Research map / Label-efficient and robust learning / Domain adaptation and generalization
Universal Domain Adaptation
Kaichao You, Mingsheng Long, Zhangjie Cao, Jianmin Wang, Michael I. Jordan
Check 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 |
|---|---|---|---|
| use sample-level transferability weighting with domain similarity and prediction uncertainty | UAN · Office-Home (ξ = 0.15) | average class accuracy (%): 73.39 -> 77.02 | Improved |
| use sample-level transferability weighting with domain similarity and prediction uncertainty | UAN · Office-31 (ξ = 0.32) | average class accuracy (%): 86.68 -> 89.24 | Improved |
| use sample-level transferability weighting with domain similarity and prediction uncertainty | UAN · ImageNet-Caltech (ξ = 0.07), I → C | average class accuracy (%): 72.19 -> 75.28 | Improved |
| use sample-level transferability weighting with domain similarity and prediction uncertainty | UAN · ImageNet-Caltech (ξ = 0.07), C → I | average class accuracy (%): 67.36 -> 70.17 | Improved |
| use sample-level transferability weighting with domain similarity and prediction uncertainty | UAN · VisDA2017 (ξ = 0.50) | average class accuracy (%): 58.72 -> 60.83 | Improved |
| add domain similarity to the sample-level transferability criterion (ablation) | UAN · Office-Home (ξ = 0.15) | average class accuracy (%): 75.39 -> 77.02 | Improved |
| add prediction uncertainty to the sample-level transferability criterion (ablation) | UAN · Office-Home (ξ = 0.15) | average class accuracy (%): 72.91 -> 77.02 | Improved |
Closest papers by meaning
- Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation (IJCV 2023 · similarity 0.92)
- Active Universal Domain Adaptation (ICCV 2021 · similarity 0.91)
- Learning to Detect Open Classes for Universal Domain Adaptation (ECCV 2020 · similarity 0.91)
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · similarity 0.91)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.90)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · 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.
