2 papers
cs.CV2024
On the effectiveness of Rotation-Equivariance in U-Net: A Benchmark for Image Segmentation
Robin Ghyselinck, Valentin Delchevalerie, Bruno Dumas +1
Numerous studies have recently focused on incorporating different variations of equivariance in Convolutional Neural Networks (CNNs). In particular, rotation-equivariance has gathe…
cs.CV2023
SO(2) and O(2) Equivariance in Image Recognition with Bessel-Convolutional Neural Networks
Valentin Delchevalerie, Alexandre Mayer, Adrien Bibal +1
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 networ…