Parameter Estimation and Energy Minimization for Region-based Semantic Segmentation

Abstract : We consider the problem of parameter estimation and energy minimization for a region-based semantic segmentation model. The model divides the pixels of an image into non-overlapping connected regions, each of which is to a semantic class. In the context of energy minimization, the main problem we face is the large number of putative pixel-to-region assignments. We address this problem by designing an accurate linear programming based approach for selecting the best set of regions from a large dictionary. The dictionary is constructed by merging and intersecting segments obtained from multiple bottom-up over-segmentations. The linear program is solved efficiently using dual decomposition. In the context of parameter estimation, the main problem we face is the lack of fully supervised data. We address this issue by developing a principled framework for parameter estimation using diverse data. More precisely, we propose a latent structural support vector machine formulation, where the latent variables model any missing information in the human annotation. Of particular interest to us are three types of annotations: (i) images segmented using generic foreground or background classes; (ii) images with bounding boxes specified for objects; and (iii) images labeled to indicate the presence of a class. Using large, publicly available datasets we show that our methods are able to significantly improve the accuracy of the region-based model.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2015, 37 (7), pp.1373-1386. 〈10.1109/TPAMI.2014.2372766 〉
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01223979
Contributeur : M. Pawan Kumar <>
Soumis le : mardi 3 novembre 2015 - 17:29:09
Dernière modification le : vendredi 6 avril 2018 - 13:32:01
Document(s) archivé(s) le : jeudi 4 février 2016 - 11:31:31

Fichier

KTPK-PAMI2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

M Pawan Kumar, Haithem Turki, Dan Preston, Daphne Koller. Parameter Estimation and Energy Minimization for Region-based Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2015, 37 (7), pp.1373-1386. 〈10.1109/TPAMI.2014.2372766 〉. 〈hal-01223979〉

Partager

Métriques

Consultations de la notice

207

Téléchargements de fichiers

188