Deep Part-Based Generative Shape Model with Latent Variables

Abstract : The Shape Boltzmann Machine (SBM) [6] and its multilabel version MSBM [5] have been recently introduced as deep generative models that capture the variations of an object shape. While being more flexible MSBM requires datasets with labeled parts of the objects for training. In the paper we present an algorithm for training MSBM using binary masks of objects and the seeds which approximately correspond to the locations of objects parts. The latter can be obtained from part-based detectors in an unsupervised manner. We derive a latent variable model and an EM-like training procedure for adjusting the weights of MSBM using a deep learning framework. We show that the model trained by our method outperforms SBM in the tasks related to binary shapes and is very close to the original MSBM in terms of quality of multilabel shapes.
Type de document :
Communication dans un congrès
27th British Machine Vision Conference (BMVC 2016), Sep 2016, York, United Kingdom. Proceedings of the British Machine Vision Conference (BMVC)
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01404071
Contributeur : Anton Osokin <>
Soumis le : lundi 28 novembre 2016 - 12:18:23
Dernière modification le : jeudi 26 avril 2018 - 10:28:58
Document(s) archivé(s) le : mardi 21 mars 2017 - 05:24:32

Fichier

kirillov16.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01404071, version 1

Collections

Citation

Alexander Kirillov, Mikhail Gavrikov, Ekaterina Lobacheva, Anton Osokin, Dmitry Vetrov. Deep Part-Based Generative Shape Model with Latent Variables. 27th British Machine Vision Conference (BMVC 2016), Sep 2016, York, United Kingdom. Proceedings of the British Machine Vision Conference (BMVC). 〈hal-01404071〉

Partager

Métriques

Consultations de la notice

298

Téléchargements de fichiers

147