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
@article{arxiv.1912.05035,
title = {Deep Adaptive Wavelet Network},
author = {Maria Ximena Bastidas Rodriguez and Adrien Gruson and Luisa F. Polania and Shin Fujieda and Flavio Prieto Ortiz and Kohei Takayama and Toshiya Hachisuka},
journal= {arXiv preprint arXiv:1912.05035},
year = {2019}
}