Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm
Fuxiang Huang, Xiaowei Fu, Shiyu Ye, Lina Ma, Wen Li, Xinbo Gao, David D. Zhang, Lei Zhang
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 DART robustification | CDAN · Office-31 | adversarial accuracy (%): 34.7 -> 87.4 | Improved |
| add DART robustification | MCC · Office-31 | adversarial accuracy (%): 34.2 -> 88.1 | Improved |
| add DART robustification | MDD · Office-31 | adversarial accuracy (%): 36.0 -> 88.5 | Improved |
| DART instead of vanilla adversarial training (ablation) | CDAN · Office-31 | adversarial accuracy (%): 59.1 -> 87.4 | Improved |
| DART instead of vanilla adversarial training (ablation) | CDAN · Office-31 | clean accuracy (%): 69.9 -> 88.0 | Improved |
| DART instead of Trades (ablation) | MCC · Office-31 | adversarial accuracy (%): 58.9 -> 88.1 | Improved |
| add DART robustification, clean cost | CDAN · Office-31 | clean accuracy (%): 88.2 -> 88.0 | No clear effect |
| add DART robustification, clean cost | MCC · Office-Home | clean accuracy (%): 71.4 -> 70.0 | Mixed |
| add DART robustification | MCC · Office-Home | adversarial accuracy (%): 35.5 -> 69.2 | Improved |
| add DART robustification | CDAN · VisDA-2017 | adversarial accuracy (%): 48.6 -> 76.9 | Improved |
| add DART robustification, clean cost | MCC · VisDA-2017 | clean accuracy (%): 83.7 -> 80.1 | Hurt |
| add DART robustification | PL-Mix · Amazon Reviews | adversarial accuracy (%): 33.2 -> 58.9 | Improved |
Closest papers by meaning
- Adversarial Robustness for Unsupervised Domain Adaptation (ICCV 2021 · similarity 0.94)
- Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks (TPAMI 2021 · similarity 0.94)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.92)
- Adversarial Unsupervised Domain Adaptation With Conditional and Label Shift: Infer, Align and Iterate (ICCV 2021 · similarity 0.92)
- Toward Improving Robustness and Accuracy in Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.91)
- TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification (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.
