FrequentNet: A Novel Interpretable Deep Learning Model for Image Classification

TL;DR

FrequentNet introduces an interpretable deep learning approach for image classification that selects frequency domain basis filters, offering physical insights and improved training efficiency over traditional CNNs.

Contribution

The paper presents a novel deep learning model that uses frequency domain basis filters instead of learned filters, enhancing interpretability and training efficiency.

Findings

Provides physical insights through frequency basis analysis

Reduces training time compared to CNNs

Enhances model interpretability

Abstract

This paper has proposed a new baseline deep learning model of more benefits for image classification. Different from the convolutional neural network(CNN) practice where filters are trained by back propagation to represent different patterns of an image, we are inspired by a method called "PCANet" in "PCANet: A Simple Deep Learning Baseline for Image Classification?" to choose filter vectors from basis vectors in frequency domain like Fourier coefficients or wavelets without back propagation. Researchers have demonstrated that those basis in frequency domain can usually provide physical insights, which adds to the interpretability of the model by analyzing the frequencies selected. Besides, the training process will also be more time efficient, mathematically clear and interpretable compared with the "black-box" training process of CNN.