Deep Network Classification by Scattering and Homotopy Dictionary Learning
Abstract
We introduce a sparse scattering deep convolutional neural network, which provides a simple model to analyze properties of deep representation learning for classification. Learning a single dictionary matrix with a classifier yields a higher classification accuracy than AlexNet over the ImageNet 2012 dataset. The network first applies a scattering transform that linearizes variabilities due to geometric transformations such as translations and small deformations. A sparse dictionary coding reduces intra-class variability while preserving class separation through projections over unions of linear spaces. It is implemented in a deep convolutional network with a homotopy algorithm having an exponential convergence. A convergence proof is given in a general framework that includes ALISTA. Classification results are analyzed on ImageNet.
Cite
@article{arxiv.1910.03561,
title = {Deep Network Classification by Scattering and Homotopy Dictionary Learning},
author = {John Zarka and Louis Thiry and Tomás Angles and Stéphane Mallat},
journal= {arXiv preprint arXiv:1910.03561},
year = {2020}
}