AI Paper Atlas

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

Incorporating Pre-Training Data Matters in Unsupervised Domain Adaptation

Yinsong Xu, Aidong Men, Yang Liu, Xiahai Zhuang, Qingchao Chen

TPAMI 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 4 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
add pre-training data cross-entropy loss Lp (ablation)SHOT · Office-Home Cl->Praccuracy: 78.2 -> 79.9Improved
add Lp (ablation)SHOT · Office-Home Cl->Araccuracy: 68.0 -> 69.4Improved
add intermediate-domain semantic loss Lsem alone (ablation)SHOT · Office-Home Cl->Praccuracy: 78.2 -> 79.9Improved
add Lsem on top of Lp (ablation)SHOT · Office-Home Cl->Praccuracy: 79.9 -> 81.2Improved
add feature interpolation loss Lfeat (ablation)SHOT with Lp and Lsem · Office-Home Cl->Praccuracy: 81.2 -> 81.3Improved
select WordNet-similar classes instead of all 1000 classes (ablation)TriDA+SHOT · Office-Homeaccuracy: 72.3 -> 73.5Improved
select classes by similarity instead of random (ablation)TriDA+SHOT · Office-Homeaccuracy: 72.6 -> 73.5Improved
vary Beta(alpha,alpha) mixing parameter from 0.5 to 4.0 (ablation)TriDA+SHOT · Office-Homeavg accuracy: 73.2 -> 73.5No clear effect
add TriDA to CDANCDAN · Office-Home (ResNet-50, UDA)accuracy: 68.8 -> 70.9Improved
add TriDA to MDDMDD · Office-Home (ResNet-50, UDA)accuracy: 69.7 -> 71.4Improved
add TriDA to SHOTSHOT · Office-Home (ResNet-50, SFUDA)accuracy: 71.8 -> 73.5Improved
add TriDA to CoWACoWA · Office-31 (ResNet-50)accuracy: 90.3 -> 90.3No clear effect

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