nips nips2005 nips2005-109 nips2005-109-reference knowledge-graph by maker-knowledge-mining

109 nips-2005-Learning Cue-Invariant Visual Responses


Source: pdf

Author: Jarmo Hurri

Abstract: Multiple visual cues are used by the visual system to analyze a scene; achromatic cues include luminance, texture, contrast and motion. Singlecell recordings have shown that the mammalian visual cortex contains neurons that respond similarly to scene structure (e.g., orientation of a boundary), regardless of the cue type conveying this information. This paper shows that cue-invariant response properties of simple- and complex-type cells can be learned from natural image data in an unsupervised manner. In order to do this, we also extend a previous conceptual model of cue invariance so that it can be applied to model simple- and complex-cell responses. Our results relate cue-invariant response properties to natural image statistics, thereby showing how the statistical modeling approach can be used to model processing beyond the elemental response properties visual neurons. This work also demonstrates how to learn, from natural image data, more sophisticated feature detectors than those based on changes in mean luminance, thereby paving the way for new data-driven approaches to image processing and computer vision. 1


reference text

[1] I. Mareschal and C. Baker, Jr. A cortical locus for the processing of contrast-defined contours. Nature Neuroscience 1(2):150–154, 1998.

[2] Y.-X. Zhou and C. Baker, Jr. A processsing stream in mammalian visual cortex neurons for non-Fourier responses. Science 261(5117):98–101, 1993.

[3] A. G. Leventhal, Y. Wang, M. T. Schmolesky, and Y. Zhou. Neural correlates of boundary perception. Visual Neuroscience 15(6):1107–1118, 1998.

[4] I. Mareschal and C. Baker, Jr. Temporal and spatial response to second-order stimuli in cat area 18. Journal of Neurophysiology 80(6):2811–2823, 1998.

[5] J. A. Bourne, R. Tweedale, and M. G. P. Rosa. Physiological responses of New World monkey V1 neurons to stimuli defined by coherent motion. Cerebral Cortex 12(11):1132–1145, 2002.

[6] B. A. Olshausen and D. Field. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583):607–609, 1996.

[7] A. Bell and T. J. Sejnowski. The independent components of natural scenes are edge filters. Vision Research 37(23):3327–3338, 1997.

[8] J. H. van Hateren and A. van der Schaaf. Independent component filters of natural images compared with simple cells in primary visual cortex. Proceedings of the Royal Society of London B 265(1394):359–366, 1998.

[9] A. Hyvärinen and P. O. Hoyer. A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images. Vision Research 41(18):2413–2423, 2001.

[10] P. Dayan and L. F. Abbott. Theoretical Neuroscience. The MIT Press, 2001.

[11] O. Schwartz and E. P. Simoncelli. Natural signal statistics and sensory gain control. Nature Neuroscience 4(8):819–825, 2001.

[12] J. Hurri and A. Hyvärinen. Simple-cell-like receptive fields maximize temporal coherence in natural video. Neural Computation 15(3):663–691, 2003.

[13] J. Hurri and A. Hyvärinen. Temporal and spatiotemporal coherence in simple-cell responses: a generative model of natural image sequences. Network: Computation in Neural Systems 14(3):527–551, 2003.

[14] Y. Karklin and M. S. Lewicki. Higher-order structure of natural images. Network: Computation in Neural Systems 14(3):483–499, 2003.

[15] A. Hyvärinen, J. Karhunen, and E. Oja. Independent Component Analysis. John Wiley & Sons, 2001.

[16] D. J. Heeger. Normalization of cell responses in cat striate cortex. Visual Neuroscience 9(2):181–197, 1992.