AI Paper Atlas

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

Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm

Fuxiang Huang, Xiaowei Fu, Shiyu Ye, Lina Ma, Wen Li, Xinbo Gao, David D. Zhang, Lei Zhang

IJCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 8 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 DART robustificationCDAN · Office-31adversarial accuracy (%): 34.7 -> 87.4Improved
add DART robustificationMCC · Office-31adversarial accuracy (%): 34.2 -> 88.1Improved
add DART robustificationMDD · Office-31adversarial accuracy (%): 36.0 -> 88.5Improved
DART instead of vanilla adversarial training (ablation)CDAN · Office-31adversarial accuracy (%): 59.1 -> 87.4Improved
DART instead of vanilla adversarial training (ablation)CDAN · Office-31clean accuracy (%): 69.9 -> 88.0Improved
DART instead of Trades (ablation)MCC · Office-31adversarial accuracy (%): 58.9 -> 88.1Improved
add DART robustification, clean costCDAN · Office-31clean accuracy (%): 88.2 -> 88.0No clear effect
add DART robustification, clean costMCC · Office-Homeclean accuracy (%): 71.4 -> 70.0Mixed
add DART robustificationMCC · Office-Homeadversarial accuracy (%): 35.5 -> 69.2Improved
add DART robustificationCDAN · VisDA-2017adversarial accuracy (%): 48.6 -> 76.9Improved
add DART robustification, clean costMCC · VisDA-2017clean accuracy (%): 83.7 -> 80.1Hurt
add DART robustificationPL-Mix · Amazon Reviewsadversarial accuracy (%): 33.2 -> 58.9Improved

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