Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Runhe, Lu, Xinhua, Chen, Kanghao, Chen, Qichao, Zheng, Wei-Shi, Wang, Ruixuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915461271126016
author Lai, Runhe
Lu, Xinhua
Chen, Kanghao
Chen, Qichao
Zheng, Wei-Shi
Wang, Ruixuan
author_facet Lai, Runhe
Lu, Xinhua
Chen, Kanghao
Chen, Qichao
Zheng, Wei-Shi
Wang, Ruixuan
contents In trustworthy medical diagnosis systems, integrating out-of-distribution (OOD) detection aims to identify unknown diseases in samples, thereby mitigating the risk of misdiagnosis. In this study, we propose a novel OOD detection framework based on vision-language models (VLMs), which integrates hierarchical visual information to cope with challenging unknown diseases that resemble known diseases. Specifically, a cross-scale visual fusion strategy is proposed to couple visual embeddings from multiple scales. This enriches the detailed representation of medical images and thus improves the discrimination of unknown diseases. Moreover, a cross-scale hard pseudo-OOD sample generation strategy is proposed to benefit OOD detection maximally. Experimental evaluations on three public medical datasets support that the proposed framework achieves superior OOD detection performance compared to existing methods. The source code is available at https://openi.pcl.ac.cn/OpenMedIA/HVL.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17667
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detection
Lai, Runhe
Lu, Xinhua
Chen, Kanghao
Chen, Qichao
Zheng, Wei-Shi
Wang, Ruixuan
Computer Vision and Pattern Recognition
Artificial Intelligence
In trustworthy medical diagnosis systems, integrating out-of-distribution (OOD) detection aims to identify unknown diseases in samples, thereby mitigating the risk of misdiagnosis. In this study, we propose a novel OOD detection framework based on vision-language models (VLMs), which integrates hierarchical visual information to cope with challenging unknown diseases that resemble known diseases. Specifically, a cross-scale visual fusion strategy is proposed to couple visual embeddings from multiple scales. This enriches the detailed representation of medical images and thus improves the discrimination of unknown diseases. Moreover, a cross-scale hard pseudo-OOD sample generation strategy is proposed to benefit OOD detection maximally. Experimental evaluations on three public medical datasets support that the proposed framework achieves superior OOD detection performance compared to existing methods. The source code is available at https://openi.pcl.ac.cn/OpenMedIA/HVL.
title Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.17667