FrequentNet : A Novel Interpretable Deep Learning Model for Image Classification

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 an image, we inspired method called PCANet choose filter vectors basis in frequency domain like Fourier coefficients or wavelets without propagation. Researchers have demonstrated that those can usually provide physical insights, which adds interpretability analyzing frequencies selected. Besides, training process will also be time efficient, mathematically clear and interpretable compared with black-box CNN.