What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?

TL;DR

This paper thoroughly explains how to calculate receptive, effective receptive, and projective fields in CNNs, aiding understanding and optimization of these networks for practical applications.

Contribution

It provides detailed methods for calculating these fields in CNNs and extends the approach to deconvolutional networks, enhancing analysis tools.

Findings

Clear formulas for receptive fields in CNNs

Extension of methods to deconvolutional networks

Implications for network analysis and optimization

Abstract

In this work, we explain in detail how receptive fields, effective receptive fields, and projective fields of neurons in different layers, convolution or pooling, of a Convolutional Neural Network (CNN) are calculated. While our focus here is on CNNs, the same operations, but in the reverse order, can be used to calculate these quantities for deconvolutional neural networks. These are important concepts, not only for better understanding and analyzing convolutional and deconvolutional networks, but also for optimizing their performance in real-world applications.