Learning adaptive regularization for image labeling using geometric assignment

DOI10.1007/S10851-020-00977-2MaRDI QIDQ2031748zbMATH OpenOpenAlexFDO

Authors Ruben Hühnerbein, Fabrizio Savarino, Stefania Petra, Christoph Schnörr

Publication date 14 June 2021

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

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1910.09976

zbMATH Keywords

adaptive regularizationassignment flowassignment manifolddynamical systemsevolutionary dynamicsimage labelingparameter learningreplicator equationsensitivity analysis

Mathematics Subject Classification ID

Computer science (68-XX) Information and communication theory, circuits (94-XX)

Recommendations

• Image labeling based on graphical models using Wasserstein messages and geometric assignment
• Label propagation via local geometry preserving for deep semi-supervised image recognition
• Unsupervised assignment flow: label learning on feature manifolds by spatially regularized geometric assignment
• Learning linearized assignment flows for image labeling
• Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
• MAP image labeling using Wasserstein messages and geometric assignment
• Flexible semi-supervised embedding based on adaptive loss regression: application to image categorization

Cites work

• A proposal on machine learning via dynamical systems
• Adjoint Sensitivity Analysis for Differential-Algebraic Equations: The Adjoint DAE System and Its Numerical Solution
• Assignment flows
• Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms
• Estimating the ``wrong graphical model: benefits in the computation-limited setting
• Geometric Numerical Integration
• Geometric numerical integration of the assignment flow
• scientific article; zbMATH DE number 3473616 (Why is no real title available?)
• scientific article; zbMATH DE number 1560711 (Why is no real title available?)
• Image labeling based on graphical models using Wasserstein messages and geometric assignment
• Image labeling by assignment
• Information geometry
• Introduction to Smooth Manifolds
• MAP Estimation Via Agreement on Trees: Message-Passing and Linear Programming
• Riemannian geometry and geometric analysis
• Runge-Kutta methods in optimal control and the transformed adjoint system
• Solving Ordinary Differential Equations I
• Stable architectures for deep neural networks
• Symplectic Runge-Kutta schemes for adjoint equations, automatic differentiation, optimal control, and more
• Unsupervised assignment flow: label learning on feature manifolds by spatially regularized geometric assignment

Cited in

(12)

• Image labeling by assignment
• Assignment flow for order-constrained OCT segmentation
• Assignment flows for data labeling on graphs: convergence and stability
• Unsupervised assignment flow: label learning on feature manifolds by spatially regularized geometric assignment
• Image labeling based on graphical models using Wasserstein messages and geometric assignment
• Graphical model parameter learning by inverse linear programming
• Numerical integration of Riemannian gradient flows for image labeling
• MAP image labeling using Wasserstein messages and geometric assignment
• A Nonlocal Graph-PDE and Higher-Order Geometric Integration for Image Labeling
• Learning adaptive regularization for image labeling using geometric assignment
• Riemannian patch assignment gradient flows
• Learning linear assignment flows for image labeling via exponential integration

This page was built for publication: Learning adaptive regularization for image labeling using geometric assignment

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2031748)