Weight-guided feature fusion and non-local balance model for aluminum surface defect detection

Abstract

Aluminum surface defect detection plays a crucial role in the manufacturing industry. Due to the complexity of aluminum surface defects, the existing defect detection methods have false and missed detection problems. To address the characteristics of aluminum surface defects and the problems of existing methods, we propose a weight-guided feature fusion and non-local balance model to improve the detection effect. Firstly, we design the feature extraction network cross-stage partial ConvNeXt, which achieves adequate feature extraction while reducing the model’s size. In addition, we propose a weight-guided feature fusion and non-local balanced feature pyramid (WBFPN). Specifically, we design a weight-guided feature fusion module to replace the simple feature fusion method so that the WBFPN can suppress interference information when fusing feature maps at different scales. The non-local balancing module captures the long-range dependencies of image features and effectively balances small target defects’ detail and semantic information. Finally, the confidence loss was redefined to effectively solve the problem of poor detection effect caused by the imbalance of positive and negative samples. Experimental results show that the average accuracy of the proposed model reaches 91.9%, and the detection speed is high, which meets the requirement of real-time defect detection.