Graphical model parameter learning by inverse linear programming
We introduce two novel methods for learning parameters of graphical models for image labelling. The following two tasks underline both methods: (i) perturb model parameters based on given features and ground truth labelings, so as to exactly reproduce these labelings as optima of the local polytope...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Dokumenttyp: | Kapitel/Artikel Konferenzschrift |
| Sprache: | Englisch |
| Veröffentlicht: |
18 May 2017
|
| In: |
Scale Space and Variational Methods in Computer Vision
Year: 2017, Pages: 323-334 |
| DOI: | 10.1007/978-3-319-58771-4_26 |
| Schlagworte: | |
| Online-Zugang: | Verlag, Volltext: http://dx.doi.org/10.1007/978-3-319-58771-4_26 Verlag, Volltext: https://link.springer.com/chapter/10.1007/978-3-319-58771-4_26 
|
| Verfasserangaben: | Vera Trajkovska, Paul Swoboda, Freddie Åström, Stefania Petra |
| Zusammenfassung: | We introduce two novel methods for learning parameters of graphical models for image labelling. The following two tasks underline both methods: (i) perturb model parameters based on given features and ground truth labelings, so as to exactly reproduce these labelings as optima of the local polytope relaxation of the labelling problem; (ii) train a predictor for the perturbed model parameters so that improved model parameters can be applied to the labelling of novel data. Our first method implements task (i) by inverse linear programming and task (ii) using a regressor e.g. a Gaussian process. Our second approach simultaneously solves tasks (i) and (ii) in a joint manner, while being restricted to linearly parameterised predictors. Experiments demonstrate the merits of both approaches. |
|---|---|
| Beschreibung: | Gesehen am 15.03.2018 |
| Beschreibung: | Online Resource |
| ISBN: | 9783319587714 |
| DOI: | 10.1007/978-3-319-58771-4_26 |