RDMS: Reverse distillation with multiple students of different scales for anomaly detection
IET Image Processing · 2024-11 · 18 (13) · 3815-3826
DOI: 10.1049/ipr2.13210 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Image Processing, online erschienen am 23.08.2024. Verfasst von Ziheng Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hubei Province.
Abstract (Originalsprache)
Unsupervised anomaly detection, often approached as a one‐class classification problem, is a critical task in computer vision. Knowledge distillation has emerged as a promising technique for enhancing anomaly detection accuracy, especially with the advent of reverse distillation networks that employ encoder–decoder architectures. This study introduces a novel reverse knowledge distillation framework known as RDMS, which incorporates a pretrained teacher encoding module, a multi‐level feature fusion connection module, and a student decoding module consisting of three independent decoders. RDMS is designed to distill distinct features from the teacher encoder, mitigating overfitting issues associated with similar or identical teacher–student structures. The model achieves an average of 99.3 image‐level AUROC and 98.34 pixel‐level AUROC on the MVTec‐AD dataset and demonstrates state‐of‐the‐art performance on the more challenging BTAD dataset. The RDMS model's high accuracy in anomaly detection and localization underscores the potential of multi‐student reverse distillation to advance unsupervised anomaly detection capabilities. The source code is available at https://github.com/zihengchen777/RDMS
Förderung
- Natural Science Foundation of Hubei Province
Zitieren
APA
Chen, Z., Lyu, C., Zhang, L., Li, S., & Xia, B. (2024). RDMS: Reverse distillation with multiple students of different scales for anomaly detection. IET Image Processing, 18(13), 3815-3826. https://doi.org/10.1049/ipr2.13210
Vancouver
Chen Z, Lyu C, Zhang L, Li S, Xia B. RDMS: Reverse distillation with multiple students of different scales for anomaly detection. IET Image Processing. 2024;18(13):3815-3826. doi:10.1049/ipr2.13210
BibTeX
@article{Chen2024,
author = {Chen, Ziheng and Lyu, Chenzhi and Zhang, Lei and Li, ShaoKang and Xia, Bin},
title = {RDMS: Reverse distillation with multiple students of different scales for anomaly detection},
journal = {IET Image Processing},
year = {2024},
volume = {18},
number = {13},
pages = {3815--3826},
doi = {10.1049/ipr2.13210}
}
EUVIMED