OntoAug: Rethinking Generative Data Augmentation via Ontology Guidance
OntoAug is an ontology-oriented data augmentation framework that explicitly distinguishes between subject and environment, and achieves strong performance across multiple tasks, including image classification, few-shot learning, weakly supervised object localization (WSOL), and large vision-language model reasoning.
Shuo Wang, Zhichuan Wang, Jun Luo
· 0 citations