Networks That Learn for Image Understanding

Learning is becoming a central problem in trying to understand intelligence and in trying to develop intelligent machines. This paper describes some recent work on developing machines that learn in the domains of vision and graphics. We will introduce an underlying theory which connects function approximation techniques, neural network architectures and statistical methods. While these techniques have limitations, one can overcome these limitations by using the idea of virtual examples. We shall describe some learning-based systems we have developed that recognize objects, in particular faces, nd speciic objects in cluttered scenes, and produce novel images under user control. Finally, we will discuss about the implications of this research on how the brain might work.

[1]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2]  Robert J. Baron,et al.  Mechanisms of Human Facial Recognition , 1981, Int. J. Man Mach. Stud..

[3]  J. Friedman,et al.  Projection Pursuit Regression , 1981 .

[4]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[5]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[6]  T Poggio,et al.  Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks , 1990, Science.

[7]  G. Wahba.  Spline models for observational data , 1990 .

[8]  A. Barron.  Approximation and Estimation Bounds for Artificial Neural Networks , 1991, COLT '91.

[9]  T. Poggio,et al.  Recognition and Structure from one 2D Model View: Observations on Prototypes, Object Classes and Symmetries , 1992 .

[10]  F. Girosi,et al.  From regularization to radial, tensor and additive splines , 1993, Neural Networks for Signal Processing III - Proceedings of the 1993 IEEE-SP Workshop.

[11]  Roberto Brunelli,et al.  Face Recognition: Features Versus Templates , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  J. M. Gilbert,et al.  A real-time face recognition system using custom VLSI hardware , 1993, 1993 Computer Architectures for Machine Perception.

[13]  Leo Breiman,et al.  Hinging hyperplanes for regression, classification, and function approximation , 1993, IEEE Trans. Inf. Theory.

[14]  Tomaso Poggio,et al.  Example Based Image Analysis and Synthesis , 1993 .

[15]  Partha Niyogi,et al.  Active Learning for Function Approximation , 1994, NIPS.

[16]  David Beymer,et al.  Face recognition under varying pose , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[17]  N. Logothetis,et al.  View-dependent object recognition by monkeys , 1994, Current Biology.

[18]  David Beymer,et al.  Face recognition from one example view , 1995, Proceedings of IEEE International Conference on Computer Vision.

[19]  N. Logothetis,et al.  Shape representation in the inferior temporal cortex of monkeys , 1995, Current Biology.

[20]  N. Logothetis,et al.  Psychophysical and physiological evidence for viewer-centered object representations in the primate. , 1995, Cerebral cortex.

[21]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[22]  Kah Kay Sung,et al.  Learning and example selection for object and pattern detection , 1995 .

[23]  Federico Girosi,et al.  On the Relationship between Generalization Error, Hypothesis Complexity, and Sample Complexity for Radial Basis Functions , 1996, Neural Computation.

[24]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..