Understanding convolutional neural networks through Z-transform: Frequency domain analysis of kernel feature extraction
Sora Togawa, Kenya Jin’no · Nonlinear Theory and Its Applications IEICE · 2025
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.