Search Results for author: David Vaillancourt

Found 3 papers, 1 papers with code

MVC-Net: A Convolutional Neural Network Architecture for Manifold-Valued Images With Applications

no code implementations2 Mar 2020 Jose J. Bouza, Chun-Hao Yang, David Vaillancourt, Baba C. Vemuri

Our goal in this paper is to generalize convolutional neural networks (CNN) to the manifold-valued image case which arises commonly in medical imaging and computer vision applications.

Higher Order Gauge Equivariant CNNs on Riemannian Manifolds and Applications

no code implementations26 May 2023 Gianfranco Cortes, Yue Yu, Robin Chen, Melissa Armstrong, David Vaillancourt, Baba C. Vemuri

With the advent of group equivariant convolutions in deep networks literature, spherical CNNs with $\mathsf{SO}(3)$-equivariant layers have been developed to cope with data that are samples of signals on the sphere $S^2$.

Cannot find the paper you are looking for? You can Submit a new open access paper.