# A precortical module for robust CNNs to light variations

arXiv: https://arxiv.org/abs/2202.07432 · HTML: https://mlsanity.com/paper/2202.07432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 45 references that are in the map.
- First posted on arXiv 15 Feb 2022.

## Builds on (most cited first, 9 of 9)

- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [B-Spline CNNs on Lie Groups](https://mlsanity.com/paper/1909.12057/) (2019)
- [Critical Learning Periods in Deep Neural Networks](https://mlsanity.com/paper/1711.08856/) (2017)
- [Non-linear Convolution Filters for CNN-based Learning](https://mlsanity.com/paper/1708.07038/) (2017)
- [A rotation-equivariant convolutional neural network model of primary visual cortex](https://mlsanity.com/paper/1809.10504/) (2018)
- [On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification](https://mlsanity.com/paper/2106.07091/) (2021)
- [Time-causal and time-recursive spatio-temporal receptive fields](https://mlsanity.com/paper/1504.02648/) (2015)
- [From receptive profiles to a metric model of V1](https://mlsanity.com/paper/1803.05783/) (2018)
- [LGN-CNN: a biologically inspired CNN architecture](https://mlsanity.com/paper/1911.06276/) (2019)

## Abstract (arXiv)

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.