将胶囊网络与卷积型柯尔莫哥洛夫-阿诺德网络结合，提升病理图像分类准确率。
Capsule-ConvKAN: A Hybrid Neural Approach to Medical Image Classification
- 融合胶囊网络动态路由与卷积KAN的可解释函数逼近能力
- 在病理图像数据集上达到91.21%准确率，最优表现
- 适合需要高精度与可解释性的医学图像分析任务
本研究全面比较了四种神经网络架构：卷积神经网络、胶囊网络、卷积型柯尔莫哥洛夫-阿诺德网络，以及新提出的胶囊-卷积型柯尔莫哥洛夫-阿诺德网络（Capsule-ConvKAN）。该混合模型结合了胶囊网络的动态路由与空间层次结构优势，以及卷积型柯尔莫哥洛夫-阿诺德网络在函数逼近上的灵活性和可解释性。旨在提升特征表示与分类准确性，尤其针对复杂的现实世界生物医学图像数据。在组织病理学图像数据集上的评估显示，Capsule-ConvKAN取得了91.21%的最高分类准确率。结果表明，该新模型在捕捉空间模式、处理复杂特征方面具有潜力，并能克服传统卷积模型在医学图像分类中的局限性。
原文摘要 · Abstract (English)
This study conducts a comprehensive comparison of four neural network architectures: Convolutional Neural Network, Capsule Network, Convolutional Kolmogorov-Arnold Network, and the newly proposed Capsule-Convolutional Kolmogorov-Arnold Network. The proposed Capsule-ConvKAN architecture combines the dynamic routing and spatial hierarchy capabilities of Capsule Network with the flexible and interpretable function approximation of Convolutional Kolmogorov-Arnold Networks. This novel hybrid model was developed to improve feature representation and classification accuracy, particularly in challenging real-world biomedical image data. The architectures were evaluated on a histopathological image dataset, where Capsule-ConvKAN achieved the highest classification performance with an accuracy of 91.21%. The results demonstrate the potential of the newly introduced Capsule-ConvKAN in capturing spatial patterns, managing complex features, and addressing the limitations of traditional convolutional models in medical image classification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。