EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MCM-YOLO: A Lightweight Conflict Mitigation Network for Industrial Metal Surface Defect Detection

Shuhao Zhang, Kunjin He, Jiachen Xu, Heshan Sha, Zhengming Chen

Sensors · 09.07.2026 · 26 (14) · 4349

DOI: 10.3390/s26144349 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.07.2026. Verfasst von Shuhao Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Engineering, Hohai University, Changzhou 213200, China. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Fundamental Research Funds for the Central Universities, the National Key Research and Development Program of China, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industrial metal surface defect detection is essential for visual sensing-based quality inspection, where lightweight models must balance reliable defect perception and efficient deployment under limited computational resources. However, weak textures, blurred boundaries, and small defect scales often reduce the reliability of lightweight detectors, while heavy global modeling modules increase computational cost. This article proposes a lightweight You Only Look Once (YOLO)-based framework, termed Mediation-based Conflict Mitigation YOLO (MCM-YOLO), for industrial metal surface defect detection. Built upon YOLOv11, MCM-YOLO introduces a C3-Res2Lite (C3-R2L) block to enhance fine-grained local representation and an Aggregated Bidirectional Feature Pyramid Network (Agg-BiFPN) to strengthen multiscale feature aggregation. We further observe that directly coupling the enhanced backbone and strengthened neck may degrade performance, which is referred to as Feature Integration Conflict (FIC). To alleviate the potential feature incompatibility associated with FIC, this article introduces a synergistic attention block, termed MCM-SAB, at the critical interface to perform coordinated channel recalibration and spatial refinement. Experiments on NEU-DET and GC-10 show that MCM-YOLO achieves 80.4% and 65.1% mean average precision (mAP) at an intersection-over-union (IoU) threshold of 0.5, respectively, with 6.3 giga floating-point operations (GFLOPs) and 2.70 million parameters. These results indicate that MCM-YOLO provides a competitive accuracy–efficiency tradeoff for industrial visual inspection.

Schlagwörter

Stichwörter der Autor:innen

YOLOattention mechanismslightweight neural networksmetal surface defect detectionmultiscale feature fusion

Autor:innen und Institutionen

  • College of Information Science and Engineering, Hohai University, Changzhou 213200, China.
  • Key Laboratory of Maritime Intelligent Cyberspace Technology of Ministry of Education, Hohai University, Changzhou 213200, China.

Förderung

  • the Fundamental Research Funds for the Central Universities
  • the National Key Research and Development Program of China
  • Fundamental Research Funds for the Central Universities
  • National Key Research and Development Program of China

Zitieren

APA

Zhang, S., He, K., Xu, J., Sha, H., & Chen, Z. (2026). MCM-YOLO: A Lightweight Conflict Mitigation Network for Industrial Metal Surface Defect Detection. Sensors, 26(14), 4349. https://doi.org/10.3390/s26144349

Vancouver

Zhang S, He K, Xu J, Sha H, Chen Z. MCM-YOLO: A Lightweight Conflict Mitigation Network for Industrial Metal Surface Defect Detection. Sensors. 2026;26(14):4349. doi:10.3390/s26144349

BibTeX
@article{Zhang2026,
  author = {Zhang, Shuhao and He, Kunjin and Xu, Jiachen and Sha, Heshan and Chen, Zhengming},
  title = {MCM-YOLO: A Lightweight Conflict Mitigation Network for Industrial Metal Surface Defect Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4349},
  doi = {10.3390/s26144349}
}
Kostenlos starten →