de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Factorial coding of natural images: how effective are linear models in removing higher-order dependencies?

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons83805

Bethge,  M
Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Bethge, M. (2006). Factorial coding of natural images: how effective are linear models in removing higher-order dependencies? Journal of the Optical Society of America A, 23(6), 1253-1268. Retrieved from http://josaa.osa.org/DirectPDFAccess/6B1E0AAE-BDB9-137E-C052FB22B16FA3E3_89867.pdf?da=1id=89867seq=0CFID=42173763CFTOKEN=22721557.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-D11F-D
Abstract
The performance of unsupervised learning models for natural images is evaluated quantitatively by means of information theory. We estimate the gain in statistical independence (the multi-information reduction) achieved with independent component analysis (ICA), principal component analysis (PCA), zero-phase whitening, and predictive coding. Predictive coding is translated into the transform coding framework, where it can be characterized by the constraint of a triangular filter matrix. A randomly sampled whitening basis and the Haar wavelet are included into the comparison as well. The comparison of all these methods is carried out for different patch sizes, ranging from 2x2 to 16x16 pixels. In spite of large differences in the shape of the basis functions, we find only small differences in the multi-information between all decorrelation transforms (5 or less) for all patch sizes. Among the second-order methods, PCA is optimal for small patch sizes and predictive coding performs best for large patch sizes. The extra gain achieved with ICA is always less than 2. In conclusion, the `edge filtersamp;amp;amp;amp;lsquo; found with ICA lead only to a surprisingly small improvement in terms of its actual objective.