mlsanityData to 7 Oct 2026

Unsupervised Anomaly Detection with an Enhanced Teacher for Student-Teacher Feature Pyramid Matching

arXiv 2512.18219 ↗First posted 20 Dec 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Anomaly detection or outlier is one of the challenging subjects in unsupervised learning . This paper is introduced a student-teacher framework for anomaly detection that its teacher network is enhanced for achieving high-performance metrics . For this purpose , we first pre-train the ResNet-18 network on the ImageNet and then fine-tune it on the MVTech-AD dataset . Experiment results on the image-level and pixel-level demonstrate that this idea has achieved better metrics than the previous methods . Our model , Enhanced Teacher for Student-Teacher Feature Pyramid (ET-STPM), achieved 0.971 mean accuracy on the image-level and 0.977 mean accuracy on the pixel-level for anomaly detection.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 23 references that are in the map. First posted on arXiv 20 Dec 2025.

Builds on

12 of 23 references.

References · 12

  1. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  2. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  3. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  4. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  5. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  6. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  7. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
  8. 2020Explainable Deep One-Class Classificationcited by 126
  9. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  10. 2018Metric Learning for Novelty and Anomaly Detectioncited by 21
  11. 2016Identifying and Categorizing Anomalies in Retinal Imaging Datacited by 18
  12. 2018Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representationscited by 17

Built on by

Not cited yet.