AI Paper Atlas

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

Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo

Jiangbo Pei, Ruizhe Li, Aidong Men, Yang Liu, Xiahai Zhuang, Qingchao Chen

TPAMI 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 3 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
allow multi-architecture source model zoos (Zoo-MSFDA) instead of one model per domainDECISION · Office-Homeaccuracy: 75.5 -> 81.6Improved
add SIM adaptation to the selected ensembleSEA ensemble (Ours-tf) · Office-Homeaccuracy: 90.7 -> 91.8Improved
add SIM adaptation to the selected ensembleSEA ensemble (Ours-tf) · DomainNetaccuracy: 59.1 -> 62.3Improved
use SUTE instead of NMI in selection and ensemble (ablation)SEA · Office-Homeaccuracy: 85.7 -> 91.8Improved
use SUTE instead of LEEP* in selection and ensemble (ablation)SEA · Office-31accuracy: 68.2 -> 94.9Improved
add diversity-based selection (ablation)SEA · Office-Homeaccuracy: 90.4 -> 91.8Improved
add diversity-based selection (ablation)SEA · Office-31accuracy: 94.5 -> 94.9Improved
use SUTE-based ensemble weights instead of learnable weights (ablation)SEA · Office-Homeaccuracy: 91.1 -> 91.8Improved
add L_pse loss (ablation)SEA · Office-Homeaccuracy: 89.9 -> 91.8Improved
add Outlier Knowledge Recycle loss L_omr (ablation)SEA · Office-31accuracy: 94.1 -> 94.9Improved
use Separate Information Maximization L_sim instead of L_cim (ablation)SEA · Office-Homeaccuracy: 91.3 -> 91.8Improved
add semantics consistency indicator (ablation)SUTE · Office-HomeSpearman correlation: 0.72 -> 0.94Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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