PDE-based group equivariant convolutional neural networks
From MaRDI portal
Publication:6156050
DOI10.1007/s10851-022-01114-xarXiv2001.09046OpenAlexW3001808426WikidataQ114226025 ScholiaQ114226025MaRDI QIDQ6156050
Remco Duits, Jim Portegies, Erik J. Bekkers, Bart M. N. Smets
Publication date: 12 June 2023
Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2001.09046
Related Items (6)
Deep limits of residual neural networks ⋮ Local binary patterns of segments of a binary object for shape analysis ⋮ Functional properties of PDE-based group equivariant convolutional neural networks ⋮ Can generalised divergences help for invariant neural networks? ⋮ Dynamical Systems–Based Neural Networks ⋮ Analysis of (sub-)Riemannian PDE-G-CNNs
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Functional inequalities and Hamilton-Jacobi equations in geodesic spaces
- Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations
- Translating numerical concepts for PDEs into neural architectures
- A cortical based model of perceptual completion in the roto-translation space
- Weighted subcoercive operators on Lie groups
- Estimations of the heat kernel on homogeneous spaces
- Abstract harmonic analysis of continuous wavelet transforms
- Nonsmooth analysis and Hamilton--Jacobi equations on Riemannian manifolds
- A geometric model of multi-scale orientation preference maps via Gabor functions
- Design and processing of invertible orientation scores of 3D images
- A first-order primal-dual algorithm for convex problems with applications to imaging
- Coherent states, wavelets and their generalizations
- Deep neural networks motivated by partial differential equations
- Cyclic schemes for PDE-based image analysis
- Total variation and mean curvature PDEs on the homogeneous space of positions and orientations
- A bio-inspired geometric model for sound reconstruction
- A cortical-inspired geometry for contour perception and motion integration
- Evolution equations on Gabor transforms and their applications
- Metric Hopf-Lax formula with semicontinuous data
- A proposal on machine learning via dynamical systems
- Geometrical optical illusion via sub-Riemannian geodesics in the roto-translation group
- Total roto-translational variation
- Morphological and linear scale spaces for fiber enhancement in DW-MRI
- A PDE Approach to Data-Driven Sub-Riemannian Geodesics in $SE$(2)
- Collaborative Total Variation: A General Framework for Vectorial TV Models
- Sub-Riemannian Mean Curvature Flow for Image Processing
- Numerical Approaches for Linear Left-invariant Diffusions onSE(2), their Comparison to Exact Solutions, and their Applications in Retinal Imaging
- Hypoelliptic Diffusion and Human Vision: A Semidiscrete New Twist
- Introduction to Smooth Manifolds
- Geodesic Methods in Computer Vision and Graphics
- A VERSION OF THE HOPF-LAX FORMULA IN THE HEISENBERG GROUP
- New Approximation of a Scale Space Kernel on SE(3) and Applications in Neuroimaging
- Left-invariant parabolic evolutions on $SE(2)$ and contour enhancement via invertible orientation scores Part I: Linear left-invariant diffusion equations on $SE(2)$
- Left-invariant parabolic evolutions on $SE(2)$ and contour enhancement via invertible orientation scores Part II: Nonlinear left-invariant diffusions on invertible orientation scores
- Integral representations of resolvents and semigroups
- First Order Algorithms in Variational Image Processing
- Computer Vision - ECCV 2004
- An operational calculus for the Euclidean motion group with applications in robotics and polymer science
This page was built for publication: PDE-based group equivariant convolutional neural networks
