Spatially Regularized Geometric Assignment for Unsupervised Label Learning on Manifolds

We introduce a smooth coupled system of Riemannian flows for simultaneously learning a dictionary of manifold‐valued prototypes and assigning these prototypes to the image data in a spatially coherent way.

Saved in:

Bibliographic Details
Main Authors:	Zern, Artjom (Author) , Zisler, Matthias (Author) , Petra, Stefania (Author) , Schnörr, Christoph (Author)
Format:	Article (Journal)
Language:	English
Published:	18 November 2019
In:	Proceedings in applied mathematics and mechanics Year: 2019, Volume: 19, Issue: 1
ISSN:	1617-7061
DOI:	10.1002/pamm.201900258
Online Access:	Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1002/pamm.201900258 Verlag, lizenzpflichtig, Volltext: https://onlinelibrary.wiley.com/doi/10.1002/pamm.201900258
Author Notes:	Artjom Zern, Matthias Zisler, Stefania Petra, and Christoph Schnörr

Description
Summary:	We introduce a smooth coupled system of Riemannian flows for simultaneously learning a dictionary of manifold‐valued prototypes and assigning these prototypes to the image data in a spatially coherent way.
Item Description:	Gesehen am 20.01.2021
Physical Description:	Online Resource
ISSN:	1617-7061
DOI:	10.1002/pamm.201900258