Research map / Label-efficient and robust learning / Domain adaptation and generalization
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation
Fan Wang, Zhongyi Han, Zhiyan Zhang, Rundong He, Yilong Yin
Read the paperCheck 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 MHPL instead of ELPT for active source-free adaptation | ResNet-50 · Office-Home (12-task average, 5% labels) | accuracy (%): 79.3 vs. 77.0 | Improved |
| Use MHPL instead of ELPT for active source-free adaptation | ResNet-101 · VisDA-2017 (5% labels) | accuracy (%): 91.3 vs. 89.2 | Improved |
| Use MHPL instead of EADA | ResNet-50 · Office-31 (6-task average, 5% labels) | accuracy (%): 93.2 vs. 93.2 | No clear effect |
| Use MHPL instead of EADA | ResNet-50 · VisDA-2017 (5% labels) | accuracy (%): 88.3 ± 0.1 -> 89.6 ± 0.1 | Improved |
| Select MH points instead of LC points (ablation) | Office-Home, VGG16 · Office-Home (4-task average) | accuracy (%): 58.1 -> 60.3 | Improved |
| Select MH points instead of LC points (ablation) | Office-Home, ResNet-50 · Office-Home (4-task average) | accuracy (%): 67.3 -> 69.0 | Improved |
| Remove neighbor environment uncertainty (assign sample uncertainties randomly) (ablation) | MHPL · Office-Home Ar→Cl | accuracy (%) | Hurt |
| Remove neighbor diversity relaxation (ablation) | MHPL · Office-Home Ar→Cl | accuracy (%) | Hurt |
| Select samples at the fifth training epoch instead of one-shot querying with the source model (ablation) | MHPL · Office-Home Ar→Cl | accuracy (%) | Hurt |
| Use neighbor purity and neighbor affinity together rather than either alone (ablation) | MHPL neighbor environment uncertainty · Office-Home Ar→Cl | accuracy (%) | Improved |
| Replace MH points with randomly selected samples (ablation) | MHPL · Office-Home Ar→Cl | accuracy (%) | Hurt |
| Remove neighbor focal loss (ablation) | MHPL · Office-Home Ar→Cl | accuracy (%) | Hurt |
Later papers that compared with this method
2 later accepted papers report MHPL as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Unified Modality Separation: A Vision-Language Framework for Unsupervised Domain Adaptation (TPAMI 2025 · better on 1 of 1 shared result)
- Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence (ECCV 2024 · better on 1 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty Control (ICLR 2025 · similarity 0.90)
- Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering (TPAMI 2023 · similarity 0.89)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.89)
- Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation (NeurIPS 2021 · similarity 0.89)
- When Source-Free Domain Adaptation Meets Learning with Noisy Labels (ICLR 2023 · similarity 0.89)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.88)
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.
