DeepAI AI Chat
Log In Sign Up

A precortical module for robust CNNs to light variations

by   R. Fioresi, et al.

We present a simple mathematical model for the mammalian low visual pathway, taking into account its key elements: retina, lateral geniculate nucleus (LGN), primary visual cortex (V1). The analogies between the cortical level of the visual system and the structure of popular CNNs, used in image classification tasks, suggests the introduction of an additional preliminary convolutional module inspired to precortical neuronal circuits to improve robustness with respect to global light intensity and contrast variations in the input images. We validate our hypothesis on the popular databases MNIST, FashionMNIST and SVHN, obtaining significantly more robust CNNs with respect to these variations, once such extra module is added.


page 1

page 2

page 3

page 4


Logarithmic Morphological Neural Nets robust to lighting variations

Morphological neural networks allow to learn the weights of a structurin...

A trainable monogenic ConvNet layer robust in front of large contrast changes in image classification

Convolutional Neural Networks (ConvNets) at present achieve remarkable p...

A Discriminative Channel Diversification Network for Image Classification

Channel attention mechanisms in convolutional neural networks have been ...

Convolutional Neural Networks Deceived by Visual Illusions

Visual illusions teach us that what we see is not always what it is repr...

Learning to Adapt to Light

Light adaptation or brightness correction is a key step in improving the...

Global-Local Processing in Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have achieved outstanding performan...