Maximal function pooling with applications

2021/03/01 by Wojciech Czaja, Weilin Li, Czaja, Wojciech +5
Computer Science · #Advanced Data Compression Techniques #Algorithms and Data Compression #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Information Theory (cs.IT) #Medical Image Segmentation Techniques

paper · pdf · doi:10.48550/arxiv.2103.01292

openalex publication_date 2021/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• The Theoretical Expressiveness of Maxpooling
• Comparison of Methods Generalizing Max- and Average-Pooling
• Sorted Pooling in Convolutional Networks for One-shot Learning
• Generalized Max Pooling
• Fractional Max-Pooling