{"@context":"https://schema.org","@type":"ScholarlyArticle","headline":"EFEN-YOLOv8: Surface defect detection network based on spatial feature capture and multi-level weighted attention.","author":[{"@type":"Person","name":"Meishun Wu"},{"@type":"Person","name":"Jinmin Peng"},{"@type":"Person","name":"Xinyi Yu"},{"@type":"Person","name":"Heng Xu"},{"@type":"Person","name":"Haotian Sun"}],"datePublished":"2026","isPartOf":{"@type":"Periodical","name":"PloS one"},"identifier":"https://doi.org/10.1371/journal.pone.0339617","description":"\n Surface defects in industrial environments severely the impact product aesthetics, quality, and operational efficiency. Although deep learning approaches show promise, current architectures often demonstrate inadequate feature extraction in industrial settings. We introduce EFEN-YOLOv8, a novel defect detection framework that prioritizes efficient feature extraction to enhance detection accuracy. Our approach incorporates a\n \n \n \n \n \n β\n \n \n \n \n -FEIoU loss function that concurrently tackles defect-background discrimination and positive-negative sample imbalance. The Shallow Attention Convolution (SAConv) module strengthens feature localization in early network layers, while Large Separable Kernel Attention (LSKA) expands receptive fields and augments processing efficiency. Additionally, our Weighted Atrous Spatial Pyramid Pooling (WASPP) feature fusion module facilitates multi-scale integration, enabling richer abstract information capture and improved model representation. Comprehensive experimental validation, including statistical significance testing across diverse data splits, confirms superior performance over existing methods. Our framework achieves 7.4% mAP improvement on NEU-DET and 3.3% enhancement on GC10-DET compared to baseline models, maintaining consistent performance across both 8:2 and 9:1 train-test configurations. These findings validate the method’s robust generalization capacity and establish its effectiveness for industrial surface defect detection applications. Code and datasets are available at:\n https://github.com/01WineCool/YOLO\n .\n ","url":"https://innscience.ca/en/community/literature/doi_10_1371_journal_pone_0339617"}