AI RESEARCH
SHED: Style-Homogenized Embedding Alignment for Domain Generalization
arXiv CS.LG
•
ArXi:2605.16973v1 Announce Type: cross Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong generalization, their direct image-text embedding alignment suffers from inherent information asymmetry: images encode both class semantics and domain-specific styles, whereas text prompts primarily convey basic class cues. This asymmetry hinders generalization to novel domains in realistic scenarios.