ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection

Zoghlami, Firas, Bazazian, Dena, Masala, Giovanni L, Gianni, Mario ORCID: 0000-0001-5410-2377 and Khan, Asiya (2024) ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection IEEE ACCESS, 12 (99). pp. 173304-173315. ISSN 2169-3536, 2169-3536

PDF FINAL Article.pdf - Author Accepted Manuscript Download (39MB) | Preview

Abstract

Quality inspection is an industrial field with a growing interest in anomaly detection research. An anomaly in an image can either be structural or logical. While structural anomalies lie on the image objects, challenging logical anomalies are hidden in the global relations between the image components. The proposed approach, Vision Graph based Logical Anomaly Detection (ViGLAD), uses the graph representation of an image for logical anomaly detection. Defining an image as a structure of nodes and edges leverages new possibilities for detecting hidden logical anomalies by introducing vision graph autoencoders. Our experiments on public datasets show that using vision graphs enhances the performance of state-of-the-art teacher-student-autoencoder neural networks in logical anomaly detection while achieving robust results in structural anomaly detection.

Item Type:	Article
Uncontrolled Keywords:	Anomaly detection, Feature extraction, Convolution, Training, Vectors, Image classification, Social networking (online), Object recognition, Object detection, Graph neural networks, Logical anomaly detection, graph neural networks, vision graphs
Divisions:	Faculty of Science & Engineering Faculty of Science & Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	29 Nov 2024 09:56
Last Modified:	23 May 2026 09:33
DOI:	10.1109/ACCESS.2024.3502514
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3188937
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.