5) (ablation) | UniOT · Office / Office-Home | H-score (%) | No clear effect |
| Use UniOT instead of DCC (best prior on Office-Home) | UniDA methods · Office-Home (12 tasks) | H3-score (%): 61.66 -> 70.84 | Helped |
Closest papers by meaning
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · similarity 0.91)
- Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation (ICML 2025 · similarity 0.91)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.91)
- LEAD: Learning Decomposition for Source-free Universal Domain Adaptation (CVPR 2024 · similarity 0.90)
- Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation (AAAI 2025 · similarity 0.89)
- Distinguish Then Exploit: Source-free Open Set Domain Adaptation via Weight Barcode Estimation and Sparse Label Assignment (CVPR 2025 · similarity 0.89)
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.