Probabilistic Modeling for Face Orientation Discrimination

[baluja@grr.ius.cs.cmu.edu]

The following paper is available from:
http://www.cs.cmu.edu/~baluja


Probabilistic Modeling for Face Orientation Discrimination:  
Learning from Labeled and Unlabeled Data

Shumeet Baluja 



Abstract:
This paper presents probabilistic modeling methods to solve the problem of
discriminating between five facial orientations with very little labeled
data. Three models are explored. The first model maintains no inter-pixel
dependencies, the second model is capable of modeling a set of arbitrary
pair-wise dependencies, and the last model allows dependencies only between
neighboring pixels. We show that for all three of these models, the accuracy of
the learned models can be greatly improved by augmenting a small number of
labeled training images with a large set of unlabeled images using
Expectation-Maximization. This is important because it is often difficult to
obtain image labels, while many unlabeled images are readily available. Through
a large set of empirical tests, we examine the benefits of unlabeled data for
each of the models. By using only two randomly selected labeled examples per
class, we can discriminate between the five facial orientations with an accuracy
of 94%; with six labeled examples, we achieve an accuracy of 98%.


This work was completed while the author was at:
Justsystem Pittsburgh Research Center &
School of Computer Science, Carnegie Mellon University



Comments and Questions welcome.  
Please send all feedback to sbaluja at lycos.com.