EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vision transformer and Mamba-attention fusion for high-precision PCB defect detection

Asim Niaz, Muhammad Umraiz, Shafiullah Soomro, Kwang Nam Choi iD

PLOS One · 25.09.2025 · 20 (9) · e0331175

DOI: 10.1371/journal.pone.0331175 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 25.09.2025. Verfasst von Asim Niaz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Electronics. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Information and Communication Technology (ICT), National IT Industry Promotion Agency (NIPA) through the High Performance Computing (HPC) Support Project, Ministry of Science and ICT, South Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Defects in printed circuit boards (PCBs) are being detected using computer vision-based techniques. Defect-free PCBs are essential for the reliability of consumer electronics. However, deep learning-based methods often struggle with imbalanced defect distributions and limited generalization. To address these challenges, we propose ViT-Mamba, a hybrid framework that combines Vision Transformers with a Mamba-inspired attention mechanism for global feature extraction and precise defect segmentation. We further introduce an artificial defect generation module that systematically creates six types of PCB defects to improve robustness. A multiscale hierarchical refinement strategy is employed to enhance feature representation for accurate segmentation. Experiments on a public PCB defect dataset show that ViT-Mamba outperforms existing methods, achieving a mean Average Precision (mAP) of 99.69%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningElectronicsAlgorithmsHumans

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea.
  • Department of Computer Science and Media Technology, Linnaeus University, Vaxjo, Sweden.

ORCID-Profile: Kwang Nam Choi

Förderung

  • Ministry of Science and Information and Communication Technology (ICT)
  • National IT Industry Promotion Agency (NIPA) through the High Performance Computing (HPC) Support Project
  • Ministry of Science and ICT, South Korea
  • National IT Industry Promotion Agency

Zitieren

APA

Niaz, A., Umraiz, M., Soomro, S., & Choi, K. N. (2025). Vision transformer and Mamba-attention fusion for high-precision PCB defect detection. PLOS One, 20(9), e0331175. https://doi.org/10.1371/journal.pone.0331175

Vancouver

Niaz A, Umraiz M, Soomro S, Choi KN. Vision transformer and Mamba-attention fusion for high-precision PCB defect detection. PLOS One. 2025;20(9):e0331175. doi:10.1371/journal.pone.0331175

BibTeX
@article{Niaz2025,
  author = {Niaz, Asim and Umraiz, Muhammad and Soomro, Shafiullah and Choi, Kwang Nam},
  title = {Vision transformer and Mamba-attention fusion for high-precision PCB defect detection},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {9},
  pages = {e0331175},
  doi = {10.1371/journal.pone.0331175}
}
Kostenlos starten →