Parsimonious Labeling

Abstract : We propose a new family of discrete energy minimization problems, which we call parsimonious labeling. Our energy function consists of unary potentials and high-order clique potentials. While the unary potentials are arbitrary, the clique potentials are proportional to the diversity of the set of unique labels assigned to the clique. Intuitively, our energy function encourages the labeling to be parsimonious , that is, use as few labels as possible. This in turn allows us to capture useful cues for important computer vision applications such as stereo correspondence and image denoising. Furthermore, we propose an efficient graph-cuts based algorithm for the parsimonious labeling problem that provides strong theoretical guarantees on the quality of the solution. Our algorithm consists of three steps. First, we approximate a given diversity using a mixture of a novel hierarchical P n Potts model. Second, we use a divide-and-conquer approach for each mixture component, where each subproblem is solved using an efficient α-expansion algorithm. This provides us with a small number of putative la-belings, one for each mixture component. Third, we choose the best putative labeling in terms of the energy value. Using both synthetic and standard real datasets, we show that our algorithm significantly outperforms other graph-cuts based approaches.
Type de document :
Communication dans un congrès
ICCV 2015 - International Conference on Computer Vision 2015, Dec 2015, Santiago, Chile. 2015
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01223973
Contributeur : M. Pawan Kumar <>
Soumis le : mardi 3 novembre 2015 - 17:24:27
Dernière modification le : vendredi 6 avril 2018 - 13:32:01
Document(s) archivé(s) le : jeudi 4 février 2016 - 11:27:37

Fichier

DK-ICCV2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01223973, version 1

Citation

Puneet Kumar Dokania, M. Pawan Kumar. Parsimonious Labeling. ICCV 2015 - International Conference on Computer Vision 2015, Dec 2015, Santiago, Chile. 2015. 〈hal-01223973〉

Partager

Métriques

Consultations de la notice

266

Téléchargements de fichiers

104