Original Pdf: pdf
Code: [![github](/images/github_icon.svg) j-zarka/SparseScatNet](https://github.com/j-zarka/SparseScatNet)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1910.03561/code)
TL;DR: A scattering transform followed by supervised dictionary learning reaches a higher accuracy than AlexNet on ImageNet.
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 $\ell^1$ 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.
Keywords: dictionary learning, scattering transform, sparse coding, imagenet