Research map / Label-efficient and robust learning / Domain adaptation and generalization
How Does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?
Li Zhong, Zhen Fang, Feng Liu, Jie Lu, Bo Yuan, Guangquan Zhang
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 the combined-risk proxy | DAN · Office-Home | average accuracy: 64.7 -> 68.6 | Improved |
| Add the combined-risk proxy | DANN · Office-Home | average accuracy: 61.3 -> 66.8 | Improved |
| Add the combined-risk proxy | CDAN+E · Office-Home | average accuracy: 65.2 -> 67.8 | Improved |
| Add the combined-risk proxy | SymNets · Office-Home | average accuracy: 67.2 -> 68.2 | Improved |
| Use target augmentation without mixup (ablation) | E-MixNet · Image-CLEF | average accuracy: 89.9 vs 91.0 | Hurt |
| Use target augmentation with mixup but no source augmentation (ablation) | E-MixNet · Image-CLEF | average accuracy: 90.2 vs 91.0 | Hurt |
| Replace e-mixup with mixup (ablation) | E-MixNet · Image-CLEF | average accuracy: 90.8 vs 91.0 | Hurt |
| Add source augmentation to target augmentation with mixup (ablation) | E-MixNet · Image-CLEF | average accuracy: 90.2 -> 90.8 | Improved |
Closest papers by meaning
- Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation (ICLR 2026 · similarity 0.90)
- Unsupervised Multi-Source Domain Adaptation Without Access to Source Data (CVPR 2021 · similarity 0.88)
- Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation (NeurIPS 2023 · similarity 0.88)
- Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning (NeurIPS 2021 · similarity 0.88)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.87)
- Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline (NeurIPS 2024 · 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.
