Deep Scattering Network with Max-pooling

TL;DR

This paper introduces a scattering-maxp network that integrates max-pooling into the scattering network, maintaining key properties while reducing parameters and increasing speed for image classification.

Contribution

It proposes a novel scattering-maxp network that incorporates max-pooling into the scattering framework, enhancing efficiency without significant performance loss.

Findings

Maintains translation invariance

Reduces number of parameters

Faster than original scattering network

Abstract

Scattering network is a convolutional network, consisting of cascading convolutions using pre-defined wavelets followed by the modulus operator. Since its introduction in 2012, the scattering network is used as one of few mathematical tools explaining components of the convolutional neural networks (CNNs). However, a pooling operator, which is one of main components of conventional CNNs, is not considered in the original scattering network. In this paper, we propose a new network, called scattering-maxp network, integrating the scattering network with the max-pooling operator. We model continuous max-pooling, apply it to the scattering network, and get the scattering-maxp network. We show that the scattering-maxp network shares many useful properties of the scattering network including translation invariance, but with much smaller number of parameters. Numerical experiments show that the use of scattering-maxp does not degrade the performance too much and is much faster than the original one, in image classification tasks.