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.
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
18 November 2019
|
| In: |
Proceedings in applied mathematics and mechanics
Year: 2019, Jahrgang: 19, Heft: 1 |
| ISSN: | 1617-7061 |
| DOI: | 10.1002/pamm.201900258 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1002/pamm.201900258 Verlag, lizenzpflichtig, Volltext: https://onlinelibrary.wiley.com/doi/10.1002/pamm.201900258 
|
| Verfasserangaben: | Artjom Zern, Matthias Zisler, Stefania Petra, and Christoph Schnörr |
| Zusammenfassung: | 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. |
|---|---|
| Beschreibung: | Gesehen am 20.01.2021 |
| Beschreibung: | Online Resource |
| ISSN: | 1617-7061 |
| DOI: | 10.1002/pamm.201900258 |