Maximal function pooling with applications
Computer Vision and Pattern Recognition
2021-03-03 v1 Information Theory
math.IT
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.
Cite
@article{arxiv.2103.01292,
title = {Maximal function pooling with applications},
author = {Wojciech Czaja and Weilin Li and Yiran Li and Mike Pekala},
journal= {arXiv preprint arXiv:2103.01292},
year = {2021}
}
Comments
18 pages, 1 figure, to appear in Excursions in Harmonic Analysis, Volume 6