EUVIMEDEUVIMED entdecken
Crossref

A SAM-guided Two-stream Lightweight Model for Anomaly Detection

Chenghao Li, Lei Qi, Xin Geng

ACM Transactions on Multimedia Computing, Communications, and Applications · 28.02.2025 · 21 (2) · 1-23

DOI: 10.1145/3706574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 09.01.2025. Verfasst von Chenghao Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: NSFC, China Postdoctoral Science Foundation, Postdoctoral Fellowship Program of CPSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In industrial anomaly detection, model efficiency and mobile-friendliness become the primary concerns in real-world applications. Simultaneously, the impressive generalization capabilities of Segment Anything (SAM) have garnered broad academic attention, making it an ideal choice for localizing unseen anomalies and diverse real-world patterns. In this paper, considering these two critical factors, we propose a SAM-guided Two-stream Lightweight Model for unsupervised anomaly detection (STLM) that not only aligns with the two practical application requirements but also harnesses the robust generalization capabilities of SAM. We employ two lightweight image encoders, i.e., our two-stream lightweight module, guided by SAM’s knowledge. To be specific, one stream is trained to generate discriminative and general feature representations in both normal and anomalous regions, while the other stream reconstructs the same images without anomalies, which effectively enhances the differentiation of two-stream representations when facing anomalous regions. Furthermore, we employ a shared mask decoder and a feature aggregation module to generate anomaly maps. Our experiments conducted on MVTec AD benchmark show that STLM, with about 16M parameters and achieving an inference time in 20ms, competes effectively with state-of-the-art methods in terms of performance, 98.26% on pixel-level AUC and 94.92% on PRO. We further experiment on more difficult datasets, e.g., VisA and DAGM, to demonstrate the effectiveness and generalizability of STLM. Codes are available online at https://github.com/Qi5Lei/STLM .

Förderung

  • NSFC
  • China Postdoctoral Science Foundation
  • Postdoctoral Fellowship Program of CPSF
  • Jiangsu Funding Program for Excellent Postdoctoral Talent

Zitieren

APA

Li, C., Qi, L., & Geng, X. (2025). A SAM-guided Two-stream Lightweight Model for Anomaly Detection. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(2), 1-23. https://doi.org/10.1145/3706574

Vancouver

Li C, Qi L, Geng X. A SAM-guided Two-stream Lightweight Model for Anomaly Detection. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(2):1-23. doi:10.1145/3706574

BibTeX
@article{Li2025,
  author = {Li, Chenghao and Qi, Lei and Geng, Xin},
  title = {A SAM-guided Two-stream Lightweight Model for Anomaly Detection},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2025},
  volume = {21},
  number = {2},
  pages = {1--23},
  doi = {10.1145/3706574}
}
Kostenlos starten →