EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Abnormal Discrepancy-Guided Knowledge Distillation for Image Anomaly Detection

Zhenjun Yu iD, Lin Sun, Kai Wang, Fengxiang Jin

Journal of Imaging · 30.06.2026 · 12 (7) · 291

DOI: 10.3390/jimaging12070291 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 30.06.2026. Verfasst von Zhenjun Yu und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266000, China. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knowledge distillation is a cornerstone of image anomaly detection for amplifying subtle defects via teacher–student discrepancy, yet existing methods rely on feature alignment loss that causes reconstruction error confusion and degrades accuracy. To address this critical limitation, this study proposes an abnormal discrepancy-guided knowledge distillation method (DiffKD) that differentially guides student feature reconstruction through channel-level discrepancy masks, leveraging normal features as supervisory signals and abnormal discrepancy features as constraints to enhance anomaly detection performance. The approach integrates a knowledge distillation network for feature reconstruction with a segmentation network for anomaly localization, while utilizing prior anomaly samples and synthetic anomaly samples to provide real-time training data of anomalous samples. Extensive evaluations on the SUT-Crack and MVTec AD benchmarks validate the effectiveness and generalizability of our approach. On MVTec AD, it achieves 80.7% average precision (AP) and 81.9% instance-level average precision (IAP), showing competitive performance against the representative methods evaluated under the same protocol. These results not only demonstrate significant improvements in IAD accuracy but also highlight its promise for enabling real-time, automated anomaly detection in practical applications.

Schlagwörter

Stichwörter der Autor:innen

anomaly segmentationimage anomaly detectionknowledge distillation

Autor:innen und Institutionen

  • College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266000, China.
  • Qingdao Star-Rising Technologies Co., Ltd., Qingdao 266000, China.

ORCID-Profile: Zhenjun Yu

Zitieren

APA

Yu, Z., Sun, L., Wang, K., & Jin, F. (2026). Abnormal Discrepancy-Guided Knowledge Distillation for Image Anomaly Detection. Journal of Imaging, 12(7), 291. https://doi.org/10.3390/jimaging12070291

Vancouver

Yu Z, Sun L, Wang K, Jin F. Abnormal Discrepancy-Guided Knowledge Distillation for Image Anomaly Detection. Journal of Imaging. 2026;12(7):291. doi:10.3390/jimaging12070291

BibTeX
@article{Yu2026,
  author = {Yu, Zhenjun and Sun, Lin and Wang, Kai and Jin, Fengxiang},
  title = {Abnormal Discrepancy-Guided Knowledge Distillation for Image Anomaly Detection},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {7},
  pages = {291},
  doi = {10.3390/jimaging12070291}
}
Kostenlos starten →