Valentin Delchevalerie (UNamur)

Title : SO(2) and O(2) Equivariance in Image Recognition with Bessel-Convolutional Neural Networks

Abstract : For many years, it has been shown how much exploiting equivariances can be beneficial when solving image analysis tasks. For example, the superiority of convolutional neural networks (CNNs) compared to dense networks mainly comes from an elegant exploitation of the translation equivariance. Patterns can appear at arbitrary positions and convolutions take this into account to achieve translation invariant operations through weight sharing. Nevertheless, images often involve other symmetries that can also be exploited. It is the case of rotations and reflections that have drawn particular attention and led to the development of multiple equivariant CNN architectures. Among all these methods, Bessel-convolutional neural networks (B-CNNs) exploit a particular decomposition based on Bessel functions to modify the key operation between images and filters and make it by design equivariant to all the continuous set of planar rotations, and also include the incorporation of reflection and multi-scale equivariances.

More information: https://arxiv.org/abs/2304.09214  https://proceedings.neurips.cc/paper/2021/hash/f18224a1adfb7b3dbff668c9b655a35a-Abstract.html

The seminar will take place in Room S08 at the Faculty of Sciences.