Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

6-2024

Abstract

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 out-lier 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.

Keywords

Out-of-Distribution detection, OOD detection, Open-vocabulary learning, Closed-vocabulary classification, Open-vocabulary classification

Discipline

Artificial Intelligence and Robotics | Computer Sciences

Research Areas

Data Science and Engineering; Intelligent Systems and Optimization

Publication

Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024) : Seattle, WA, USA, June 16-22

Identifier

10.1109/CVPR52733.2024.01665

Publisher

IEEE

City or Country

Seattle, USA

Additional URL

https://doi.org/10.1109/CVPR52733.2024.01665

Download

Share

COinS