Research map / Label-efficient and robust learning / Domain adaptation and generalization
Towards Better Robustness against Common Corruptions for Unsupervised Domain Adaptation
Zhiqiang Gao, Kaizhu Huang, Rui Zhang, Dawei Liu, Jieming Ma
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 image discretization to DDAR (ablation) | CDAN+MCC+DDAR · Office-31 corrupted | mCE: 36.8 -> 30.5 | Improved |
| add adversarial perturbation to image discretization (ablation) | CDAN+MCC+DDAR · Office-31 corrupted | mCE: 33.8 -> 30.5 | Improved |
| add Gaussian random start for adversarial data (ablation) | CDAN+MCC+DDAR · Office-31 corrupted | mCE: 31.7 -> 30.5 | No clear effect |
| use Wasserstein regularization instead of KL or CDAN loss (ablation) | DDAR with discriminator adversarial generation · Office-31 corrupted | mCE: 38.9 -> 29.8 | Improved |
| generate adversarial data with discriminator instead of KL loss (ablation) | DDAR · Office-31 corrupted | mCE: 30.3 -> 29.8 | Improved |
| add DDAR to MCC+CDAN | MCC+CDAN · VisDA-2017 | mCE: 65.8 -> 55.6 | Improved |
| add DDAR to MCC on VisDA-2017 | MCC · VisDA-2017 | accuracy (%): 77.0 -> 66.8 | Hurt |
| add DDAR to MCC+CDAN on Office-31 | MCC+CDAN · Office-31 | accuracy (%): 89.6 -> 88.9 | Hurt |
| use pixel-space instead of discretized adversarial data (ablation) | DDAR · Office-31 corrupted | mCE: 30.5 -> 36.8 | Hurt |
| apply DDAR on top of Tent (epoch 1) | CDAN+MCC+Tent · Office-31 corrupted | mCE: 30.5 -> 25.4 | Improved |
Closest papers by meaning
- Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm (IJCV 2025 · similarity 0.91)
- Adversarial Robustness for Unsupervised Domain Adaptation (ICCV 2021 · similarity 0.90)
- RDA: Robust Domain Adaptation via Fourier Adversarial Attacking (ICCV 2021 · similarity 0.89)
- Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks (TPAMI 2021 · similarity 0.89)
- Toward Improving Robustness and Accuracy in Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.87)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.87)
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.
