Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Self-Attention Enhanced Student–Teacher Framework for Visual Anomaly Detection in Industrial Images
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0002-3774-4850
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0001-8607-4083
2026 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 14, p. 36318-36330Article in journal (Refereed) Published
Abstract [en]

In this work we introduce AeCSAD, a student–teacher framework designed to detect two types of anomalies in images of industrial components: structural anomalies (physical defects) and logical anomalies (incorrect relationships between components). Unlike prior methods, AeCSAD extends the component segmentation–based logical anomaly detection scheme (c. 2024) with self-attention mechanisms, enabling more effective relational modeling. We demonstrate consistent improvements on the MVTec LOCO Anomaly Detection benchmark. Specifically, AeCSAD employs a global student network with self-attention for reasoning across distant components, complemented by a local student network for fine-grained analysis. Additionally, a patch histogram module measures the frequency distribution of components, allowing the system to detect irregularities in their occurrence. During inference, anomaly scores from the histogram module and the fused local–global networks are combined to produce the final anomaly score. Experiments show that AeCSAD achieves superior average AUROC performance on both structural and logical anomaly detection tasks compared to prior approaches.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2026. Vol. 14, p. 36318-36330
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:miun:diva-56899DOI: 10.1109/ACCESS.2026.3670056ISI: 001711131800044Scopus ID: 2-s2.0-105031928794OAI: oai:DiVA.org:miun-56899DiVA, id: diva2:2046059
Available from: 2026-03-16 Created: 2026-03-16 Last updated: 2026-03-27Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Shallari, IridaO'Nils, Mattias

Search in DiVA

By author/editor
Shallari, IridaO'Nils, Mattias
By organisation
Department of Computer and Electrical Engineering (2023-)
In the same journal
IEEE Access
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 97 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf