EUVIMEDEUVIMED entdecken
Crossref

Sensitivity Analysis-Based Explainable Diffusion Transformers for Anomaly Detection in Consumer Electronics Manufacturing

Ling Yi, Shiyu Liu, Li Zhou, Zhaolong Ning, Jiajie Song, Qingda Chen, Ke Zhang, Jinliang Ding

IEEE Transactions on Consumer Electronics · 2025-02 · 71 (1) · 2039-2050

DOI: 10.1109/tce.2025.3527809 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-02. Verfasst von Ling Yi und 7 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Research Program of Chongqing Municipal Education Commission, Xingliao Talent Program of Liaoning Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Consumer electronics play a crucial role in the artificial intelligence Internet of Things (AIoT), with anomaly detection (AD) being particularly critical for the consumer product manufacturing industry. However, existing AD methods suffer from limitations such as poor detection accuracy and lack of explainability, hindering their widespread adoption in industrial manufacturing. To address these issues, we propose SADiTAD, a Sensitivity Analysis-based Diffusion Transformer for Anomaly Detection. This model comprises a diffusion transformer (DiT)-based reconstruction enhancement sub-network and a vision transformer (ViT)-based detection sub-network. In the DiT sub-network, we introduce a structural similarity index measure (SSIM)-guided one-step denoising method to expedite the denoising process. Additionally, to enhance the model’s explainability, we develop a sensitivity analysis-based ViT (SA-ViT) model, which evaluates the sensitivity of input embeddings to various image regions to determine if the fault region is being accurately identified during anomaly detection. The proposed SADiTAD model has been evaluated on public datasets MVTec AD and VisA, demonstrating superior performance over existing state-of-the-art anomaly detection methods and providing enhanced explainability.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Research Program of Chongqing Municipal Education Commission
  • Xingliao Talent Program of Liaoning Province
  • Open Research Fund from Guangdong Laboratory of Artificial Intelligence and Digital Economy, Shenzhen

Zitieren

APA

Yi, L., Liu, S., Zhou, L., Ning, Z., Song, J., Chen, Q., Zhang, K., & Ding, J. (2025). Sensitivity Analysis-Based Explainable Diffusion Transformers for Anomaly Detection in Consumer Electronics Manufacturing. IEEE Transactions on Consumer Electronics, 71(1), 2039-2050. https://doi.org/10.1109/tce.2025.3527809

Vancouver

Yi L, Liu S, Zhou L, Ning Z, Song J, Chen Q, et al. Sensitivity Analysis-Based Explainable Diffusion Transformers for Anomaly Detection in Consumer Electronics Manufacturing. IEEE Transactions on Consumer Electronics. 2025;71(1):2039-2050. doi:10.1109/tce.2025.3527809

BibTeX
@article{Yi2025,
  author = {Yi, Ling and Liu, Shiyu and Zhou, Li and Ning, Zhaolong and Song, Jiajie and Chen, Qingda and Zhang, Ke and Ding, Jinliang},
  title = {Sensitivity Analysis-Based Explainable Diffusion Transformers for Anomaly Detection in Consumer Electronics Manufacturing},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2025},
  volume = {71},
  number = {1},
  pages = {2039--2050},
  doi = {10.1109/tce.2025.3527809}
}
Kostenlos starten →