
提案された新しいOOD検出フレームワークは、CLIPを活用してIDライクな外れ値を発見し、プロンプト学習を行うことで、最も難しいOODサンプルを特定する能力を向上させます。


coremsg

id-like-prompt-learning-for-few-shot-out-of-distribution-detection-a-novel-approach-using-clip


ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection: A Novel Approach Using CLIP


title_rewrite


CLIP-driven Outliers Synthesis (CLIP-OS) synthesizes reliable out-of-distribution (OOD) supervised signals to enhance the separability between in-distribution (ID) and OOD samples in few-shot scenarios.


clip-driven-outlier-synthesis-for-effective-few-shot-out-of-distribution-detection


CLIP-Driven Outlier Synthesis for Effective Few-Shot Out-of-Distribution Detection
