AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gu, Zhaopeng, Zhu, Bingke, Zhu, Guibo, Chen, Yingying, Ge, Wei, Tang, Ming, Wang, Jinqiao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913980394504192
author Gu, Zhaopeng
Zhu, Bingke
Zhu, Guibo
Chen, Yingying
Ge, Wei
Tang, Ming
Wang, Jinqiao
author_facet Gu, Zhaopeng
Zhu, Bingke
Zhu, Guibo
Chen, Yingying
Ge, Wei
Tang, Ming
Wang, Jinqiao
contents Anomaly detection is a critical task across numerous domains and modalities, yet existing methods are often highly specialized, limiting their generalizability. These specialized models, tailored for specific anomaly types like textural defects or logical errors, typically exhibit limited performance when deployed outside their designated contexts. To overcome this limitation, we propose AnomalyMoE, a novel and universal anomaly detection framework based on a Mixture-of-Experts (MoE) architecture. Our key insight is to decompose the complex anomaly detection problem into three distinct semantic hierarchies: local structural anomalies, component-level semantic anomalies, and global logical anomalies. AnomalyMoE correspondingly employs three dedicated expert networks at the patch, component, and global levels, and is specialized in reconstructing features and identifying deviations at its designated semantic level. This hierarchical design allows a single model to concurrently understand and detect a wide spectrum of anomalies. Furthermore, we introduce an Expert Information Repulsion (EIR) module to promote expert diversity and an Expert Selection Balancing (ESB) module to ensure the comprehensive utilization of all experts. Experiments on 8 challenging datasets spanning industrial imaging, 3D point clouds, medical imaging, video surveillance, and logical anomaly detection demonstrate that AnomalyMoE establishes new state-of-the-art performance, significantly outperforming specialized methods in their respective domains.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06203
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection
Gu, Zhaopeng
Zhu, Bingke
Zhu, Guibo
Chen, Yingying
Ge, Wei
Tang, Ming
Wang, Jinqiao
Computer Vision and Pattern Recognition
Anomaly detection is a critical task across numerous domains and modalities, yet existing methods are often highly specialized, limiting their generalizability. These specialized models, tailored for specific anomaly types like textural defects or logical errors, typically exhibit limited performance when deployed outside their designated contexts. To overcome this limitation, we propose AnomalyMoE, a novel and universal anomaly detection framework based on a Mixture-of-Experts (MoE) architecture. Our key insight is to decompose the complex anomaly detection problem into three distinct semantic hierarchies: local structural anomalies, component-level semantic anomalies, and global logical anomalies. AnomalyMoE correspondingly employs three dedicated expert networks at the patch, component, and global levels, and is specialized in reconstructing features and identifying deviations at its designated semantic level. This hierarchical design allows a single model to concurrently understand and detect a wide spectrum of anomalies. Furthermore, we introduce an Expert Information Repulsion (EIR) module to promote expert diversity and an Expert Selection Balancing (ESB) module to ensure the comprehensive utilization of all experts. Experiments on 8 challenging datasets spanning industrial imaging, 3D point clouds, medical imaging, video surveillance, and logical anomaly detection demonstrate that AnomalyMoE establishes new state-of-the-art performance, significantly outperforming specialized methods in their respective domains.
title AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.06203