Prompt learning has shown to be an efficient and effective fine-tuning method
for vision-language models like CLIP. While numerous studies have focused on
the generalisation of these models in few-shot classification, their capability
in near out-of-distribution (OOD) detection has been overlooked. A few recent
works have highlighted the promising performance of prompt learning in far OOD
detection. However, the more challenging task of few-shot near OOD detection
has not yet been addressed. In this study, we investigate the near OOD
detection capabilities of prompt learning models and observe that commonly used
OOD scores have limited performance in near OOD detection. To enhance the
performance, we propose a fast and simple post-hoc method that complements
existing logit-based scores, improving near OOD detection AUROC by up to 11.67%
with minimal computational cost. Our method can be easily applied to any prompt
learning model without change in architecture or re-training the models.
Comprehensive empirical evaluations across 13 datasets and 8 models demonstrate
the effectiveness and adaptability of our method.

我们研究了提示式学习模型在近似 OOD 检测中的能力，并观察到常用的 OOD 得分在此任务中表现有限。为了提升性能，我们提出了一种快速简单的后续方法，与现有的基于逻辑的得分相结合，将近似 OOD 检测的 AUROC 提高了最佳 11.67％，并具有最小的计算成本。我们的方法可以轻松应用于任何提示式学习模型，无需改变架构或重新训练模型。通过对 13 个数据集和 8 个模型进行全面的实证评估，证明了我们的方法的有效性和适应性。