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

Learning novel concepts, remembering previous knowledge, and adapting it to future tasks
occur simultaneously throughout a human's lifetime. To model such comprehensive abilities …

In this work, we address the Zero-Shot Domain Generalization (ZSDG) task, where the goal
is to learn a model from multiple source domains, such that it can generalize well to both …

Zero-shot domain generalization (ZSDG) simultaneously addresses the challenges of
dissimilar distribution and disjoint label-spaces of the training and test data in the context of …

Generalized zero-shot learning (GZSL) focuses on recognizing seen and unseen classes
against domain shift problem (DSP) where data of unseen classes may be misclassified as …

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 …

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 …