Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Haoran, Liu, Yanlin, Tong, Zizhao, Li, Jiaze, Fu, Kexue, Zhang, Yuyang, Gao, Longxiang, Li, Shuaiguang, Li, Xingyu, Xu, Yanran, Wang, Changwei
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.14052
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908776471199744
author Xu, Haoran
Liu, Yanlin
Tong, Zizhao
Li, Jiaze
Fu, Kexue
Zhang, Yuyang
Gao, Longxiang
Li, Shuaiguang
Li, Xingyu
Xu, Yanran
Wang, Changwei
author_facet Xu, Haoran
Liu, Yanlin
Tong, Zizhao
Li, Jiaze
Fu, Kexue
Zhang, Yuyang
Gao, Longxiang
Li, Shuaiguang
Li, Xingyu
Xu, Yanran
Wang, Changwei
contents Out-of-Distribution (OOD) detection is a critical task that has garnered significant attention. The emergence of CLIP has spurred extensive research into zero-shot OOD detection, often employing a training-free approach. Current methods leverage expert knowledge from large language models (LLMs) to identify potential outliers. However, these approaches tend to over-rely on knowledge in the text space, neglecting the inherent challenges involved in detecting out-of-distribution samples in the image space. In this paper, we propose a novel pipeline, MM-OOD, which leverages the multimodal reasoning capabilities of MLLMs and their ability to conduct multi-round conversations for enhanced outlier detection. Our method is designed to improve performance in both near OOD and far OOD tasks. Specifically, (1) for near OOD tasks, we directly feed ID images and corresponding text prompts into MLLMs to identify potential outliers; and (2) for far OOD tasks, we introduce the sketch-generate-elaborate framework: first, we sketch outlier exposure using text prompts, then generate corresponding visual OOD samples, and finally elaborate by using multimodal prompts. Experiments demonstrate that our method achieves significant improvements on widely used multimodal datasets such as Food-101, while also validating its scalability on ImageNet-1K.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14052
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Vision Also You Need: Navigating Out-of-Distribution Detection with Multimodal Large Language Model
Xu, Haoran
Liu, Yanlin
Tong, Zizhao
Li, Jiaze
Fu, Kexue
Zhang, Yuyang
Gao, Longxiang
Li, Shuaiguang
Li, Xingyu
Xu, Yanran
Wang, Changwei
Computer Vision and Pattern Recognition
Out-of-Distribution (OOD) detection is a critical task that has garnered significant attention. The emergence of CLIP has spurred extensive research into zero-shot OOD detection, often employing a training-free approach. Current methods leverage expert knowledge from large language models (LLMs) to identify potential outliers. However, these approaches tend to over-rely on knowledge in the text space, neglecting the inherent challenges involved in detecting out-of-distribution samples in the image space. In this paper, we propose a novel pipeline, MM-OOD, which leverages the multimodal reasoning capabilities of MLLMs and their ability to conduct multi-round conversations for enhanced outlier detection. Our method is designed to improve performance in both near OOD and far OOD tasks. Specifically, (1) for near OOD tasks, we directly feed ID images and corresponding text prompts into MLLMs to identify potential outliers; and (2) for far OOD tasks, we introduce the sketch-generate-elaborate framework: first, we sketch outlier exposure using text prompts, then generate corresponding visual OOD samples, and finally elaborate by using multimodal prompts. Experiments demonstrate that our method achieves significant improvements on widely used multimodal datasets such as Food-101, while also validating its scalability on ImageNet-1K.
title Vision Also You Need: Navigating Out-of-Distribution Detection with Multimodal Large Language Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.14052