AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4348-4356
DOI: 10.1609/aaai.v40i6.42432 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhaopeng Gu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Gu, Z., Zhu, B., Zhu, G., Chen, Y., Ge, W., Tang, M., & Wang, J. (2026). AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4348-4356. https://doi.org/10.1609/aaai.v40i6.42432
Vancouver
Gu Z, Zhu B, Zhu G, Chen Y, Ge W, Tang M, et al. AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4348-4356. doi:10.1609/aaai.v40i6.42432
BibTeX
@article{Gu2026,
author = {Gu, Zhaopeng and Zhu, Bingke and Zhu, Guibo and Chen, Yingying and Ge, Wei and Tang, Ming and Wang, Jinqiao},
title = {AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {6},
pages = {4348--4356},
doi = {10.1609/aaai.v40i6.42432}
}
EUVIMED