Image Labeling Based on Graphical Models Using Wasserstein Messages and Geometric Assignment

10/04/2017
by   Ruben Hühnerbein, et al.
0

We introduce a novel approach to Maximum A Posteriori inference based on discrete graphical models. By utilizing local Wasserstein distances for coupling assignment measures across edges of the underlying graph, a given discrete objective function is smoothly approximated and restricted to the assignment manifold. A corresponding multiplicative update scheme combines in a single process (i) geometric integration of the resulting Riemannian gradient flow and (ii) rounding to integral solutions that represent valid labelings. Throughout this process, local marginalization constraints known from the established LP relaxation are satisfied, whereas the smooth geometric setting results in rapidly converging iterations that can be carried out in parallel for every edge.

READ FULL TEXT

page 24

page 26

page 28

page 29

page 30

page 31

page 32

research
03/16/2016

Image Labeling by Assignment

We introduce a novel geometric approach to the image labeling problem. A...
research
10/22/2019

Learning Adaptive Regularization for Image Labeling Using Geometric Assignment

We study the inverse problem of model parameter learning for pixelwise i...
research
06/30/2023

Quantum State Assignment Flows

This paper introduces assignment flows for density matrices as state spa...
research
07/11/2021

On the Expressiveness of Assignment Messages

In this note we prove that the class of valuation functions representabl...
research
02/26/2020

Assignment Flows for Data Labeling on Graphs: Convergence and Stability

The assignment flow recently introduced in the J. Math. Imaging and Visi...
research
05/09/2022

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

This paper introduces a novel nonlocal partial difference equation (PDE)...

Please sign up or login with your details

Forgot password? Click here to reset