Learning Transferable Negative Prompts for Out-of-Distribution Detection
This addresses the issue of high false positive rates in OOD detection for computer vision, particularly in open-vocabulary scenarios, though it is an incremental improvement over existing prompt-learning methods.
The paper tackles the problem of Out-of-Distribution (OOD) detection by introducing NegPrompt, a method that learns transferable negative prompts from In-Distribution data only, achieving state-of-the-art performance on ImageNet benchmarks with consistent leads in hard OOD detection.
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 https://github.com/mala-lab/negprompt.