Analysis of (sub-)Riemannian PDE-G-CNNs

DOI10.1007/S10851-023-01147-WarXiv2210.00935OpenAlexW4366003524MaRDI QIDQ6186783FDOQ6186783

Authors: Gijs Bellaard, Daan L. J. Bon, Gautam Pai, Bart M. N. Smets, Remco Duits 

Publication date: 10 January 2024

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Abstract: Group equivariant convolutional neural networks (G-CNNs) have been successfully applied in geometric deep learning. Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network. The recently introduced framework of PDE-based G-CNNs (PDE-G-CNNs) generalises G-CNNs. PDE-G-CNNs have the core advantages that they simultaneously 1) reduce network complexity, 2) increase classification performance, and 3) provide geometric interpretability. Their implementations primarily consist of linear and morphological convolutions with kernels. In this paper we show that the previously suggested approximative morphological kernels do not always accurately approximate the exact kernels accurately. More specifically, depending on the spatial anisotropy of the Riemannian metric, we argue that one must resort to sub-Riemannian approximations. We solve this problem by providing a new approximative kernel that works regardless of the anisotropy. We provide new theorems with better error estimates of the approximative kernels, and prove that they all carry the same reflectional symmetries as the exact ones. We test the effectiveness of multiple approximative kernels within the PDE-G-CNN framework on two datasets, and observe an improvement with the new approximative kernels. We report that the PDE-G-CNNs again allow for a considerable reduction of network complexity while having comparable or better performance than G-CNNs and CNNs on the two datasets. Moreover, PDE-G-CNNs have the advantage of better geometric interpretability over G-CNNs, as the morphological kernels are related to association fields from neurogeometry.

Full work available at URL: https://arxiv.org/abs/2210.00935

Recommendations

• Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations
• Homogeneous vector bundles and \(G\)-equivariant convolutional neural networks
• Functional properties of PDE-based group equivariant convolutional neural networks
• Analysis of deep convolutional networks from group theory viewpoint

zbMATH Keywords

Riemannian geometrysub-Riemannian geometryconvolutional neural networksPDEsgeometric deep learningmorphological convolutionsscale space theory

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) PDEs in connection with computer science (35Q68)

Cites Work

• Title not available (Why is that?)
• Cut locus and optimal synthesis in the sub-Riemannian problem on the group of motions of a plane
• A cortical based model of perceptual completion in the roto-translation space
• Nonsmooth analysis and Hamilton--Jacobi equations on Riemannian manifolds
• Maxwell strata in sub-Riemannian problem on the group of motions of a plane
• Weak KAM theorem on non compact manifolds
• Left-invariant parabolic evolutions on \(SE(2)\) and contour enhancement via invertible orientation scores. I: Linear left-invariant diffusion equations on \(SE(2)\)
• Association fields via cuspless sub-Riemannian geodesics in SE(2)
• Morphological and linear scale spaces for fiber enhancement in DW-MRI
• A PDE approach to data-driven sub-Riemannian geodesics in \(\mathrm{SE}(2)\)
• Morphological counterparts of linear shift-invariant scale-spaces
• Title not available (Why is that?)
• Weighted subcoercive operators on Lie groups
• Optimal paths for variants of the 2D and 3D Reeds-Shepp car with applications in image analysis
• Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations
• Extension of mathematical morphology in Riemannian spaces
• Nilpotent approximations of sub-Riemannian distances for fast perceptual grouping of blood vessels in 2D and 3D
• A geometric model of multi-scale orientation preference maps via Gabor functions
• Elements of neurogeometry. Functional architectures of vision. Translated from the French by the author
• Geometrical optical illusion via sub-Riemannian geodesics in the roto-translation group
• PDE-based group equivariant convolutional neural networks

Cited In (1)

• Functional properties of PDE-based group equivariant convolutional neural networks

This page was built for publication: Analysis of (sub-)Riemannian PDE-G-CNNs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6186783)