Research map / Label-efficient and robust learning / Domain adaptation and generalization
Divide and Adapt: Active Domain Adaptation via Customized Learning
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 |
|---|---|---|---|
| Use DiaNA active sampling and customized adaptation | Active domain adaptation · DomainNet AVG, 1k budget | accuracy: 43.8 -> 45.0 | Helped |
| Use DiaNA active sampling and customized adaptation | Active domain adaptation · DomainNet AVG, 2k budget | accuracy: 48.1 -> 50.2 | Helped |
| Use DiaNA active sampling and customized adaptation | Active domain adaptation · DomainNet AVG, 5k budget | accuracy: 53.9 -> 57.8 | Helped |
| Use DiaNA active sampling and customized adaptation | Active domain adaptation · Office-Home AVG, 5% budget | accuracy: 76.7 -> 77.7 | Helped |
| Add UI active sampling instead of random sampling (ablation) | DiaNA · Office-Home AVG, 5% budget | accuracy: 74.8 -> 77.7 | Helped |
| Add consistency regularization (ablation) | DiaNA · Office-Home AVG, 5% budget | accuracy: 76.9±0.3 -> 77.7±0.2 | Helped |
| Add conditional entropy loss (ablation) | DiaNA · Office-Home AVG, 5% budget | accuracy: 75.8±0.3 -> 77.7±0.2 | Helped |
| Add GMM-based adaptive data partitioning (ablation) | DiaNA · Office-Home AVG, 5% budget | accuracy: 74.0±0.2 -> 77.7±0.2 | Helped |
| Select UI rather than UC for annotation (ablation) | DiaNA sampling strategy · Office-Home AVG, 5% budget | accuracy: 68.3±0.6 -> 72.1±0.4 | Helped |
| Select UI rather than CI for annotation (ablation) | DiaNA sampling strategy · Office-Home AVG, 5% budget | accuracy: 66.4±0.8 -> 72.1±0.4 | Helped |
| Select UI rather than CC for annotation (ablation) | DiaNA sampling strategy · Office-Home AVG, 5% budget | accuracy: 63.0±0.3 -> 72.1±0.4 | Helped |
Closest papers by meaning
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (CVPR 2024 · similarity 0.93)
- Category-Aware Active Domain Adaptation (ICML 2024 · similarity 0.90)
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · similarity 0.89)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.88)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.87)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 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.