Dual-Tree Wavelet Packet CNNs for Image Classification

Hubert Leterme, Kévin Polisano, Valérie Perrier, Karteek Alahari

Keywords: convolutional neural networks, wavelet packet transform, dual-tree wavelet packet transform, image classification, deep learning, image processing

Abstract: In this paper, we target an important issue of deep convolutional neural networks (CNNs) — the lack of a mathematical understanding of their properties. We present an explicit formalism that is motivated by the similarities between trained CNN kernels and oriented Gabor filters for addressing this problem. The core idea is to constrain the behavior of convolutional layers by splitting them into a succession of wavelet packet decompositions, which are modulated by freely-trained mixture weights. We evaluate our approach with three variants of wavelet decompositions with the AlexNet architecture for image classification as an example. The first variant relies on the separable wavelet packet transform while the other two implement the 2D dual-tree real and complex wavelet packet transforms, taking advantage of their feature extraction properties such as directional selectivity and shift invariance. Our experiments show that we achieve the accuracy rate of standard AlexNet, but with a significantly lower number of parameters, and an interpretation of the network that is grounded in mathematical theory.

One-sentence Summary: We introduce the dual-tree wavelet packet transform into convolutional neural networks in order to constrain their behavior while keeping their predicting power.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=82Y-rMthk