EUVIMEDEUVIMED entdecken
Crossref

Transformer-based multicategory unsupervised anomaly detection for fabric surfaces

Hantao Zeng, Shubo Zhou, Weiyu Hu, Xueqin Jiang, Feng Pan

Textile Research Journal · 08.11.2026

DOI: 10.1177/00405175261502595 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Textile Research Journal, online erschienen am 08.11.2026. Verfasst von Hantao Zeng und 4 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fabric anomaly detection often relies on defect-free training because annotated defects are difficult to collect. Using one detector for multiple fabric categories would reduce training and maintenance costs. However, normal appearance varies considerably across weave structures, printed patterns, dyeing conditions, and local texture continuity, while many defects affect only a small region. Therefore, a unified model must adapt to the normal appearance of each fabric category while remaining sensitive to subtle local disruptions. To address these challenges, we present CALG-AD, a context-adaptive local–global reconstruction framework based on Dinomaly. Unlike Dinomaly’s directly grouped encoder targets, adaptive context decoupling constructs each reconstruction target relative to the fused class-token context and current-image spatial feature mean. Adaptive local–global attention retains Dinomaly’s global linear-attention branch and augments its value path with a routed local residual for small defects and local texture irregularities. Experiments on MVTec-AD textures, WFDD, and ZJU-Leaper evaluate the method across different fabric structures and defect shapes. On WFDD, CALG-AD improves I-AUROC from 93.41% to 97.36% and P-AUPRO from 92.58% to 93.66%. The defect-type analysis shows particularly clear P-AP gains for flecked, line, and string defects. CALG-AD also improves all three image-level metrics and P-AUPRO over Dinomaly on MVTec-AD textures and ZJU-Leaper, while requiring fewer parameters and FLOPs. These results demonstrate its effectiveness for unified anomaly detection across multiple fabric categories within each dataset. Our code is available at https://github.com/CaptaZ/CALG-AD .

Zitieren

APA

Zeng, H., Zhou, S., Hu, W., Jiang, X., & Pan, F. (2026). Transformer-based multicategory unsupervised anomaly detection for fabric surfaces. Textile Research Journal. https://doi.org/10.1177/00405175261502595

Vancouver

Zeng H, Zhou S, Hu W, Jiang X, Pan F. Transformer-based multicategory unsupervised anomaly detection for fabric surfaces. Textile Research Journal. 2026. doi:10.1177/00405175261502595

BibTeX
@article{Zeng2026,
  author = {Zeng, Hantao and Zhou, Shubo and Hu, Weiyu and Jiang, Xueqin and Pan, Feng},
  title = {Transformer-based multicategory unsupervised anomaly detection for fabric surfaces},
  journal = {Textile Research Journal},
  year = {2026},
  doi = {10.1177/00405175261502595}
}
Kostenlos starten →