AI Paper Atlas

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

CVPR 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 26 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use MHPL instead of ELPT for active source-free adaptationResNet-50 · Office-Home (12-task average, 5% labels)accuracy (%): 79.3 vs. 77.0Improved
Use MHPL instead of ELPT for active source-free adaptationResNet-101 · VisDA-2017 (5% labels)accuracy (%): 91.3 vs. 89.2Improved
Use MHPL instead of EADAResNet-50 · Office-31 (6-task average, 5% labels)accuracy (%): 93.2 vs. 93.2No clear effect
Use MHPL instead of EADAResNet-50 · VisDA-2017 (5% labels)accuracy (%): 88.3 ± 0.1 -> 89.6 ± 0.1Improved
Select MH points instead of LC points (ablation)Office-Home, VGG16 · Office-Home (4-task average)accuracy (%): 58.1 -> 60.3Improved
Select MH points instead of LC points (ablation)Office-Home, ResNet-50 · Office-Home (4-task average)accuracy (%): 67.3 -> 69.0Improved
Remove neighbor environment uncertainty (assign sample uncertainties randomly) (ablation)MHPL · Office-Home Ar→Claccuracy (%)Hurt
Remove neighbor diversity relaxation (ablation)MHPL · Office-Home Ar→Claccuracy (%)Hurt
Select samples at the fifth training epoch instead of one-shot querying with the source model (ablation)MHPL · Office-Home Ar→Claccuracy (%)Hurt
Use neighbor purity and neighbor affinity together rather than either alone (ablation)MHPL neighbor environment uncertainty · Office-Home Ar→Claccuracy (%)Improved
Replace MH points with randomly selected samples (ablation)MHPL · Office-Home Ar→Claccuracy (%)Hurt
Remove neighbor focal loss (ablation)MHPL · Office-Home Ar→Claccuracy (%)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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy