AI RESEARCH
Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
arXiv CS.LG
•
ArXi:2605.23797v1 Announce Type: new Aiming at identifying unexpected inputs from unknown classes, out-of-distribution (OOD) detection has emerged as a pivotal approach to enhancing the reliability of machine learning models. This paper focuses on the burgeoning paradigm of post-hoc OOD detection with pre-trained vision-language models (VLMs), where a popular pipeline is to detect OOD inputs by examining their affinities between ID labels and negative labels, i.e., those semantically different from ID labels.