ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection
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 compone...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10758311/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846156547206414336 |
|---|---|
| author | Firas Zoghlami Dena Bazazian Giovanni L. Masala Mario Gianni Asiya Khan |
| author_facet | Firas Zoghlami Dena Bazazian Giovanni L. Masala Mario Gianni Asiya Khan |
| author_sort | Firas Zoghlami |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-a7a451110cf24d0b97f70a1c13ff3aa4 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a7a451110cf24d0b97f70a1c13ff3aa42024-11-26T00:01:16ZengIEEEIEEE Access2169-35362024-01-011217330417331510.1109/ACCESS.2024.350251410758311ViGLAD: Vision Graph Neural Networks for Logical Anomaly DetectionFiras Zoghlami0https://orcid.org/0000-0001-9609-2568Dena Bazazian1https://orcid.org/0000-0002-1229-4494Giovanni L. Masala2https://orcid.org/0000-0001-6734-9424Mario Gianni3https://orcid.org/0000-0001-5410-2377Asiya Khan4https://orcid.org/0000-0003-3620-3048School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, U.K.School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, U.K.School of Computing, University of Kent, Canterbury, U.K.Department of Computer Science, University of Liverpool, Liverpool, U.K.School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, U.K.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.https://ieeexplore.ieee.org/document/10758311/Logical anomaly detectiongraph neural networksvision graphs |
| spellingShingle | Firas Zoghlami Dena Bazazian Giovanni L. Masala Mario Gianni Asiya Khan ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection IEEE Access Logical anomaly detection graph neural networks vision graphs |
| title | ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection |
| title_full | ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection |
| title_fullStr | ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection |
| title_full_unstemmed | ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection |
| title_short | ViGLAD: Vision Graph Neural Networks for Logical Anomaly Detection |
| title_sort | viglad vision graph neural networks for logical anomaly detection |
| topic | Logical anomaly detection graph neural networks vision graphs |
| url | https://ieeexplore.ieee.org/document/10758311/ |
| work_keys_str_mv | AT firaszoghlami vigladvisiongraphneuralnetworksforlogicalanomalydetection AT denabazazian vigladvisiongraphneuralnetworksforlogicalanomalydetection AT giovannilmasala vigladvisiongraphneuralnetworksforlogicalanomalydetection AT mariogianni vigladvisiongraphneuralnetworksforlogicalanomalydetection AT asiyakhan vigladvisiongraphneuralnetworksforlogicalanomalydetection |