Sciweavers

JMLR
2012

Multiresolution Deep Belief Networks

11 years 6 months ago
Multiresolution Deep Belief Networks
Motivated by the observation that coarse and fine resolutions of an image reveal different structures in the underlying visual phenomenon, we present a model based on the Deep Belief Network (DBN) which learns features from the multiscale representation of images. A Laplacian Pyramid is first constructed for each image. DBNs are then trained separately at each level of the pyramid. Finally, a top level RBM combines these DBNs into a single network we call the Multiresolution Deep Belief Network (MrDBN). Experiments show that MrDBNs generalize better than standard DBNs on NORB classification and TIMIT phone recognition. In the domain of generative learning, we demonstrate the superiority of MrDBNs at modeling face images.
Yichuan Tang, Abdel-rahman Mohamed
Added 27 Sep 2012
Updated 27 Sep 2012
Type Journal
Year 2012
Where JMLR
Authors Yichuan Tang, Abdel-rahman Mohamed
Comments (0)