EUVIMEDEUVIMED entdecken
Crossref

Unlocking the Potential of Reverse Distillation for Anomaly Detection

Xinyue Liu, Jianyuan Wang, Biao Leng, Shuo Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 5640-5648

DOI: 10.1609/aaai.v39i6.32601 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Xinyue Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To address this problem, the widely accepted Reverse Distillation (RD) paradigm designs the asymmetry teacher and student network, using an encoder as teacher and a decoder as student. Yet, the design of RD does not ensure that the teacher encoder effectively distinguishes between normal and abnormal features or that the student decoder generates anomaly-free features. Additionally, the absence of skip connections results in a loss of fine details during feature reconstruction. To address these issues, we propose RD with Expert, which introduces a novel Expert-Teacher-Student network for simultaneous distillation of both the teacher encoder and student decoder. The added expert network enhances the student's ability to generate normal features and optimizes the teacher's differentiation between normal and abnormal features, reducing missed detections. Additionally, Guided Information Injection is designed to filter and transfer features from teacher to student, improving detail reconstruction and minimizing false positives. Experiments on several benchmarks prove that our method outperforms existing unsupervised AD methods under RD paradigm, fully unlocking RD’s potential.

Zitieren

APA

Liu, X., Wang, J., Leng, B., & Zhang, S. (2025). Unlocking the Potential of Reverse Distillation for Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 5640-5648. https://doi.org/10.1609/aaai.v39i6.32601

Vancouver

Liu X, Wang J, Leng B, Zhang S. Unlocking the Potential of Reverse Distillation for Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):5640-5648. doi:10.1609/aaai.v39i6.32601

BibTeX
@article{Liu2025,
  author = {Liu, Xinyue and Wang, Jianyuan and Leng, Biao and Zhang, Shuo},
  title = {Unlocking the Potential of Reverse Distillation for Anomaly Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {6},
  pages = {5640--5648},
  doi = {10.1609/aaai.v39i6.32601}
}
Kostenlos starten →