AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence

Mengyao Lyu, Tianxiang Hao, Xinhao Xu, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 6 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 contrastive active sampling (CAS) margin instead of vanilla BvSB (ablation)LFTL · VisDA-C 1% budgetaccuracy (%): 85.1 -> 86.7Improved
Add class-level transferability term to the sampling criterion (ablation)LFTL CAS · VisDA-C 1% budgetaccuracy (%): 86.7 -> 86.9Improved
Add anchor-based clustering loss L_ac (ablation)LFTL · VisDA-C 1% budgetaccuracy (%): 86.9 -> 87.0Improved
Replace L_ac with visual-persistence-guided L_vpa (EMA anchor features) (ablation)LFTL · Office-31 5% budgetaccuracy (%): 92.0 -> 93.5Improved
Replace L_ac with L_vpa (ablation)LFTL · VisDA-C 1% budgetaccuracy (%): 87.0 -> 87.4Improved
Use CAS instead of other active learning criteria (Random, entropy, K-means, etc.) (ablation)LFTL · VisDA-C 1% budget, 10 roundsaccuracy (%): 85.1 (BvSB) -> 87.4Improved
Sample with entropy-min instead of random (ablation)Active learning baselines · VisDA-C 1% budget, 10 roundsaccuracy (%): 82.7 -> 63.9Hurt
Plug CAS sampling into SHOT with 1% labelsSHOT · VisDA-Caccuracy (%): 85.5 -> 86.4Improved
Plug CAS sampling into SHOT++ with 1% labelsSHOT++ · VisDA-Caccuracy (%): 87.3 -> 87.5No clear effect
Remove source data loss from LADA (SF-LADA) instead of using hypothesis transfer (ablation)LADA · source-free comparisonaccuracyHurt
Add source cross-entropy loss to LFTL (S-LFTL) (ablation)LFTL · Office datasetsaccuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most 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

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