EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MWYOLO: A Mamba-Enhanced Lightweight YOLO Framework with Multi-Frequency Attention for Industrial Surface Defect Detection

Junjian Chen, Zhigang Ren, Haidong Xiao, Zongze Wu

AI for Engineering · 2026

DOI: 10.3390/aieng1010003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI for Engineering, 2026. Verfasst von Junjian Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Basic and Applied Basic Research Foundation, Guangdong Major Project of Basic and Applied Basic Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industrial surface defect detection constitutes a fundamental component in automated quality inspection but remains challenging due to complex textures, diverse defect scales, and stringent real-time constraints. To address these issues, we present MWYOLO, an enhanced YOLO11-based detection framework tailored for accurate and efficient industrial inspection. First, a C3k2-Mamba Spatial Fusion Block (C3k2-MSFB) that integrates global contextual information with local structural cues via state-space modeling, enabling more discriminative representations of fine-grained texture variations. Second, a multi-scale wavelet attention (MWA) module is embedded into the backbone, leveraging wavelet-domain feature decomposition and dual attention to capture multi-frequency patterns, thereby improving sensitivity to fine-grained and subtle defect patterns. Third, an Inner-CIoU loss is developed to emphasize interior geometric alignment during bounding-box regression, offering more stable optimization for ambiguous or low-contrast targets. Extensive experiments conducted on three representative industrial datasets—NEU-DET, HRIPCB, and a self-constructed GSD dataset—demonstrate the effectiveness of MWYOLO. The model achieves mAP50 scores of 81.4%, 98.1%, and 67.7%, respectively, while maintaining a lightweight design with only 3.2M parameters and 7.3 GFLOPs. The results validate MWYOLO as a robust and computationally efficient solution, offering a favorable balance between accuracy, interpretability, and deployability for real-world industrial defect detection tasks.

Förderung

  • Guangdong Basic and Applied Basic Research Foundation
  • Guangdong Major Project of Basic and Applied Basic Research

Zitieren

APA

Chen, J., Ren, Z., Xiao, H., & Wu, Z. (2026). MWYOLO: A Mamba-Enhanced Lightweight YOLO Framework with Multi-Frequency Attention for Industrial Surface Defect Detection. AI for Engineering. https://doi.org/10.3390/aieng1010003

Vancouver

Chen J, Ren Z, Xiao H, Wu Z. MWYOLO: A Mamba-Enhanced Lightweight YOLO Framework with Multi-Frequency Attention for Industrial Surface Defect Detection. AI for Engineering. 2026. doi:10.3390/aieng1010003

BibTeX
@article{Chen2026,
  author = {Chen, Junjian and Ren, Zhigang and Xiao, Haidong and Wu, Zongze},
  title = {MWYOLO: A Mamba-Enhanced Lightweight YOLO Framework with Multi-Frequency Attention for Industrial Surface Defect Detection},
  journal = {AI for Engineering},
  year = {2026},
  doi = {10.3390/aieng1010003}
}
Kostenlos starten →