Deep Network classification by Scattering and Homotopy dictionary learning

10/08/2019
by   John Zarka, et al.
Cole Normale Suprieure
9

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 ILSVRC2012 dataset. The network first applies a scattering transform which linearizes variabilities due to geometric transformations such as translations and small deformations. A sparse l1 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 including ALISTA. Classification results are analyzed over ImageNet.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/09/2018

Polarimetric Convolutional Network for PolSAR Image Classification

The approaches for analyzing the polarimetric scattering matrix of polar...
12/30/2014

Deep Roto-Translation Scattering for Object Classification

Dictionary learning algorithms or supervised deep convolution networks h...
02/10/2022

Coded ResNeXt: a network for designing disentangled information paths

To avoid treating neural networks as highly complex black boxes, the dee...
06/17/2019

PolSAR Image Classification based on Polarimetric Scattering Coding and Sparse Support Matrix Machine

POLSAR image has an advantage over optical image because it can be acqui...
12/18/2020

Separation and Concentration in Deep Networks

Numerical experiments demonstrate that deep neural network classifiers p...
01/19/2021

The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods

A recent line of work showed that various forms of convolutional kernel ...
11/23/2020

Scattering Transform Based Image Clustering using Projection onto Orthogonal Complement

In the last few years, large improvements in image clustering have been ...

Code Repositories

SparseScatNet

Code implementation of paper: Deep Network Classification by Scattering and Homotopy Dictionary Learning


view repo

Please sign up or login with your details

Forgot password? Click here to reset