Deep Adaptive Wavelet Network

TL;DR

This paper introduces a systematic, interpretable deep neural network that integrates multiresolution wavelet analysis via the lifting scheme, reducing hyper-parameter tuning while maintaining competitive accuracy in image classification.

Contribution

It presents a novel deep wavelet network design that is interpretable, systematically constructed, and capable of learning wavelet coefficients end-to-end.

Findings

Requires less hyper-parameter tuning

Achieves competitive accuracy in image classification

Provides interpretability through wavelet analysis

Abstract

Even though convolutional neural networks have become the method of choice in many fields of computer vision, they still lack interpretability and are usually designed manually in a cumbersome trial-and-error process. This paper aims at overcoming those limitations by proposing a deep neural network, which is designed in a systematic fashion and is interpretable, by integrating multiresolution analysis at the core of the deep neural network design. By using the lifting scheme, it is possible to generate a wavelet representation and design a network capable of learning wavelet coefficients in an end-to-end form. Compared to state-of-the-art architectures, the proposed model requires less hyper-parameter tuning and achieves competitive accuracy in image classification tasks