A precortical module for robust CNNs to light variations
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 45 references that are in the map. First posted on arXiv 15 Feb 2022.
Builds on
9 of 45 references.
References · 9
- 2016Group Equivariant Convolutional Networkscited by 1,154
- 2019B-Spline CNNs on Lie Groupscited by 97
- 2017Critical Learning Periods in Deep Neural Networkscited by 78
- 2017Non-linear Convolution Filters for CNN-based Learningcited by 38
- 2018A rotation-equivariant convolutional neural network model of primary visual cortexcited by 15
- 2021On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classificationcited by 15
- 2015Time-causal and time-recursive spatio-temporal receptive fieldscited by 7
- 2018From receptive profiles to a metric model of V1cited by 2
- 2019LGN-CNN: a biologically inspired CNN architecturecited by 2
Built on by
Not cited yet.