The analogies between the mammalian primary visual cortex and the structure of CNNs used for image classification tasks suggest that the introduction of an additional preliminary convolutional module inspired by the mathematical modeling of the precortical neuronal circuits can improve robustness with respect to global light intensity and contrast variations in the input images. We validate this hypothesis using the popular databases MNIST, FashionMNIST, and SVHN for these variations once an extra module is added.
Petkovic J., Fioresi R. (2024). Spontaneous Emergence of Robustness to Light Variation in CNNs With a Precortically Inspired Module. NEURAL COMPUTATION, 36(9), 1832-1853 [10.1162/neco_a_01691].
Spontaneous Emergence of Robustness to Light Variation in CNNs With a Precortically Inspired Module
Petkovic J.Membro del Collaboration Group
;Fioresi R.
Membro del Collaboration Group
2024
Abstract
The analogies between the mammalian primary visual cortex and the structure of CNNs used for image classification tasks suggest that the introduction of an additional preliminary convolutional module inspired by the mathematical modeling of the precortical neuronal circuits can improve robustness with respect to global light intensity and contrast variations in the input images. We validate this hypothesis using the popular databases MNIST, FashionMNIST, and SVHN for these variations once an extra module is added.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
