Developmental Constraints Aid the Acquisition of Binocular Disparity Sensitivities

This article considers the hypothesis that systems learning aspects of visual perception may benefit from the use of suitably designed developmental progressions during training. We report the results of simulations in which four models were trained to detect binocular disparities in pairs of visual images. Three of the models were developmental models in the sense that the nature of their visual input changed during the course of training. These models received a relatively impoverished visual input early in training, and the quality of this input improved as training progressed. One model used a coarse-scale-to-multiscale developmental progression, another used a fine-scale-to-multiscale progression, and the third used a random progression. The final model was nondevelopmental in the sense that the nature of its input remained the same throughout the training period. The simulation results show that the two developmental models whose progressions were organized by spatial frequency content consistently outperformed the nondevelopmental and random developmental models. We speculate that the superior performance of these two models is due to two important features of their developmental progressions: (1) these models were exposed to visual inputs at a single scale early in training, and (2) the spatial scale of their inputs progressed in an orderly fashion from one scale to a neighboring scale during training. Simulation results consistent with these speculations are presented. We conclude that suitably designed developmental sequences can be useful to systems learning to detect binocular disparities. The idea that visual development can aid visual learning is a viable hypothesis in need of study.

[1]  J. Atkinson,et al.  Stereoscopic Discrimination in Infants , 1976 .

[2]  P. L. Adams THE ORIGINS OF INTELLIGENCE IN CHILDREN , 1976 .

[3]  D Marr,et al.  A computational theory of human stereo vision. , 1979, Proceedings of the Royal Society of London. Series B, Biological sciences.

[4]  S. Dumais,et al.  Stereopsis in human infants. , 1980, Science.

[5]  R. Held,et al.  Stereoacuity of human infants. , 1980, Proceedings of the National Academy of Sciences of the United States of America.

[6]  J. Mayhew,et al.  Vergence Eye Movements Made in Response to Spatial-Frequency-Filtered Random-Dot Stereograms , 1981, Perception.

[7]  G. Baumgartner,et al.  Development of stereopsis and cortical binocularity in human infants: electrophysiological evidence. , 1981, Science.

[8]  G Turkewitz,et al.  Limitations on input as a basis for neural organization and perceptual development: a preliminary theoretical statement. , 1982, Developmental psychobiology.

[9]  A. Norcia,et al.  Spatial frequency sweep VEP: Visual acuity during the first year of life , 1985, Vision Research.

[10]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[11]  William H. Press,et al.  Numerical Recipes in C The Art of Scientific Computing , 1995 .

[12]  E. Smith,et al.  Multiple sensitive periods in the development of the primate visual system. , 1986, Science.

[13]  W. Greenough,et al.  Experience and brain development. , 1987, Child development.

[14]  Stephen T. Barnard,et al.  Stereo Matching by Hierarchical, Microcanonical Annealing , 1987, IJCAI.

[15]  L. Quam Hierarchical warp stereo , 1987 .

[16]  S. McKee,et al.  The role of retinal correspondence in stereoscopic matching , 1988, Vision Research.

[17]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[18]  Elissa L. Newport,et al.  Maturational Constraints on Language Learning , 1990, Cogn. Sci..

[19]  I. Ohzawa,et al.  Stereoscopic depth discrimination in the visual cortex: neurons ideally suited as disparity detectors. , 1990, Science.

[20]  Jocelyn Sietsma,et al.  Creating artificial neural networks that generalize , 1991, Neural Networks.

[21]  Kiyotoshi Matsuoka,et al.  Noise injection into inputs in back-propagation learning , 1992, IEEE Trans. Syst. Man Cybern..

[22]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[23]  William H. Press,et al.  Numerical recipes in C++: the art of scientific computing, 2nd Edition (C++ ed., print. is corrected to software version 2.10) , 1994 .

[24]  William H. Press,et al.  Numerical Recipes in Fortran 77: The Art of Scientific Computing 2nd Editionn - Volume 1 of Fortran Numerical Recipes , 1992 .

[25]  J. Elman Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[26]  Andrew R. Webb,et al.  Functional approximation by feed-forward networks: a least-squares approach to generalization , 1994, IEEE Trans. Neural Networks.

[27]  Ning Qian,et al.  Computing Stereo Disparity and Motion with Known Binocular Cell Properties , 1994, Neural Computation.

[28]  F. Kingdom,et al.  Contrast thresholds for stereoscopic depth identification with isoluminant and isochromatic stimuli , 1994, Vision Research.

[29]  H. Smallman Fine-to-coarse scale disambiguation in stereopsis , 1995, Vision Research.

[30]  Christopher M. Bishop,et al.  Training with Noise is Equivalent to Tikhonov Regularization , 1995, Neural Computation.

[31]  Ning Qian,et al.  Binocular Receptive Field Models, Disparity Tuning, and Characteristic Disparity , 1996, Neural Computation.

[32]  C. Shatz Emergence of order in visual system development , 1996, Journal of Physiology-Paris.

[33]  David J. Fleet,et al.  Neural encoding of binocular disparity: Energy models, position shifts and phase shifts , 1996, Vision Research.

[34]  M S Gray,et al.  Reliable disparity estimation through selective integration , 1998, Visual Neuroscience.

[35]  Douglas L. T. Rohde,et al.  Language acquisition in the absence of explicit negative evidence: how important is starting small? , 1999, Cognition.

[36]  Giulio Sandini,et al.  Developmental robotics: a survey , 2003, Connect. Sci..

[37]  Hanspeter A. Mallot,et al.  Is correspondence search in human stereo vision a coarse-to-fine process? , 1996, Biological Cybernetics.