3 accepted papers
In cross-domain visual understanding tasks, models often achieve strong performance on the source domain but suffer severe degradation when applied to target domains with substantial distribution shifts. This challenge is particularly prominent under the zero-shot domain adaptation setting, where ad…
Attribute-based Zero-Shot Learning (ZSL) has revolutionized the ability of models to recognize new classes not seen during training. However, with the advancement of large-scale models, the expectations have risen. Beyond merely achieving zero-shot generalization, there is a growing demand for unive…
Compositional Zero-Shot Learning (CZSL) aims to transfer knowledge from seen state-object pairs to novel unseen pairs. In this process, visual bias caused by the diverse interrelationship of state-object combinations blurs their visual features, hindering the learning of distinguishable class protot…