Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jung, Myong Chol, Dipnall, Joanna, Gabbe, Belinda, Zhao, He
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914464292405248
author Jung, Myong Chol
Dipnall, Joanna
Gabbe, Belinda
Zhao, He
author_facet Jung, Myong Chol
Dipnall, Joanna
Gabbe, Belinda
Zhao, He
contents Prompt learning has emerged as an efficient and effective method for fine-tuning vision-language models such as CLIP. While many studies have explored generalisation abilities of these models in few-shot classification tasks and a few studies have addressed far out-of-distribution (OOD) of the models, their potential for addressing near OOD detection remains underexplored. Existing methods either require training from scratch, need fine-tuning, or are not designed for vision-language prompt learning. To address this, we introduce the Contrastive Logit Score (CLS), a novel post-hoc, plug-and-play scoring function. CLS significantly improves near OOD detection of pre-trained vision-language prompt learning methods without modifying their model architectures or requiring retraining. Our method achieves up to an 11.67% improvement in AUROC for near OOD detection with minimal computational overhead. Extensive evaluations validate the effectiveness, efficiency, and generalisability of our approach. Our code is available at https://github.com/davidmcjung/near-OOD-prompt-learning.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16091
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score
Jung, Myong Chol
Dipnall, Joanna
Gabbe, Belinda
Zhao, He
Computer Vision and Pattern Recognition
Prompt learning has emerged as an efficient and effective method for fine-tuning vision-language models such as CLIP. While many studies have explored generalisation abilities of these models in few-shot classification tasks and a few studies have addressed far out-of-distribution (OOD) of the models, their potential for addressing near OOD detection remains underexplored. Existing methods either require training from scratch, need fine-tuning, or are not designed for vision-language prompt learning. To address this, we introduce the Contrastive Logit Score (CLS), a novel post-hoc, plug-and-play scoring function. CLS significantly improves near OOD detection of pre-trained vision-language prompt learning methods without modifying their model architectures or requiring retraining. Our method achieves up to an 11.67% improvement in AUROC for near OOD detection with minimal computational overhead. Extensive evaluations validate the effectiveness, efficiency, and generalisability of our approach. Our code is available at https://github.com/davidmcjung/near-OOD-prompt-learning.
title Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.16091