EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AnomalyNLP: Noisy-Label Prompt Learning for Few-Shot Industrial Anomaly Detection

Li Hua, Jin Qian

Electronics · 13.10.2025 · 14 (20) · 4016

DOI: 10.3390/electronics14204016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 13.10.2025. Verfasst von Li Hua und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Province’s Blue and Young Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-Shot Industrial Anomaly Detection (FSIAD) is an essential yet challenging problem in practical scenarios such as industrial quality inspection. Its objective is to identify previously unseen anomalous regions using only a limited number of normal support images from the same category. Recently, large pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable few-shot image-text representation abilities across a range of visual tasks, including anomaly detection. Despite their promise, real-world industrial anomaly datasets often contain noisy labels, which can degrade prompt learning and detection performance. In this paper, we propose AnomalyNLP, a new Noisy-Label Prompt Learning approach designed to tackle the challenge of few-shot anomaly detection. This framework offers a simple and efficient approach that leverages the expressive representations and precise alignment capabilities of VLMs for industrial anomaly detection. First, we design a Noisy-Label Prompt Learning (NLPL) strategy. This strategy utilizes feature learning principles to suppress the influence of noisy samples via Mean Absolute Error (MAE) loss, thereby improving the signal-to-noise ratio and enhancing overall model robustness. Furthermore, we introduce a prompt-driven optimal transport feature purification method to accurately partition datasets into clean and noisy subsets. For both image-level and pixel-level anomaly detection, AnomalyNLP achieves state-of-the-art performance across various few-shot settings on the MVTecAD and VisA public datasets. Qualitative and quantitative results on two datasets demonstrate that our method achieves the largest average AUC improvement over baseline methods across 1-, 2-, and 4-shot settings, with gains of up to 10.60%, 10.11%, and 9.55% in practical anomaly detection scenarios.

Förderung

  • Jiangsu Province’s Blue and Young Project

Zitieren

APA

Hua, L., & Qian, J. (2025). AnomalyNLP: Noisy-Label Prompt Learning for Few-Shot Industrial Anomaly Detection. Electronics, 14(20), 4016. https://doi.org/10.3390/electronics14204016

Vancouver

Hua L, Qian J. AnomalyNLP: Noisy-Label Prompt Learning for Few-Shot Industrial Anomaly Detection. Electronics. 2025;14(20):4016. doi:10.3390/electronics14204016

BibTeX
@article{Hua2025,
  author = {Hua, Li and Qian, Jin},
  title = {AnomalyNLP: Noisy-Label Prompt Learning for Few-Shot Industrial Anomaly Detection},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {20},
  pages = {4016},
  doi = {10.3390/electronics14204016}
}
Kostenlos starten →