Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations

DOI10.1007/978-3-030-75549-2_3zbMath1484.68206OpenAlexW3159319455MaRDI QIDQ826129

Jim Portegies, Remco Duits, Bart M. N. Smets, Erik J. Bekkers

Publication date: 20 December 2021

Full work available at URL: https://doi.org/10.1007/978-3-030-75549-2_3

zbMATH Keywords

PDEsconvolutional neural networksCramér transformgeometric deep learningmorphological convolutionsscale-space theory

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10) PDEs in connection with computer science (35Q68)

Related Items (6)

Designing rotationally invariant neural networks from PDEs and variational methods ⋮ Connections between numerical algorithms for PDEs and neural networks ⋮ PDE-based group equivariant convolutional neural networks ⋮ Functional properties of PDE-based group equivariant convolutional neural networks ⋮ Analysis of (sub-)Riemannian PDE-G-CNNs ⋮ Scale-covariant and scale-invariant Gaussian derivative networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Morphological counterparts of linear shift-invariant scale-spaces
• Asymptotic expansion of the hypoelliptic heat kernel on the diagonal
• Weighted subcoercive operators on Lie groups
• Optimal paths for variants of the 2D and 3D Reeds-Shepp car with applications in image analysis
• Left-invariant parabolic evolutions on $SE(2)$ and contour enhancement via invertible orientation scores Part I: Linear left-invariant diffusion equations on $SE(2)$
• Lévy flights: Exact results and asymptotics beyond all orders
• Optimal control and viscosity solutions of Hamilton-Jacobi-Bellman equations

This page was built for publication: Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations