Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products

Owing to the remarkable development of deep learning algorithms, defect detection techniques based on deep neural networks have been extensively applied in industrial production. Most existing surface defect detection models assign equal costs to the classification errors among different defect categories but do not strictly distinguish them. However, various errors can generate a great discrepancy in decision risk or classification costs and then produce a cost-sensitive issue that is crucial to the manufacturing process. To address this engineering challenge, we propose a novel supervised classification cost-sensitive learning method (SCCS) and apply it to improve YOLOv5 as CS-YOLOv5, where the classification loss function of object detection was reconstructed according to a new cost-sensitive learning criterion explained by a label-cost vector selection method. In this way, the classification risk information from a cost matrix is directly introduced into the detection model and fully exploited in training. As a result, the developed approach can make low-risk classification decisions for defect detection. It is applicable for direct cost-sensitive learning based on a cost matrix to implement detection tasks. Using two datasets of a painting surface and a hot-rolled steel strip surface, our CS-YOLOv5 model outperforms the original version with respect to cost under different positive classes, coefficients, and weight ratios, but also maintains effective detection performance measured by mAP and F1 scores.

Automated summary

Due to the development of deep learning algorithms, defect detection techniques based on deep neural networks have been widely used in industrial production. However, most existing models do not strictly distinguish between different defect categories, which can result in a cost-sensitive issue in the manufacturing process. To address this challenge, we propose a novel supervised classification cost-sensitive learning method and apply it to improve the YOLOv5 model as CS-YOLOv5. This approach introduces classification risk information into the detection model and achieves better performance in terms of cost and detection accuracy.