2025 年 16 巻 4 号 p. 878-895
This paper analyzes Convolutional Neural Networks (CNNs) from a spatial frequency perspective using Z-transforms to evaluate kernel transfer functions. By examining which frequency bands kernels respond to, we quantitatively analyze feature processing through CNN layers. Experiments with custom and pre-trained models (InceptionV3, VGG16, ResNet-50, DenseNet-121) reveal CNNs capture high-frequency features in early layers while increasingly focusing on low-frequency features in deeper layers. Kernel pruning experiments demonstrate that kernels with larger weights capturing low-frequency features are critical for model performance. These findings provide insights into CNN feature extraction processes, contributing to improved interpretability and model construction guidelines.
