EUVIMEDEUVIMED entdecken
Crossref

FocusPatch AD: Few-Shot Multi-Class Anomaly Detection With Unified Keywords Patch Prompts

Xicheng Ding, Xiaofan Li, Mingang Chen, Jingyu Gong, Yuan Xie

IEEE Transactions on Image Processing · 2026 · 35 · 112-123

DOI: 10.1109/tip.2025.3646861 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Xicheng Ding und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Chongqing, China, Natural Science Foundation of Shanghai.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industrial few-shot anomaly detection (FSAD) requires identifying various abnormal states by leveraging as few normal samples as possible (abnormal samples are unavailable during training). However, current methods often require training a separate model for each category, leading to increased computation and storage overhead. Thus, designing a unified anomaly detection model that supports multiple categories remains a challenging task, as such a model must recognize anomalous patterns across diverse objects and domains. To tackle these challenges, this paper introduces FocusPatch AD, a unified anomaly detection framework based on vision-language models, achieving anomaly detection under few-shot multi-class settings. FocusPatch AD links anomaly state keywords to highly relevant discrete local regions within the image, guiding the model to focus on cross-category anomalies while filtering out background interference. This approach mitigates the false detection issues caused by global semantic alignment in vision-language models. We evaluate the proposed method on the MVTec, VisA, and Real-IAD datasets, comparing them against several prevailing anomaly detection methods. In both image-level and pixel-level anomaly detection tasks, FocusPatch AD achieves significant gains in classification and localization performance, demonstrating excellent generalization and adaptability.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Chongqing, China
  • Natural Science Foundation of Shanghai
  • Open Project Program of the State Key Laboratory of Computer-Aided Design and Computer Graphics
  • Zhejiang University

Zitieren

APA

Ding, X., Li, X., Chen, M., Gong, J., & Xie, Y. (2026). FocusPatch AD: Few-Shot Multi-Class Anomaly Detection With Unified Keywords Patch Prompts. IEEE Transactions on Image Processing, 35, 112-123. https://doi.org/10.1109/tip.2025.3646861

Vancouver

Ding X, Li X, Chen M, Gong J, Xie Y. FocusPatch AD: Few-Shot Multi-Class Anomaly Detection With Unified Keywords Patch Prompts. IEEE Transactions on Image Processing. 2026;35:112-123. doi:10.1109/tip.2025.3646861

BibTeX
@article{Ding2026,
  author = {Ding, Xicheng and Li, Xiaofan and Chen, Mingang and Gong, Jingyu and Xie, Yuan},
  title = {FocusPatch AD: Few-Shot Multi-Class Anomaly Detection With Unified Keywords Patch Prompts},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {112--123},
  doi = {10.1109/tip.2025.3646861}
}
Kostenlos starten →