Pooling Methods in Deep Neural Networks, a Review

TL;DR

This paper reviews various pooling methods in deep neural networks, emphasizing their roles in reducing computational cost and overfitting, and discusses their effectiveness in extracting useful features.

Contribution

It provides a comprehensive review of popular pooling techniques in deep neural networks, highlighting their advantages and limitations.

Findings

Pooling reduces feature map dimensions and computational cost.

Different pooling methods vary in effectiveness for feature extraction.

Pooling techniques influence model performance and overfitting control.

Abstract

Nowadays, Deep Neural Networks are among the main tools used in various sciences. Convolutional Neural Network is a special type of DNN consisting of several convolution layers, each followed by an activation function and a pooling layer. The pooling layer is an important layer that executes the down-sampling on the feature maps coming from the previous layer and produces new feature maps with a condensed resolution. This layer drastically reduces the spatial dimension of input. It serves two main purposes. The first is to reduce the number of parameters or weights, thus lessening the computational cost. The second is to control the overfitting of the network. An ideal pooling method is expected to extract only useful information and discard irrelevant details. There are a lot of methods for the implementation of pooling operation in Deep Neural Networks. In this paper, we reviewed some of the famous and useful pooling methods.