Research map / Label-efficient and robust learning / Domain adaptation and generalization
Transferable Query Selection for Active Domain Adaptation
Bo Fu, Zhangjie Cao, Jianmin Wang, Mingsheng Long
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 TQS instead of ADMA for selecting target samples with a 5% labeling budget | active domain adaptation · Office-31 | accuracy (%): 89.4±0.3 -> 91.1±0.3 | Improved |
| use TQS instead of ADMA for selecting target samples with a 5% labeling budget | active domain adaptation · Office-Home | accuracy (%): 68.6±0.3 -> 70.5±0.3 | Improved |
| use TQS instead of ADMA for selecting target samples with a 5% labeling budget | active domain adaptation · VisDA-2017 | accuracy (%): 81.4±0.4 -> 83.1±0.4 | Improved |
| add transferable committee to TQS (ablation) | TQS · Office-31 | accuracy | Improved |
| add transferable uncertainty to TQS (ablation) | TQS · Office-31 | accuracy | Improved |
| add transferable domainness to TQS (ablation) | TQS · Office-31 | accuracy | Improved |
| use min-max adversarial optimization for the committee (ablation) | TQS · Office-31 | accuracy | Improved |
| use transferable uncertainty rather than single-classifier entropy (ablation) | TQS · Office-31 | accuracy | Improved |
| use transferable domainness rather than domain similarity (ablation) | TQS · Office-31 | accuracy | Improved |
| use an ensemble of classifiers for uncertainty estimation (ablation) | TQS · Office-31 | accuracy | Improved |
| use margin rather than entropy as the uncertainty function (ablation) | TQS · Office-31 | accuracy | Improved |
| use randomized selection to diversify selected target samples (ablation) | TQS · Office-31 | accuracy | Improved |
Closest papers by meaning
- Divide and Adapt: Active Domain Adaptation via Customized Learning (CVPR 2023 · similarity 0.90)
- Prototype-Driven Active Domain Adaptation with Density Consideration (AAAI 2026 · similarity 0.89)
- Category-Aware Active Domain Adaptation (ICML 2024 · similarity 0.89)
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (CVPR 2024 · similarity 0.89)
- Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline (NeurIPS 2024 · similarity 0.89)
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 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.
