AI Paper Atlas

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

Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization

Zuyu Zhang, Ning Chen, Yongshan Liu, Qinghua Zhang, Xu Zhang

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 5 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
replace standard SGD with LE-guided LEAwareSGD (ablation)AdvST · PACSaverage accuracy (%): 67.06 -> 69.46Improved
replace Adam with LEAwareSGD (ablation)AdvST · PACSaverage accuracy (%): 66.43 -> 69.46Improved
replace RMSprop with LEAwareSGD (ablation)AdvST · PACSaverage accuracy (%): 62.34 -> 69.46Improved
add LEAwareSGD to ADAADA · PACSaverage accuracy (%): 61.62 -> 62.14Improved
add LEAwareSGD to ME-ADAME-ADA · PACSaverage accuracy (%): 60.22 -> 62.52Improved
add LEAwareSGD to AdvSTAdvST · PACSaverage accuracy (%): 67.06 -> 69.46Improved
add LEAwareSGD to ADAADA · OfficeHomeaverage accuracy (%): 44.75 -> 49.90Improved
add LEAwareSGD to ME-ADAME-ADA · OfficeHomeaverage accuracy (%): 45.35 -> 52.35Improved
add LEAwareSGD to AdvSTAdvST · OfficeHomeaverage accuracy (%): 52.60 -> 54.38Improved
compare with AdvST under 10% source dataLEAwareSGD+AdvST · PACS 10% dataaverage accuracy (%): 49.26 -> 58.73Improved
compare with AdvST under 50% source dataLEAwareSGD+AdvST · PACS 50% dataaverage accuracy (%): 60.18 -> 66.44Improved
compare with AdvST in multi-source leave-one-outLEAwareSGD+AdvST · PACS multi-sourceaverage accuracy (%): 81.05 -> 84.52No clear effect

Earlier methods this paper compares with

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