Statistical models of images and early vision

A fundamental question in visual neuroscience is: Why are the receptive fields and response properties of visual neurons as they are? A modern approach to this problem emphasizes the importance of adaptation to ecologically valid input. In this paper, we will review work on modelling statistical regularities in ecologically valid visual input (“natural images”) and the obtained functional explanation of the properties of visual neurons. A seminal statistical model for natural images was linear sparse coding which is equivalent to the model called independent component analysis (ICA). Linear features estimated by ICA resemble wavelets or Gabor functions, and provide a very good description of the properties of simple cells in the primary visual cortex. We have introduced extensions of ICA that are based on modelling dependencies of the ”independent” components estimated by basic ICA. The dependencies of the components are used to define either a grouping or a topographic order between the components. With natural image data, these models lead to emergence of further properties of visual neurons: the topographic organization and complex cell receptive fields. We have also modelled the temporal structure of natural image sequences, which provides an alternative approach to the sparseness used in most models. These models can be combined in a unifying framework that we call bubble coding. Finally, we will discuss a promising new direction of research: predictive visual neuroscience. There, the goal is to try to predict response properties of neurons in areas that are poorly understood, still based on statistical modelling of natural input.

[1]  U. Polat,et al.  What pattern the eye sees best , 1999, Vision Research.

[2]  Pamela Reinagel.  How do visual neurons respond in the real world? , 2001, Current Opinion in Neurobiology.

[3]  Dinh-Tuan Pham,et al.  Blind separation of instantaneous mixtures of nonstationary sources , 2001, IEEE Trans. Signal Process..

[4]  G. Boynton,et al.  Visual Cortex: The Continuing Puzzle of Area V2 , 2004, Current Biology.

[5]  Konrad P. Körding,et al.  Extracting Slow Subspaces from Natural Videos Leads to Complex Cells , 2001, ICANN.

[6]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[7]  Peter Földiák,et al.  Learning Invariance from Transformation Sequences , 1991, Neural Comput..

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

[9]  Eero P. Simoncelli,et al.  A model of neuronal responses in visual area MT , 1998, Vision Research.

[10]  Terrence J. Sejnowski,et al.  Slow Feature Analysis: Unsupervised Learning of Invariances , 2002, Neural Computation.

[11]  Aapo Hyvärinen,et al.  Simple-Cell-Like Receptive Fields Maximize Temporal Coherence in Natural Video , 2003, Neural Computation.

[12]  V. Mountcastle.  The columnar organization of the neocortex. , 1997, Brain : a journal of neurology.

[13]  D. Ruderman,et al.  INDEPENDENT COMPONENT ANALYSIS OF NATURAL IMAGE SEQUENCES YIELDS SPATIOTEMPORAL FILTERS SIMILAR TO SIMPLE CELLS IN PRIMARY VISUAL CORTEX , 1998 .

[14]  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.

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

[16]  A. Hyvärinen,et al.  Temporal and spatiotemporal coherence in simple-cell responses: a generative model of natural image sequences , 2003, Network.

[17]  Aapo Hyvärinen,et al.  Bubbles: a unifying framework for low-level statistical properties of natural image sequences. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[18]  Martin J. Wainwright,et al.  Image denoising using scale mixtures of Gaussians in the wavelet domain , 2003, IEEE Trans. Image Process..

[19]  Edward H. Adelson,et al.  Noise removal via Bayesian wavelet coring , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[20]  Jean-François Cardoso,et al.  Multidimensional independent component analysis , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[21]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[22]  Aapo Hyvärinen,et al.  Estimation of Non-Normalized Statistical Models by Score Matching , 2005, J. Mach. Learn. Res..

[23]  Aapo Hyvärinen,et al.  Topographic Independent Component Analysis , 2001, Neural Computation.

[24]  Eero P. Simoncelli,et al.  Modeling Surround Suppression in V1 Neurons with a Statistically Derived Normalization Model , 1998, NIPS.

[25]  H. Barlow.  Vision Science: Photons to Phenomenology by Stephen E. Palmer , 2000, Trends in Cognitive Sciences.

[26]  Lewis D. Griffin,et al.  Natural image profiles are most likely to be step edges , 2004, Vision Research.

[27]  Kiyotoshi Matsuoka,et al.  A neural net for blind separation of nonstationary signals , 1995, Neural Networks.

[28]  Bruno A. Olshausen,et al.  Principles of Image Representation in Visual Cortex , 2003 .

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

[30]  A. Hyvärinen,et al.  A multi-layer sparse coding network learns contour coding from natural images , 2002, Vision Research.

[31]  Eero P. Simoncelli,et al.  Natural image statistics and neural representation. , 2001, Annual review of neuroscience.

[32]  Aapo Hyvärinen,et al.  Blind separation of sources that have spatiotemporal variance dependencies , 2004, Signal Process..

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

[34]  Aapo Hyvärinen,et al.  Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces , 2000, Neural Computation.

[35]  Aapo Hyvärinen,et al.  Blind source separation by nonstationarity of variance: a cumulant-based approach , 2001, IEEE Trans. Neural Networks.

[36]  Aapo Hyvärinen,et al.  Sparse Code Shrinkage: Denoising of Nongaussian Data by Maximum Likelihood Estimation , 1999, Neural Computation.

[37]  Aapo Hyvärinen,et al.  Statistical model of natural stimuli predicts edge-like pooling of spatial frequency channels in V2 , 2004, BMC Neuroscience.

[38]  David J. Field,et al.  What Is the Goal of Sensory Coding? , 1994, Neural Computation.