Can I read Convolution Goes Higher-order: a Biologically Inspired Mechanism Empowers Image Classification on EtoBox?

Convolution Goes Higher-order: a Biologically Inspired Mechanism Empowers Image Classification by Azeglio, Simone; Marre, Olivier; Neri, Peter; Ferrari, Ulisse is a scholarly article available to read on EtoBox.

What is Convolution Goes Higher-order: a Biologically Inspired Mechanism Empowers Image Classification about?

We propose a novel approach to image classification inspired by complex nonlinear biological visual processing, whereby classical convolutional neural networks (CNNs) are equipped with learnable higher-order convolutions. Our model incorporates a Volterra-like expansion of the convolution operator, capturing multiplicative interactions akin to those observed in early and advanced stages of biological visual processing. We evaluated this approach on synthetic datasets by measuring sensitivity to testing higher-order correlations and performance in standard benchmarks (MNIST, FashionMNIST, CIFAR10, CIFAR100 and Imagenette). Our architecture outperforms traditional CNN baselines, and achieves optimal performance with expansions up to 3rd/4th order, aligning remarkably well with the distribution of pixel intensities in natural images. Through systematic perturbation analysis, we validate this alignment by isolating the contributions of specific image statistics to model performance, demonstrating how different orders of convolution process distinct aspects of visual information. Furthermore, Representational Similarity Analysis reveals distinct geometries across network layers, indicat

Author

Azeglio, Simone; Marre, Olivier; Neri, Peter; Ferrari, Ulisse

Published

2024

Language

EN