Maximal function pooling with applications

TL;DR

This paper introduces maxfun pooling, a new pooling method inspired by the Hardy-Littlewood maximal function, which can interpolate between max and average pooling, with applications in convolutional sparse coding and image classification.

Contribution

It proposes a novel pooling strategy called maxfun pooling, offering an alternative and interpolation between max and average pooling methods.

Findings

Maxfun pooling performs competitively in image classification tasks.

It effectively interpolates between max and average pooling.

Demonstrates utility in convolutional sparse coding.

Abstract

Inspired by the Hardy-Littlewood maximal function, we propose a novel pooling strategy which is called maxfun pooling. It is presented both as a viable alternative to some of the most popular pooling functions, such as max pooling and average pooling, and as a way of interpolating between these two algorithms. We demonstrate the features of maxfun pooling with two applications: first in the context of convolutional sparse coding, and then for image classification.