PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization

arXiv:2404.09011v1 Announce Type: cross
Abstract: Domain Generalization (DG) aims to resolve distribution shifts between source and target domains, and current DG methods are default to the setting that data from source and target domains share identical categories. Nevertheless, there exists unseen classes from target domains in practical scenarios. To address this issue, Open Set Domain Generalization (OSDG) has emerged and several methods have been exclusively proposed. However, most existing methods adopt complex architectures with slight improvement compared with DG methods. …

abstract arxiv cs.cv cs.lg current data distillation distribution domain domains hybrid language language models practical type vision vision-language models