A Nonlocal Graph-PDE and Higher-Order Geometric Integration for Image Labeling

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sitenko, Dmitrij, Boll, Bastian, Schnörr, Christoph
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913487175811072
author Sitenko, Dmitrij
Boll, Bastian
Schnörr, Christoph
author_facet Sitenko, Dmitrij
Boll, Bastian
Schnörr, Christoph
contents This paper introduces a novel nonlocal partial difference equation (G-PDE) for labeling metric data on graphs. The G-PDE is derived as nonlocal reparametrization of the assignment flow approach that was introduced in \textit{J.~Math.~Imaging \& Vision} 58(2), 2017. Due to this parameterization, solving the G-PDE numerically is shown to be equivalent to computing the Riemannian gradient flow with respect to a nonconvex potential. We devise an entropy-regularized difference-of-convex-functions (DC) decomposition of this potential and show that the basic geometric Euler scheme for integrating the assignment flow is equivalent to solving the G-PDE by an established DC programming scheme. Moreover, the viewpoint of geometric integration reveals a basic way to exploit higher-order information of the vector field that drives the assignment flow, in order to devise a novel accelerated DC programming scheme. A detailed convergence analysis of both numerical schemes is provided and illustrated by numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2205_03991
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle A Nonlocal Graph-PDE and Higher-Order Geometric Integration for Image Labeling
Sitenko, Dmitrij
Boll, Bastian
Schnörr, Christoph
Optimization and Control
Computer Vision and Pattern Recognition
Numerical Analysis
This paper introduces a novel nonlocal partial difference equation (G-PDE) for labeling metric data on graphs. The G-PDE is derived as nonlocal reparametrization of the assignment flow approach that was introduced in \textit{J.~Math.~Imaging \& Vision} 58(2), 2017. Due to this parameterization, solving the G-PDE numerically is shown to be equivalent to computing the Riemannian gradient flow with respect to a nonconvex potential. We devise an entropy-regularized difference-of-convex-functions (DC) decomposition of this potential and show that the basic geometric Euler scheme for integrating the assignment flow is equivalent to solving the G-PDE by an established DC programming scheme. Moreover, the viewpoint of geometric integration reveals a basic way to exploit higher-order information of the vector field that drives the assignment flow, in order to devise a novel accelerated DC programming scheme. A detailed convergence analysis of both numerical schemes is provided and illustrated by numerical experiments.
title A Nonlocal Graph-PDE and Higher-Order Geometric Integration for Image Labeling
topic Optimization and Control
Computer Vision and Pattern Recognition
Numerical Analysis
url https://arxiv.org/abs/2205.03991