EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UniFlow: Unified Normalizing Flow for Unsupervised Multi-Class Anomaly Detection

Jianmei Zhong, Yanzhi Song

Information · 10.12.2024 · 15 (12) · 791

DOI: 10.3390/info15120791 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 10.12.2024. Verfasst von Jianmei Zhong und 1 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, NSF of China, Major Project of Science and Technology Innovation Tackling Plan of Anhui Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-class anomaly detection is more efficient and less resource-consuming in industrial anomaly detection scenes that involve multiple categories or exhibit large intra-class diversity. However, most industrial image anomaly detection methods are developed for one-class anomaly detection, which typically suffer significant performance drops in multi-class scenarios. Research specifically targeting multi-class anomaly detection remains relatively limited. In this work, we propose a powerful unified normalizing flow for multi-class anomaly detection, which we call UniFlow. A multi-cognitive visual adapter (Mona) is employed in our method as the feature adaptation layer to adapt image features for both the multi-class anomaly detection task and the normalizing flow model, facilitating the learning of general knowledge of normal images across multiple categories. We adopt multi-cognitive convolutional networks with high capacity to construct the coupling layers within the normalizing flow model for more effective multi-class distribution modeling. In addition, we employ a multi-scale feature fusion module to aggregate features from various levels, thereby obtaining fused features with enhanced expressive capabilities. UniFlow achieves a class-average image-level AUROC of 99.1% and a class-average pixel-level AUROC of 98.0% on MVTec AD, outperforming the SOTA multi-class anomaly detection methods. Extensive experiments on three benchmark datasets, MVTec AD, VisA, and BTAD, demonstrate the efficacy and superiority of our unified normalizing flow in multi-class anomaly detection.

Förderung

  • National Key R&D Program of China
  • NSF of China
  • Major Project of Science and Technology Innovation Tackling Plan of Anhui Province
  • Xiaomi Young Talents Program

Zitieren

APA

Zhong, J., & Song, Y. (2024). UniFlow: Unified Normalizing Flow for Unsupervised Multi-Class Anomaly Detection. Information, 15(12), 791. https://doi.org/10.3390/info15120791

Vancouver

Zhong J, Song Y. UniFlow: Unified Normalizing Flow for Unsupervised Multi-Class Anomaly Detection. Information. 2024;15(12):791. doi:10.3390/info15120791

BibTeX
@article{Zhong2024,
  author = {Zhong, Jianmei and Song, Yanzhi},
  title = {UniFlow: Unified Normalizing Flow for Unsupervised Multi-Class Anomaly Detection},
  journal = {Information},
  year = {2024},
  volume = {15},
  number = {12},
  pages = {791},
  doi = {10.3390/info15120791}
}
Kostenlos starten →