Abstract arge-scale foundation models, such as CLIP, have demonstrated impressive zero-
shot generalization performance on downstream tasks, leveraging well-designed language …

Universal Cross-Domain Retrieval (UCDR) retrieves relevant images from unseen domains
and classes without semantic labels, ensuring robust generalization. Existing methods …

For models to generalize under unseen domains (aka domain generalization), it is crucial to
learn feature representations that are domain-agnostic and capture the underlying …

Although supervised approaches for traffic sign classification have demonstrated excellent
performance, they are limited to classifying several traffic signs defined in the training …

Recent advances in pre-trained vision-language models, eg, CLIP, have demonstrated
remarkable success in domain generalization (DG) by tuning prompts. To promote DG, one …