English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Mixtures of Conditional Gaussian Scale Mixtures Applied to Multiscale Image Representations

Theis, L., Hosseini, R., & Bethge, M. (2012). Mixtures of Conditional Gaussian Scale Mixtures Applied to Multiscale Image Representations. PLoS One, 7(7), 1-8. doi:10.1371/journal.pone.0039857.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0001-856E-E Version Permalink: http://hdl.handle.net/21.11116/0000-0001-8570-A
Genre: Journal Article

Files

show Files

Creators

show
hide
 Creators:
Theis, L1, 2, Author              
Hosseini, R1, 2, Author              
Bethge, M1, 2, Author              
Affiliations:
1Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: We present a probabilistic model for natural images that is based on mixtures of Gaussian scale mixtures and a simple multiscale representation. We show that it is able to generate images with interesting higher-order correlations when trained on natural images or samples from an occlusion-based model. More importantly, our multiscale model allows for a principled evaluation. While it is easy to generate visually appealing images, we demonstrate that our model also yields the best performance reported to date when evaluated with respect to the cross-entropy rate, a measure tightly linked to the average log-likelihood. The ability to quantitatively evaluate our model differentiates it from other multiscale models, for which evaluation of these kinds of measures is usually intractable.

Details

show
hide
Language(s):
 Dates: 2012-07
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1371/journal.pone.0039857
eDoc: e39857
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: PLoS One
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: San Francisco, CA : Public Library of Science
Pages: - Volume / Issue: 7 (7) Sequence Number: - Start / End Page: 1 - 8 Identifier: ISSN: 1932-6203
CoNE: https://pure.mpg.de/cone/journals/resource/1000000000277850