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

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.

Fix typo mistake on equations (2) and (3). The "summation" should be the "product" instead

Cited by in corpus (8)

• PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking
• DenseNet Models for Tiny ImageNet Classification
• Using deep generative neural networks to account for model errors in Markov chain Monte Carlo inversion
• Evaluation, Tuning and Interpretation of Neural Networks for Meteorological Applications
• Deep Learning for Robust Motion Segmentation with Non-Static Cameras
• Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction
• Real-time Human Detection Model for Edge Devices
• Density-embedding layers: a general framework for adaptive receptive fields