# A precortical module for robust CNNs to light variations

Source: [A precortical module for robust CNNs to light variations](<https://www.sota2.com/research/paper/68fa58fe1e209131ce9b2e10>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T15:38:29.793Z

Authors: R. Fioresi, J. Petkovic

Published: 2022-02-15T14:18:40.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2202.07432>)

[PDF](<https://arxiv.org/pdf/2202.07432.pdf>)