PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 11, 2026Sensors0 citationsOpen Access

MSFE-YOLO: A Steel Surface Defect Detection Algorithm Integrating Multi-Scale Frequency Domain and Defect-Aware Attention

View Full Paper
SSSiqi SuJSJiale ShenPLPeiyi Lin

Key Points

  • The primary aim is to enhance surface defect detection in steel manufacturing using advanced algorithms.
  • Developed the Multi-Scale Frequency-Enhanced Convolution (MSFC) module for feature extraction.
  • Designed the Cross-Stage Partial with Multi-Scale Defect-Aware Attention (C2MSDA) module for feature enhancement.
  • Introduced Adaptive Feature Fusion Enhancement (AFFE) for adaptive aggregation of features.
  • Achieved mAP@0.5 of 79.8% on NEU-DET and 66.7% on GC10-DET datasets.
  • Improved detection performance by 1.7% and 2.1% compared to YOLOv11s.
  • Maintained an inference speed of 89.3 FPS, optimizing real-time detection capabilities.

Abstract

Detecting surface defects on steel products is crucial for maintaining quality standards in industrial manufacturing. However, existing detection algorithms face several challenges, including the difficulty of capturing multi-scale defect characteristics with fixed receptive fields, insufficient utilization of defect edge and frequency domain features, and simplistic feature fusion strategies. In response to the above challenges, this paper proposed the Multi-Scale Frequency-Enhanced YOLO (MSFE-YOLO) algorithm that integrates multi-scale frequency domain enhancement with defect-aware attention mechanisms. First, a Multi-Scale Frequency-Enhanced Convolution (MSFC) module was constructed, which extracted multi-scale spatial features in parallel through depth-adaptive dilated convolutions, explicitly modeled high-frequency edge information using the Laplacian operator, and achieved adaptive fusion of multi-branch features via learnable weights. Second, a Cross-Stage Partial with Multi-Scale Defect-Aware Attention (C2MSDA) module was designed, integrating Sobel operator-based edge perception, multi-scale spatial attention, and adaptive channel attention to collaboratively enhance features across spatial, channel, and edge domains through a gated fusion strategy. Finally, an Adaptive Feature Fusion Enhancement (AFFE) module was proposed to achieve adaptive aggregation of multi-level features through a data-driven weight generation network and cross-scale feature interaction mechanism. Experimental results on the NEU-DET and GC10-DET datasets demonstrated that MSFE-YOLO achieved the mAP@0.5 of 79.8% and 66.7%, respectively, which were 1.7% and 2.1% higher than the benchmark model YOLOv11s respectively, while maintaining an inference speed of 89.3 FPS, which satisfied the real-time detection requirements in industrial scenarios.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Su et al. (2026) studied this question.

synapsesocial.com/papers/69d9e5ec78050d08c1b76264https://doi.org/10.3390/s26082311
Ask AI
Helpful
Bookmark
Share
View Full Paper