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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace standard SGD with LE-guided LEAwareSGD (ablation) | AdvST · PACS | average accuracy (%): 67.06 -> 69.46 | Improved |
| replace Adam with LEAwareSGD (ablation) | AdvST · PACS | average accuracy (%): 66.43 -> 69.46 | Improved |
| replace RMSprop with LEAwareSGD (ablation) | AdvST · PACS | average accuracy (%): 62.34 -> 69.46 | Improved |
| add LEAwareSGD to ADA | ADA · PACS | average accuracy (%): 61.62 -> 62.14 | Improved |
| add LEAwareSGD to ME-ADA | ME-ADA · PACS | average accuracy (%): 60.22 -> 62.52 | Improved |
| add LEAwareSGD to AdvST | AdvST · PACS | average accuracy (%): 67.06 -> 69.46 | Improved |
| add LEAwareSGD to ADA | ADA · OfficeHome | average accuracy (%): 44.75 -> 49.90 | Improved |
| add LEAwareSGD to ME-ADA | ME-ADA · OfficeHome | average accuracy (%): 45.35 -> 52.35 | Improved |
| add LEAwareSGD to AdvST | AdvST · OfficeHome | average accuracy (%): 52.60 -> 54.38 | Improved |
| compare with AdvST under 10% source data | LEAwareSGD+AdvST · PACS 10% data | average accuracy (%): 49.26 -> 58.73 | Improved |
| compare with AdvST under 50% source data | LEAwareSGD+AdvST · PACS 50% data | average accuracy (%): 60.18 -> 66.44 | Improved |
| compare with AdvST in multi-source leave-one-out | LEAwareSGD+AdvST · PACS multi-source | average accuracy (%): 81.05 -> 84.52 | No 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.
- AdvST — AdvST: Revisiting Data Augmentations for Single Domain Generalization (AAAI 2024) · better on 11 of 11 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
- Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization (AAAI 2024 · similarity 0.87)
- Generalization at the Edge of Stability (NeurIPS 2026 · similarity 0.87)
- AdvST: Revisiting Data Augmentations for Single Domain Generalization (AAAI 2024 · similarity 0.87)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.87)
- Continuous Domain Generalization (NeurIPS 2025 · similarity 0.86)
- Enhancing Evolving Domain Generalization through Dynamic Latent Representations (AAAI 2024 · similarity 0.86)
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.
