Existing prompt learning methods have shown certain capabilities in
Out-of-Distribution (OOD) detection, but the lack of OOD images in the target
dataset in their training can lead to mismatches between OOD images and
In-Distribution (ID) categories, resulting in a high false positive rate. To
address this issue, we introduce a novel OOD detection method, named
'NegPrompt', to learn a set of negative prompts, each representing a negative
connotation of a given class label, for delineating the boundaries between ID
and OOD images. It learns such negative prompts with ID data only, without any
reliance on external outlier data. Further, current methods assume the
availability of samples of all ID classes, rendering them ineffective in
open-vocabulary learning scenarios where the inference stage can contain novel
ID classes not present during training. In contrast, our learned negative
prompts are transferable to novel class labels. Experiments on various ImageNet
benchmarks show that NegPrompt surpasses state-of-the-art prompt-learning-based
OOD detection methods and maintains a consistent lead in hard OOD detection in
closed- and open-vocabulary classification scenarios. Code is available at
this https URL

通过负面提示学习，在 ID 和 OOD 图像之间界定边界，以解决存在于开放词汇学习场景中的高误报率，超越了现有的基于提示学习的 OOD 检测方法，并在闭合和开放词汇分类场景中保持了一致优势。