Debiased Negative Mining Improves OOD Detection with Pretrained Vision-Language Models
arXiv·low signal
Out-of-distribution detection using pretrained VLMs suffers from biased negative mining that conflates distribution shift with semantic novelty. This debiased approach separates the two signals, improving OOD detection accuracy for production ML systems that need to reliably flag inputs from unknown classes. Applicable to any CLIP-style VLM deployment without retraining the base model.