Learning Variance Statistics of Natural Images

In this paper, we show how a nonlinear transformation can be applied to model the variance statistics of natural images resulting in a sparse distributed representation of image structures. A variance representation of the input is learned from raw natural image patches using likelihood maximization. The simulation results demonstrate that the model can not only learn new families of basis functions, including multi-scale blobs, Gabor-like gratings and ridgelike basis functions, but also captures more abstract properties of the image, such as statistical similarity of regions within natural images. Moreover, in contrast to traditional linear model, such as sparse coding and ICA, responses show only very little residual dependencies.

[1]  D. Ringach.  Spatial structure and symmetry of simple-cell receptive fields in macaque primary visual cortex. , 2002, Journal of neurophysiology.

[2]  E. Oja,et al.  Independent Component Analysis , 2001 .

[3]  H. B. Barlow,et al.  Possible Principles Underlying the Transformations of Sensory Messages , 2012 .

[4]  Alexander S. Ecker,et al.  Decorrelated Neuronal Firing in Cortical Microcircuits , 2010, Science.

[5]  Michael S. Lewicki,et al.  Emergence of complex cell properties by learning to generalize in natural scenes , 2009, Nature.

[6]  Bernhard Wegmann,et al.  Statistical dependence between orientation filter outputs used in a human-vision-based image code , 1990, Other Conferences.

[7]  Martin Rehn,et al.  A network that uses few active neurones to code visual input predicts the diverse shapes of cortical receptive fields , 2007, Journal of Computational Neuroscience.

[8]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[9]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[10]  Aapo Hyvärinen,et al.  A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images , 2001, Vision Research.

[11]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[12]  M. Lewicki,et al.  Learning higher-order structures in natural images , 2003, Network.

[13]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[14]  J. H. Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998 .

[15]  Geoffrey E. Hinton,et al.  Learning Sparse Topographic Representations with Products of Student-t Distributions , 2002, NIPS.

[16]  Eero P. Simoncelli,et al.  Natural signal statistics and sensory gain control , 2001, Nature Neuroscience.