Learning to recognize objects

A learning account for the problem of object recognition is developed within the PAC (Probably Approximately Correct) model of learnability. The proposed approach makes no assumptions on the distribution of the observed objects, but quantifies success relative to its past experience. Most importantly, the success of learning an object representation is naturally tied to the ability to represent at as a function of some intermediate representations extracted from the image. We evaluate this approach an a large scale experimental study in which the SNoW learning architecture is used to learn representations for the 100 objects in the Columbia Object Image Database (COIL-100). The SNoW-based method is shown to outperform other methods in terms of recognition rates; its performance degrades gracefully when the training data contains fewer views and in the presence of occlusion noise.

[1]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[2]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[4]  Ming Li,et al.  Learning in the presence of malicious errors , 1993, STOC '88.

[5]  David Haussler,et al.  Equivalence of models for polynomial learnability , 1988, COLT '88.

[6]  Haim Schweitzer,et al.  Learnable and Nonlearnable Visual Concepts , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  H. Shvaytser,et al.  Learnable and nonlearnable visual concepts , 1990 .

[8]  Nick Littlestone,et al.  Redundant noisy attributes, attribute errors, and linear-threshold learning using winnow , 1991, COLT '91.

[9]  Ming Li,et al.  Learning in the Presence of Malicious Errors , 1993, SIAM J. Comput..

[10]  Shimon Edelman,et al.  On Learning to Recognize 3-D Objects from Examples , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  E. Kushilevitz,et al.  On Learning Visual Concepts and DNF Formulae , 1996 .

[12]  Manfred K. Warmuth,et al.  Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..

[13]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Dan Roth,et al.  Learning to Resolve Natural Language Ambiguities: A Unified Approach , 1998, AAAI/IAAI.

[15]  Narendra Ahuja,et al.  A SNoW-Based Face Detector , 1999, NIPS.

[16]  Shimon Ullman,et al.  Computation of pattern invariance in brain-like structures , 1999, Neural Networks.

[17]  Donald Geman,et al.  Graded Learning for Object Detection , 1999 .

[18]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.