Ju-LiteMobileAtt: A lightweight attention network for efficient jujube defect classification
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).
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)
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}
}
EUVIMED