This paper presents an experimental study of Kolmogorov-Arnold Networks (KANs) applied to computer vision tasks, particularly image classification. KANs introduce learnable activation functions on edges, offering flexible non-linear transformations compared to traditional pre-fixed activation functions with specific neural work like Multi-Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs). While KANs have shown promise mostly in simplified or small-scale datasets, their effectiveness for more complex real-world tasks such as computer vision tasks remains less explored. To fill this gap, this experimental study aims to provide extended observations and insights into the strengths and limitations of KANs. We reveal that although KANs can perform well in specific vision tasks, they face significant challenges, including increased hyperparameter sensitivity and higher computational costs. These limitations suggest that KANs require architectural adaptations, such as integration with other architectures, to be practical for large-scale vision problems. This study focuses on empirical findings rather than proposing new methods, aiming to inform future research on optimizing KANs, in particular computer vision applications or alike.

翻译：本文对应用于计算机视觉任务（特别是图像分类）的Kolmogorov-Arnold网络（KANs）进行了实验研究。与多层感知机（MLPs）和卷积神经网络（CNNs）等采用固定激活函数的传统神经网络不同，KANs在边（edges）上引入了可学习的激活函数，从而提供了更灵活的非线性变换能力。尽管KANs在简化或小规模数据集上已展现出潜力，但其在计算机视觉等复杂现实任务中的有效性仍缺乏充分探索。为填补这一空白，本实验研究旨在对KANs的优势与局限提供更深入的观察与见解。我们发现，虽然KANs在特定视觉任务中表现良好，但其面临显著挑战，包括超参数敏感性增强和计算成本升高。这些局限表明，KANs需要结合其他架构进行结构调整，才能适用于大规模视觉问题。本研究侧重于实证发现而非提出新方法，旨在为未来优化KANs的研究提供参考，特别是在计算机视觉及相关领域的应用。