Kernels on Riemannian manifolds

DOI10.1007/978-3-319-22957-7_3zbMATH Open1357.68252arXiv1412.0265OpenAlexW2263570427MaRDI QIDQ2807043FDOQ2807043

Authors: Sadeep Jayasumana, Mathieu Salzmann, Richard I. Hartley 

Publication date: 19 May 2016

Published in: Riemannian Computing in Computer Vision (Search for Journal in Brave)

Abstract: In this paper, we develop an approach to exploiting kernel methods with manifold-valued data. In many computer vision problems, the data can be naturally represented as points on a Riemannian manifold. Due to the non-Euclidean geometry of Riemannian manifolds, usual Euclidean computer vision and machine learning algorithms yield inferior results on such data. In this paper, we define Gaussian radial basis function (RBF)-based positive definite kernels on manifolds that permit us to embed a given manifold with a corresponding metric in a high dimensional reproducing kernel Hilbert space. These kernels make it possible to utilize algorithms developed for linear spaces on nonlinear manifold-valued data. Since the Gaussian RBF defined with any given metric is not always positive definite, we present a unified framework for analyzing the positive definiteness of the Gaussian RBF on a generic metric space. We then use the proposed framework to identify positive definite kernels on two specific manifolds commonly encountered in computer vision: the Riemannian manifold of symmetric positive definite matrices and the Grassmann manifold, i.e., the Riemannian manifold of linear subspaces of a Euclidean space. We show that many popular algorithms designed for Euclidean spaces, such as support vector machines, discriminant analysis and principal component analysis can be generalized to Riemannian manifolds with the help of such positive definite Gaussian kernels.

Full work available at URL: https://arxiv.org/abs/1412.0265

Recommendations

• Nonlinear mean shift over Riemannian manifolds
• Probabilistic learning vector quantization on manifold of symmetric positive definite matrices
• Kernel Methods in Computer Vision
• Diffusion kernels on statistical manifolds
• Nonparametric Regression between General Riemannian Manifolds

Mathematics Subject Classification ID

Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Methods of global Riemannian geometry, including PDE methods; curvature restrictions (53C21) Machine vision and scene understanding (68T45)

Cites Work

• Shape Manifolds, Procrustean Metrics, and Complex Projective Spaces
• Title not available (Why is that?)
• Title not available (Why is that?)
• The Geometry of Algorithms with Orthogonality Constraints
• A Riemannian framework for tensor computing
• Choosing multiple parameters for support vector machines

Cited In (18)

• The Gaussian kernel on the circle and spaces that admit isometric embeddings of the circle
• Probabilistic learning vector quantization on manifold of symmetric positive definite matrices
• Manifold interpolation
• Manin kernels
• Perturbed kernel approximation on homogeneous manifolds
• Gaussian kernels on nonsimply connected closed Riemannian manifolds are never positive definite
• A Riemann-Stein kernel method
• Matrix-valued kernels for shape deformation analysis
• Kernel Approximation on Manifolds I: Bounding the Lebesgue Constant
• A kernel view on manifold sub-sampling based on Karcher variance optimization
• Welcome to Riemannian computing in computer vision
• Efficient clustering on Riemannian manifolds: a kernelised random projection approach
• Designing a boosted classifier on Riemannian manifolds
• Expanding the family of Grassmannian kernels: an embedding perspective
• Algorithmic Learning Theory
• Title not available (Why is that?)
• Diffusion kernels on statistical manifolds
• Mixed region covariance discriminative learning for image classification on Riemannian manifolds

This page was built for publication: Kernels on Riemannian manifolds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2807043)