Download:
|
by Dan Roth, Ming-hsuan Yang, Narendra Ahuja
http://l2r.cs.uiuc.edu/~danr/Papers/cvpr00.ps.gz
Add To MetaCart
Abstract:
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 quanties success relative to its past experience. Most importantly, the success of learning an object representation is naturally tied to the ability to represent it as a function of some intermediate representations extracted from the image. We evaluate this approach in 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.
Citations
|
4717
|
The Nature of Statistical Learning Theory
– Vapnik
- 1995
|
|
1728
|
A Computation Approach to Edge Detection
– Canny
- 1986
|
|
1395
|
A theory of the learnable
– Valiant
- 1984
|
|
525
|
Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm
– Littlestone
- 1993
|
|
162
|
Exponentiated gradient versus gradient descent for linear predictors
– Kivinen, Warmuth
- 1997
|
|
148
|
Learning to resolve natural language ambiguities: A unified approach
– Roth
- 1998
|
|
131
|
Learning in the presence of malicious errors
– Kearns, Li
- 1988
|
|
111
|
Support Vector Machines for 3-D Object Recognition
– Pontil, Verri
- 1998
|
|
103
|
Redundant noisy attributes, attribute errors, and linear threshold learning using winnow
– Littlestone
- 1991
|
|
89
|
Equivalence of models for polynomial learnability
– Haussler, Kearns, et al.
- 1991
|
|
87
|
A SNoW-based face detector
– Yang, Roth, et al.
- 2000
|
|
60
|
The SNoW learning architecture
– Carlson, Cumby, et al.
- 1999
|
|
28
|
On learning visual concepts and DNF formulae
– Kushilevitz, Roth
- 1993
|
|
15
|
Learning Boolean Functions in an In Attribute Space
– Blum
- 1992
|
|
15
|
On learning to recognize 3-D objects from examples
– Edelman
- 1993
|
|
12
|
Learnable and nonlearnable visual concepts
– Shvaytser
- 1990
|
|
12
|
Computation of pattern invariance in brain-like structures. Neural Networks
– Ullman, Soloviev
- 1999
|
|
7
|
Graded learning for object detection
– Fleuret, Geman
- 1999
|
