EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating Local and Global Features for Wafer Defect Pattern Classification via Sequential Hybrid Architecture

Jaeho Song, Seungmin Oh, Juhyeon Noh, Minsoo Hahn, Jinsul Kim

Processes · 31.03.2026 · 14 (7) · 1134

DOI: 10.3390/pr14071134 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 31.03.2026. Verfasst von Jaeho Song und 4 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wafer map defect pattern classification supports quality monitoring in semiconductor manufacturing, but public benchmark datasets such as WM-811K exhibit extreme class imbalance, where majority classes can dominate standard metrics. This study aims to improve minority class performance while maintaining inference efficiency. Building on an iFormer-based hybrid backbone, we propose the Pattern-Selective Sequential Hybrid Network (PSS-HNet), which redesigns attention blocks to sequentially integrate local interaction (Modulated Convolution) and global interaction (Modulated Axial Attention) and applies sigmoid-based gating to control contextual information injection. Experiments on WM-811K (9 classes) compare iFormer (baseline), Axial-only, Axial+Modulation, and PSS-HNet using macro-averaged metrics as primary indicators, along with class-wise analysis and efficiency evaluation. PSS-HNet improves Macro-Recall by 1.02 percentage points (from 0.8852 to 0.8954) and Macro-F1 by 0.54 percentage points (from 0.9044 to 0.9098) over the baseline while maintaining similar accuracy. It also reduces computational cost and inference latency to 0.754 G FLOPs, 4.381 M parameters, and 7.682 ms, compared with 1.103 G FLOPs, 6.245 M parameters, and 8.666 ms for the baseline. Overall, selective sequential local–global integration provides a favorable balance between minority class performance and efficiency.

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation

Zitieren

APA

Song, J., Oh, S., Noh, J., Hahn, M., & Kim, J. (2026). Integrating Local and Global Features for Wafer Defect Pattern Classification via Sequential Hybrid Architecture. Processes, 14(7), 1134. https://doi.org/10.3390/pr14071134

Vancouver

Song J, Oh S, Noh J, Hahn M, Kim J. Integrating Local and Global Features for Wafer Defect Pattern Classification via Sequential Hybrid Architecture. Processes. 2026;14(7):1134. doi:10.3390/pr14071134

BibTeX
@article{Song2026,
  author = {Song, Jaeho and Oh, Seungmin and Noh, Juhyeon and Hahn, Minsoo and Kim, Jinsul},
  title = {Integrating Local and Global Features for Wafer Defect Pattern Classification via Sequential Hybrid Architecture},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {7},
  pages = {1134},
  doi = {10.3390/pr14071134}
}
Kostenlos starten →