CLIP-driven Outliers Synthesis for few-shot OOD detection

arXiv:2404.00323v1 Announce Type: cross
Abstract: Few-shot OOD detection focuses on recognizing out-of-distribution (OOD) images that belong to classes unseen during training, with the use of only a small number of labeled in-distribution (ID) images. Up to now, a mainstream strategy is based on large-scale vision-language models, such as CLIP. However, these methods overlook a crucial issue: the lack of reliable OOD supervision information, which can lead to biased boundaries between in-distribution (ID) and OOD. To tackle this problem, we propose …

abstract arxiv clip cs.cv cs.lg detection distribution few-shot however images language language models outliers scale small strategy synthesis training type vision vision-language models