EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Hierarchical vision Mamba with adaptive multi-scale fusion for steel surface defect classification

Xinyi Yu, Haotian Sun, Jinmin Peng, Xianping Zeng, Yuanfu He, Liangshen Chen, Bingsan Chen

Journal of King Saud University Computer and Information Sciences · 2026-07 · 38 (5)

DOI: 10.1007/s44443-026-00623-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 12.03.2026. Verfasst von Xinyi Yu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: the Youth Program of the National Natural Science Foundation of China, the Natural Science Foundation of Fujian Province, Fujian University of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Steel surface defect classification constitutes a critical component of industrial quality control. Current computer vision-based classification approaches, however, exhibit substantial dependence on dataset characteristics, where inconsistent defect dimensions and low-contrast ambiguities significantly compromise detection accuracy. While emerging State Space Models (SSMs) such as VMamba and Vision Mamba offer efficient long-range modeling, they often lack the multi-granular feature extraction capabilities necessary for identifying such subtle industrial anomalies. To bridge this gap, we propose HiAM-Mamba, a hierarchical architecture that synergizes the linear complexity of SSMs with adaptive multi-scale processing. Distinct from existing Mamba variants, our approach integrates a Multi-Scale Fusion (MSF) module to aggregate features across varying granularities and a Gated CNN to capture fine-grained textural patterns. Furthermore, we introduce an Adaptive Feature Recalibration mechanism to dynamically suppress environmental noise and a hierarchical head for holistic decision fusion. Extensive experiments on the NEU-CLS and X-SDD benchmarks demonstrate that HiAM-Mamba achieves state-of-the-art accuracy (99.90% and 99.15%), significantly outperforming current CNN and Transformer-based methods while maintaining superior computational efficiency.

Förderung

  • the Youth Program of the National Natural Science Foundation of China
  • the Natural Science Foundation of Fujian Province
  • Fujian University of Technology
  • Outward cooperation project of Fujian Province

Zitieren

APA

Yu, X., Sun, H., Peng, J., Zeng, X., He, Y., Chen, L., & Chen, B. (2026). Hierarchical vision Mamba with adaptive multi-scale fusion for steel surface defect classification. Journal of King Saud University Computer and Information Sciences, 38(5). https://doi.org/10.1007/s44443-026-00623-8

Vancouver

Yu X, Sun H, Peng J, Zeng X, He Y, Chen L, et al. Hierarchical vision Mamba with adaptive multi-scale fusion for steel surface defect classification. Journal of King Saud University Computer and Information Sciences. 2026;38(5). doi:10.1007/s44443-026-00623-8

BibTeX
@article{Yu2026,
  author = {Yu, Xinyi and Sun, Haotian and Peng, Jinmin and Zeng, Xianping and He, Yuanfu and Chen, Liangshen and Chen, Bingsan},
  title = {Hierarchical vision Mamba with adaptive multi-scale fusion for steel surface defect classification},
  journal = {Journal of King Saud University Computer and Information Sciences},
  year = {2026},
  volume = {38},
  number = {5},
  doi = {10.1007/s44443-026-00623-8}
}
Kostenlos starten →