↪︎ Group Equivariant Convolutional Neural Networks
The goal of this project was to implement and compare group equivariant convolutional neural networks (GCNNs) against standard convolutional neural networks (CNNs) and a smoothed version of CNNs (averaging over all group symmetries) on a binary stereo image classification task (sunny or rainy weather). The group considered in this project is the dihedral group of order 8 which acts on stereo images by rotations and reflections.
GCNNs are a type of neural network that are designed to be equivariant to certain transformations of the input data and were introduced by Taco Cohen and Max Welling in 2016. I did this project as part of the course INF367A on geometric deep learning at the University of Bergen during my PhD.
This implementation can serve as a starting point for anyone interested in exploring group equivariant neural networks further or applying them to other tasks.
