LESSDD-Net: A Lightweight and Efficient Steel Surface Defect Detection Network Based on Feature Segmentation and...

Steel surface defect detection is essential for maintaining industrial production quality and operational safety. However, existing deep learning-based methods often encounter high computational costs, hindering their deployment on mobile devices. To effectively address this challenge, we propose a lightweight and efficient steel surface defect detection network based on feature segmentation and partially connected structures, termed LESSDD-Net. In LESSDD-Net, we first introduce a lightweight downsampling module called the cross-stage partial-based dual-branch downsampling module (CSPDDM). This module significantly reduces the number of model parameters and computational costs while facilitating more efficient downsampling operations. Next, we present a lightweight attention mechanism known as coupled channel attention (CCAttention), which enhances the model's capability to capture essential information in feature maps. Finally, we improve the faster implementation of cross-stage partial bottleneck with two convolutions (C2f) and design a lightweight version called the lightweight and partial faster implementation of cross-stage partial bottleneck with two convolutions (LP-C2f). This module not only enhances detection accuracy but also further diminishes the model's size. Experimental results on the data-augmented Northeastern University surface defect detection (NEU-DET) dataset indicate that the mean average precision (mAP) of LESSDD-Net improves by 3.19% compared to the baseline model YOLO11n. Additionally, in terms of model complexity, LESSDD-Net reduces the number of parameters and computational costs by 39.92% and 20.63%, respectively, compared to YOLO11n. When compared with other mainstream object detection models, LESSDD-Net achieves top detection accuracy with the highest mAP value and demonstrates significant advantages in model complexity, characterized by the lowest number of parameters and computational costs.