EUVIMEDEUVIMED entdecken
Crossref

MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection

Ruiying Lu, Gang Liu, Kang Li, Long Tian, Junwei Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15457-15465

DOI: 10.1609/aaai.v40i18.38573 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ruiying Lu und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-class unsupervised anomaly detection endeavors to establish a unified model capable of identifying anomalies across multiple classes when only normal data is accessible. However, widely employed reconstruction-based networks often struggle with the 'identical shortcut' issue of both normal and anomalous samples being reconstructed equally well, consequently failing to identify outliers. Although current methodologies attempt to tackle this problem, they remain susceptible to infiltration of anomalous information. In contrast, we introduce a novel scheme to make use of the `identical shortcut' phenomenon rather than pursue to eliminate it. Firstly, inspired by our interesting observation that normal and abnormal regions manifest distinct behaviors when encountering diverse masks, we devise a multi-branch masked autoencoder tailored for multi-class image reconstruction. Subsequently, we introduce a parallel masking scheme to magnify the reconstruction disparity between normal and abnormal regions when confronted with various masks. Ultimately, we propose a reconstruction association discrepancy learning method as a new anomaly localization criterion. The effectiveness of our approach is validated both quantitatively and qualitatively, achieving state-of-the-art results.

Zitieren

APA

Lu, R., Liu, G., Li, K., Tian, L., & Zhang, J. (2026). MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15457-15465. https://doi.org/10.1609/aaai.v40i18.38573

Vancouver

Lu R, Liu G, Li K, Tian L, Zhang J. MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15457-15465. doi:10.1609/aaai.v40i18.38573

BibTeX
@article{Lu2026,
  author = {Lu, Ruiying and Liu, Gang and Li, Kang and Tian, Long and Zhang, Junwei},
  title = {MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15457--15465},
  doi = {10.1609/aaai.v40i18.38573}
}
Kostenlos starten →