Document Detail


Modeling Natural Images Using Gated MRFs.
MedLine Citation:
PMID:  23868780     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
This paper describes a Markov Random Field for real-valued image modeling that has two sets of latent variables. One set is used to gate the interactions between all pairs of pixels, while the second set determines the mean intensities of each pixel. This is a powerful model with a conditional distribution over the input that is Gaussian, with both mean and covariance determined by the configuration of latent variables, which is unlike previous models that were restricted to using Gaussians with either a fixed mean or a diagonal covariance matrix. Thanks to the increased flexibility, this gated MRF can generate more realistic samples after training on an unconstrained distribution of high-resolution natural images. Furthermore, the latent variables of the model can be inferred efficiently and can be used as very effective descriptors in recognition tasks. Both generation and discrimination drastically improve as layers of binary latent variables are added to the model, yielding a hierarchical model called a Deep Belief Network.
Authors:
Marc'aurelio Ranzato; Volodymyr Mnih; Joshua M Susskind; Geoffrey E Hinton
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  IEEE transactions on pattern analysis and machine intelligence     Volume:  35     ISSN:  1939-3539     ISO Abbreviation:  IEEE Trans Pattern Anal Mach Intell     Publication Date:  2013 Sep 
Date Detail:
Created Date:  2013-07-22     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9885960     Medline TA:  IEEE Trans Pattern Anal Mach Intell     Country:  United States    
Other Details:
Languages:  eng     Pagination:  2206-22     Citation Subset:  IM    
Affiliation:
University of Toronto, Toronto.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Learning AND-OR Templates for Object Recognition and Detection.
Next Document:  Multi-exemplar affinity propagation.