Representation of similarity as a goal of early visual processing

We consider the representational capabilities of systems of receptive fields found in early mammalian vision, under the assumption that the successive stages of processing remap the retinal representation space in a manner that makes objectively similar stimuli (such as different views of the same 3D object) closer to each other, and dissimilar stimuli farther apart. We present theoretical analysis and computational experiments that compare the similarity between stimuli as they are represented at the successive levels of the processing hierarchy, from the retina to the nonlinear cortical units. Our results indicate that the representations at the higher levels of the hierarchy are indeed more useful for the classification of natural objects such as human faces.

[1]  Philip Rabinowitz,et al.  Methods of Numerical Integration , 1985 .

[2]  Myron Wish,et al.  Three-Way Multidimensional Scaling , 1978 .

[3]  L. Sirovich,et al.  Equivalence classes of visual stimuli , 1978, Vision Research.

[4]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[5]  Alex Pentland,et al.  On the Imaging of Fractal Surfaces , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  E. Reed.  The Ecological Approach to Visual Perception , 1989 .

[7]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[8]  John Daugman,et al.  An information-theoretic view of analog representation in striate cortex , 1993 .

[9]  Amnon Shashua,et al.  Illumination and View Position in 3D Visual Recognition , 1991, NIPS.

[10]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Nathan Intrator,et al.  Three-Dimensional Object Recognition Using an Unsupervised Neural Network: Understanding the Distinguishing Features , 1991 .

[12]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[13]  Ronen Basri,et al.  Recognition by Linear Combinations of Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Jitendra Malik,et al.  A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters , 1991, ECCV.

[15]  Andrew Zisserman,et al.  Geometric invariance in computer vision , 1992 .

[16]  Shimon Edelman,et al.  Learning to Recognize Faces from Examples , 1992, ECCV.

[17]  Leslie S. Smith,et al.  The principal components of natural images , 1992 .

[18]  Joseph J. Atick,et al.  What Does the Retina Know about Natural Scenes? , 1992, Neural Computation.

[19]  Shimon Ullman,et al.  Limitations of Non Model-Based Recognition Schemes , 1992, ECCV.

[20]  Shimon Edelman,et al.  Bringing the Grandmother back into the Picture: A Memory-Based View of Object Recognition , 1990, Int. J. Pattern Recognit. Artif. Intell..

[21]  Jitendra Malik,et al.  Computational framework for determining stereo correspondence from a set of linear spatial filters , 1992, Image Vis. Comput..

[22]  Alice J. O'Toole,et al.  Low-dimensional representation of faces in higher dimensions of the face space , 1993 .

[23]  Nathan Intrator,et al.  Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features , 1993, Neural Computation.

[24]  Shimon Ullman,et al.  Face Recognition: The Problem of Compensating for Changes in Illumination Direction , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

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

[26]  Shimon Ullman,et al.  Face Recognition: The Problem of Compensating for Changes in Illumination Direction , 1997, IEEE Trans. Pattern Anal. Mach. Intell..