AI RESEARCH

Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs

arXiv CS.CV

ArXi:2603.02618v2 Announce Type: replace Out-of-distribution (OOD) detection seeks to identify samples from unknown classes, a critical capability for deploying machine learning models in open-world scenarios. Recent research has nstrated that Vision-Language Models (VLMs) can effectively leverage their multi-modal representations for OOD detection. However, current methods often incorporate intra-modal distance during OOD detection, such as comparing negative texts with ID labels or comparing test images with image proxies.