SOURCE-LINKED INTELLIGENCE

PAPT++: Risk-Aware Adversarial Tuning and Generation for Single Domain Generalization

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Single domain generalization (SDG) aims to learn a model from one labeled source domain that generalizes to unseen target domains. A common strategy is to enrich the source distribution with augmented or generated samples, and recent text-to-image (T2I) diffusion models provide a strong generative prior for this purpose. However, diversity alone is insufficient for robust generalization, because useful generated samples should also capture variations that the current classifier finds difficult. Motivated by distributionally robust optimization (DRO), we define a semantic ambiguity set in the c

Read original source ↗ Open in workspace

recordType

paper

region

Global