FR-PatchCore: An Industrial Anomaly Detection Method for Improving Generalization
Sensors · 20.02.2024 · 24 (5) · 1368
DOI: 10.3390/s24051368 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 20.02.2024. Verfasst von Zhiqian Jiang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 611756, China. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Funds for International Cooperation and Exchange of the National Natural Science Foundation of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
In recent years, a multitude of self-supervised anomaly detection algorithms have been proposed. Among them, PatchCore has emerged as one of the state-of-the-art methods on the widely used MVTec AD benchmark due to its efficient detection capabilities and cost-saving advantages in terms of labeled data. However, we have identified that the PatchCore similarity principal approach faces significant limitations in accurately locating anomalies when there are positional relationships between similar samples, such as rotation, flipping, or misaligned pixels. In real-world industrial scenarios, it is common for samples of the same class to be found in different positions. To address this challenge comprehensively, we introduce Feature-Level Registration PatchCore (FR-PatchCore), which serves as an extension of the PatchCore method. FR-PatchCore constructs a feature matrix that is extracted into the memory bank and continually updated using the optimal negative cosine similarity loss. Extensive evaluations conducted on the MVTec AD benchmark demonstrate that FR-PatchCore achieves an impressive image-level anomaly detection AUROC score of up to 98.81%. Additionally, we propose a novel method for computing the mask threshold that enables the model to scientifically determine the optimal threshold and accurately partition anomalous masks. Our results highlight not only the high generalizability but also substantial potential for industrial anomaly detection offered by FR-PatchCore.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 611756, China.
ORCID-Profile: Jinlong Li
Förderung
- Funds for International Cooperation and Exchange of the National Natural Science Foundation of China
- National Natural Science Foundation of China
Zitieren
APA
Jiang, Z., Zhang, Y., Wang, Y., Li, J., & Gao, X. (2024). FR-PatchCore: An Industrial Anomaly Detection Method for Improving Generalization. Sensors, 24(5), 1368. https://doi.org/10.3390/s24051368
Vancouver
Jiang Z, Zhang Y, Wang Y, Li J, Gao X. FR-PatchCore: An Industrial Anomaly Detection Method for Improving Generalization. Sensors. 2024;24(5):1368. doi:10.3390/s24051368
BibTeX
@article{Jiang2024,
author = {Jiang, Zhiqian and Zhang, Yu and Wang, Yong and Li, Jinlong and Gao, Xiaorong},
title = {FR-PatchCore: An Industrial Anomaly Detection Method for Improving Generalization},
journal = {Sensors},
year = {2024},
volume = {24},
number = {5},
pages = {1368},
doi = {10.3390/s24051368}
}
EUVIMED