Generative vs. Discriminative Deep Belief Netwok for 3D Object Categorization

Abstract : Object categorization has been an important task of computer vision research in recent years. In this paper, we propose a new approach for representing and learning 3D object categories. First, We extract the Viewpoint Feature Histogram (VFH) descriptor from point clouds and then we learn the resulting features using deep learning architectures. We evaluate the performance of both generative and discriminative deep belief network architectures (GDBN/DDBN) for object categorization task. GDBN trains a sequence of Restricted Boltzmann Machines (RBMs) while DDBN uses a new deep architecture based on RBMs and the joint density model. Our results show the power of discriminative model for object categorization and outperform state-of-the-art approaches when tested on the Washington RGBD dataset.
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01931302
Contributeur : Le2i - Université de Bourgogne <>
Soumis le : jeudi 22 novembre 2018 - 16:14:05
Dernière modification le : vendredi 7 décembre 2018 - 16:48:04

Identifiants

Citation

Nabila Zrira, Mohamed Hannat, El Houssine Bouyakhf, Haris Ahmad Khan. Generative vs. Discriminative Deep Belief Netwok for 3D Object Categorization. 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), Inst Syst & Technologies Informat, Control & Commun; ACM SIGGRAPH; AFIG; Eurographics, Feb 2017, Porto, Portugal. pp.98-107, ⟨10.5220/0006151100980107⟩. ⟨hal-01931302⟩

Partager

Métriques

Consultations de la notice

39