EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Deep Learning-Based Characterization and Classification of Metallographic Microstructures Using a Multi-Scale Swin Transformer

Chenwei Shao, Xiangming Kong, Shankun Yu, Huan Liu, Bingshuai Qi, Yongzhi Zhang

Materials Research Express · 17.11.2026

DOI: 10.1088/2053-1591/aec362 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials Research Express, online erschienen am 17.11.2026. Verfasst von Chenwei Shao und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated classification of metallographic microstructures is challenged by subtle inter-class differences, substantial intra-class variations, and sparse discriminative regions. Conventional convolutional neural networks have limited ability to model long-range dependencies and cross-scale microstructural patterns, whereas vision Transformers may inadequately capture local textures and grain-boundary details. To address these limitations, an explainable multi-scale enhanced Swin Transformer is proposed for complex metallographic microstructure classification. A convolutional information enhancement module and an efficient multi-scale attention module are integrated into the backbone to strengthen the representation of local textures, grain boundaries, and multi-scale morphological features. Generalized mean pooling is adopted in the classification head, while multi-view crop augmentation, focal loss, and five-crop inference are used to improve robustness. Channel-contribution analysis is subsequently performed to identify discriminative channels associated with five microstructure classes. Channel-response maps demonstrate correspondence between the regions emphasized by the network and characteristic microstructural morphologies. The identified channels are preserved during structured pruning, while low-contribution channels are removed. The proposed model achieves an accuracy of 98.00%, a precision of 98.01%, and a Cohen’s kappa coefficient of 0.9750. After pruning, the parameter count decreases from 28.096 M to 14.043 M, representing a reduction of approximately 50.0%, while retaining competitive classification performance. These results demonstrate that the proposed framework provides an accurate, interpretable, and lightweight approach for automated recognition of complex metallographic microstructures.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Shao, C., Kong, X., Yu, S., Liu, H., Qi, B., & Zhang, Y. (2026). Explainable Deep Learning-Based Characterization and Classification of Metallographic Microstructures Using a Multi-Scale Swin Transformer. Materials Research Express. https://doi.org/10.1088/2053-1591/aec362

Vancouver

Shao C, Kong X, Yu S, Liu H, Qi B, Zhang Y. Explainable Deep Learning-Based Characterization and Classification of Metallographic Microstructures Using a Multi-Scale Swin Transformer. Materials Research Express. 2026. doi:10.1088/2053-1591/aec362

BibTeX
@article{Shao2026,
  author = {Shao, Chenwei and Kong, Xiangming and Yu, Shankun and Liu, Huan and Qi, Bingshuai and Zhang, Yongzhi},
  title = {Explainable Deep Learning-Based Characterization and Classification of Metallographic Microstructures Using a Multi-Scale Swin Transformer},
  journal = {Materials Research Express},
  year = {2026},
  doi = {10.1088/2053-1591/aec362}
}
Kostenlos starten →