Unsupervised assignment flow: label learning on feature manifolds by spatially regularized geometric assignment

DOI10.1007/s10851-019-00935-7zbMath1483.68453arXiv1904.10863OpenAlexW3103301888MaRDI QIDQ2203373

Artjom Zern, Matthias Zisler, Stefania Petra, Christoph Schnörr

Publication date: 6 October 2020

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

Full work available at URL: https://arxiv.org/abs/1904.10863

zbMATH Keywords

unsupervised learninginformation geometrydivergence functionassignment flowfeature manifolds

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45) Information geometry (statistical aspects) (62B11)

Related Items (6)

A Nonlocal Graph-PDE and Higher-Order Geometric Integration for Image Labeling ⋮ Self-Assignment Flows for Unsupervised Data Labeling on Graphs ⋮ Learning adaptive regularization for image labeling using geometric assignment ⋮ Assignment flow for order-constrained OCT segmentation ⋮ Continuous-domain assignment flows ⋮ Assignment flows for data labeling on graphs: convergence and stability

Uses Software

• mftoolbox

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonlinear mean shift over Riemannian manifolds
• Kernel methods in machine learning
• Image labeling by assignment
• Iterative multiplicative filters for data labeling
• Why Use Sobolev Metrics on the Space of Curves
• Introduction to Smooth Manifolds
• Elementary Morphology for SO(2)- and SO(3)-Orientation Fields
• Positive Definite Matrices: Data Representation and Applications to Computer Vision
• Assignment Flows
• The estimation of the gradient of a density function, with applications in pattern recognition
• Riemannian center of mass and mollifier smoothing
• Information Geometry
• Functions of Matrices
• Riemannian geometry and geometric analysis

This page was built for publication: Unsupervised assignment flow: label learning on feature manifolds by spatially regularized geometric assignment