Convolutional Trees for Fast Transform Learning

Abstract : —Dictionary learning is a powerful approach for sparse representation. However, the numerical complexity of classical dictionary learning methods restricts their use to atoms with small supports such as patches. In a previous work, we introduced a model based on a composition of convolutions with sparse kernels to build large dictionary atoms with a low computational cost. The subject of this work is to consider this model at the next level, i.e., to build a full dictionary of atoms from convolutions of sparse kernels. Moreover, we further reduce the size of the representation space by organizing the convolution kernels used to build atoms into a tree structure. The performance of the method is tested for the construction of a curvelet dictionary with a known code.
Type de document :
Communication dans un congrès
SPARS, 2015, Cambridge, United Kingdom. Proceedings of SPARS
Liste complète des métadonnées
Contributeur : Francois Malgouyres <>
Soumis le : vendredi 10 mars 2017 - 14:56:08
Dernière modification le : mardi 14 mars 2017 - 01:09:42


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01486832, version 1



Olivier Chabiron, Jean-Yves Tourneret, Herwig Wendt, François Malgouyres. Convolutional Trees for Fast Transform Learning. SPARS, 2015, Cambridge, United Kingdom. Proceedings of SPARS. <hal-01486832>



Consultations de
la notice


Téléchargements du document