Navigation überspringen
Universitätsbibliothek Heidelberg
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Hühnerbein, Ruben [VerfasserIn]   i
 Savarino, Fabrizio [VerfasserIn]   i
 Petra, Stefania [VerfasserIn]   i
 Schnörr, Christoph [VerfasserIn]   i
Titel:Learning adaptive regularization for image labeling using geometric assignment
Verf.angabe:Ruben Hühnerbein, Fabrizio Savarino, Stefania Petra, Christoph Schnörr
Jahr:2021
Umfang:30 S.
Fussnoten: Published online: 6 August 2020 ; Gesehen am 04.10.2021
Titel Quelle:Enthalten in: Journal of mathematical imaging and vision
Ort Quelle:Dordrecht [u.a.] : Springer Science + Business Media B.V, 1992
Jahr Quelle:2021
Band/Heft Quelle:63(2021), 2, Seite 186-215
ISSN Quelle:1573-7683
Abstract:We study the inverse problem of model parameter learning for pixelwise image labeling, using the linear assignment flow and training data with ground truth. This is accomplished by a Riemannian gradient flow on the manifold of parameters that determines the regularization properties of the assignment flow. Using the symplectic partitioned Runge-Kutta method for numerical integration, it is shown that deriving the sensitivity conditions of the parameter learning problem and its discretization commute. A convenient property of our approach is that learning is based on exact inference. Carefully designed experiments demonstrate the performance of our approach, the expressiveness of the mathematical model as well as its limitations, from the viewpoint of statistical learning and optimal control.
DOI:doi:10.1007/s10851-020-00977-2
URL:kostenfrei: Volltext: https://doi.org/10.1007/s10851-020-00977-2
 DOI: https://doi.org/10.1007/s10851-020-00977-2
Datenträger:Online-Ressource
Sprache:eng
K10plus-PPN:1772328294
Verknüpfungen:→ Zeitschrift
 
 
Lokale URL UB: Zum Volltext

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/68786149   QR-Code
zum Seitenanfang