Sciweavers

Share
CVPR
2009
IEEE

Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning

12 years 8 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief networks, by viewing each layer as a separate Restricted Boltzmann Machine (RBM). We develop the Convolutional RBM (C-RBM), a variant of the RBM model in which weights are shared to respect the spatial structure of images. This framework learns a set of features that can generate the images of a specific object class. Our feature extraction model is a four layer hierarchy of alternating filtering and maximum subsampling. We learn feature parameters of the first and third layers viewing them as separate C-RBMs. The outputs of our feature extraction hierarchy are then fed as input to a discriminative classifier. It is experimentally demonstrated that the extracted features are effective for object detection, using them to obtain performance comparable to the state-of-the-art on handwritten digit rec...
Mohammad Norouzi (Simon Fraser University), Mani R
Added 09 May 2009
Updated 10 Dec 2009
Type Conference
Year 2009
Where CVPR
Authors Mohammad Norouzi (Simon Fraser University), Mani Ranjbar (Simon Fraser University), Greg Mori (Simon Fraser University)
Comments (0)
books