Unsupervised assignment flow

• Verfasst von: Zern, Artjom [VerfasserIn]
• Verfasst von: Zisler, Matthias [VerfasserIn]
• Verfasst von: Petra, Stefania [VerfasserIn]
• Verfasst von: Schnörr, Christoph [VerfasserIn]
• Titel: Unsupervised assignment flow
• Titelzusatz: label learning on feature manifolds by spatially regularized geometric assignment
• Verf.angabe: Artjom Zern, Matthias Zisler, Stefania Petra, Christoph Schnörr
• Jahr: 2020
• Jahr des Originals: 2019
• Umfang: 25 S.
• Fussnoten: Published online: 14 December 2019 ; Gesehen am 24.08.2020
• Titel Quelle: Enthalten in: Journal of mathematical imaging and vision
• Ort Quelle: Dordrecht [u.a.] : Springer Science + Business Media B.V, 1992
• Jahr Quelle: 2020
• Band/Heft Quelle: 62(2020), 6, Seite 982-1006
• ISSN Quelle: 1573-7683
• DOI: doi:10.1007/s10851-019-00935-7
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1727695518

Abstract

This paper introduces the unsupervised assignment flow that couples the assignment flow for supervised image labeling (Åström et al. in J Math Imaging Vis 58(2):211-238, 2017) with Riemannian gradient flows for label evolution on feature manifolds. The latter component of the approach encompasses extensions of state-of-the-art clustering approaches to manifold-valued data. Coupling label evolution with the spatially regularized assignment flow induces a sparsifying effect that enables to learn compact label dictionaries in an unsupervised manner. Our approach alleviates the requirement for supervised labeling to have proper labels at hand, because an initial set of labels can evolve and adapt to better values while being assigned to given data. The separation between feature and assignment manifolds enables the flexible application which is demonstrated for three scenarios with manifold-valued features. Experiments demonstrate a beneficial effect in both directions: adaptivity of labels improves image labeling, and steering label evolution by spatially regularized assignments leads to proper labels, because the assignment flow for supervised labeling is exactly used without any approximation for label learning.