EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ju-LiteMobileAtt: A lightweight attention network for efficient jujube defect classification

Xiyuan Zhu iD, Hongtao Dang, Xiaoyuan Jin, Xun Li

PLOS One · 02.12.2025 · 20 (12) · e0337898

DOI: 10.1371/journal.pone.0337898 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 02.12.2025. Verfasst von Xiyuan Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Xijing University, Xi'an, Shaanxi, China. Hauptthemen laut MEDLINE: Ziziphus. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Surface defect detection of organic jujubes is critical for quality assessment. However, conventional machine vision lacks adaptability to polymorphic defects, while deep learning methods face a trade-off—deep architectures are computationally intensive and unsuitable for edge deployment, whereas lightweight models struggle to represent subtle defects. To address this, we propose Ju-LiteMobileAtt, a high-precision lightweight network based on MobileNetV2, featuring two key innovations: First, the Efficient Residual Coordinate Attention Module (EfficientRCAM) integrates spatial encoding and channel interaction for multi-scale feature capture; Second, the Cascaded Residual Coordinate Attention Module (CascadedRCAM) refines features while preserving efficiency. Experiments on the Jujube12000 dataset show Ju-LiteMobileAtt improves accuracy by 1.72% over baseline while significantly reducing parameters, enabling effective real-time edge-based jujube defect detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ZiziphusDeep LearningAlgorithmsNeural Networks, Computer

Autor:innen und Institutionen

  • Xijing University, Xi'an, Shaanxi, China.

ORCID-Profile: Xiyuan Zhu

Zitieren

APA

Zhu, X., Dang, H., Jin, X., & Li, X. (2025). Ju-LiteMobileAtt: A lightweight attention network for efficient jujube defect classification. PLOS One, 20(12), e0337898. https://doi.org/10.1371/journal.pone.0337898

Vancouver

Zhu X, Dang H, Jin X, Li X. Ju-LiteMobileAtt: A lightweight attention network for efficient jujube defect classification. PLOS One. 2025;20(12):e0337898. doi:10.1371/journal.pone.0337898

BibTeX
@article{Zhu2025,
  author = {Zhu, Xiyuan and Dang, Hongtao and Jin, Xiaoyuan and Li, Xun},
  title = {Ju-LiteMobileAtt: A lightweight attention network for efficient jujube defect classification},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {12},
  pages = {e0337898},
  doi = {10.1371/journal.pone.0337898}
}
Kostenlos starten →