In response to the rapidly evolving demands of modern manufacturing, traditional manual inspection of metal surface defects in industry can no longer meet the requirements for fast and high-precision detection. To address this challenge, this paper presents an enhanced efficient detection algorithm based on YOLOv8. The model improves multi-scale feature perception and computational efficiency by incorporating Dual Convolution (DualConv) and Large Kernel Separable Attention (LSKA) into the neck and backbone, respectively. Additionally, wavelet pooling is introduced to optimize the sampling process. These enhancements reduce the model’s parameters while further increasing its accuracy. Compared to the original YOLOv8, GFLOPs are reduced by 14.8%, parameters by 13.6%, and mAP50 and mAP50-95 on the NEU-DET dataset are improved by 1.2% and 0.4%, respectively. Experimental results demonstrate that the improved model not only effectively reduces computational overhead but also enhances accuracy in metal defect detection tasks, showing significant potential for practical applications.