Kolmogorov-Arnold networks for metal surface defect classification
It addresses defect detection in industrial metal surfaces, but is incremental as it adapts a known method to a specific domain.
This paper tackled metal surface defect classification by applying Kolmogorov-Arnold Networks (KAN) to steel surfaces, achieving better accuracy than convolutional neural networks with fewer parameters and faster convergence.
This paper presents the application of Kolmogorov-Arnold Networks (KAN) in classifying metal surface defects. Specifically, steel surfaces are analyzed to detect defects such as cracks, inclusions, patches, pitted surfaces, and scratches. Drawing on the Kolmogorov-Arnold theorem, KAN provides a novel approach compared to conventional multilayer perceptrons (MLPs), facilitating more efficient function approximation by utilizing spline functions. The results show that KAN networks can achieve better accuracy than convolutional neural networks (CNNs) with fewer parameters, resulting in faster convergence and improved performance in image classification.