Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs

Résumé

We propose an extension of the Restricted Boltzmann Machine (RBM) that allows the joint shape and appearance of foreground objects in cluttered images to be modeled independently of the background. We present a learning scheme that learns this representation directly from cluttered images with only very weak supervision. The model generates plausible samples and performs foreground-background segmentation. We demonstrate that representing foreground objects independently of the background can be beneficial in recognition tasks.
Fichier principal
Vignette du fichier
mrbm_heess.pdf (165.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00609681 , version 1 (19-07-2011)

Identifiants

  • HAL Id : inria-00609681 , version 1
  • ARXIV : 1107.3823

Citer

Nicolas Heess, Nicolas Le Roux, John Winn. Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs. ICANN 2011 - International Conference on Artificial Neural Networks, Jun 2011, Espoo, Finland. ⟨inria-00609681⟩
153 Consultations
295 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More