The Robotics Institute

Carnegie Mellon Robotics Institute

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

Deployed vision systems often encounter image variations poorly represented in their training data. While observing their environment, such vision systems obtain unlabeled data that could be used to compensate for incomplete training. In order to exploit these relatively cheap and abundant unlabeled data we present a family of algorithms called MEEM. Using these algorithms, we train an appearance-based people detection model. In contrast to approaches that rely on a large number of manually labeled training points, we use a partially labeled data set to capture appearance variation. One can both avoid the tedium of additional manual labeling and obtain improved detection performance by augmenting a labeled training set with unlabeled data. Further, enlarging the original training set with new unlabeled points enables the update of detection models after deployment without human intervention. To support these claims we show people detection results, and compare our performance to a purely generative Expectation Maximization-based approach to learning over partially labeled data.

Notes

Number of pages: 6

Text Reference

Yaron Rachlin, John M. Dolan, and Pradeep Khosla, "Learning to Detect Partially Labeled People," Proceedings of the 2003 International Conference on Intelligent Robots and Systems (IROS'03), 2003.

BibTeX Reference

@inproceedings{Rachlin_2003_5022,
   author = "Yaron Rachlin and John M Dolan and Pradeep Khosla",
   title = "Learning to Detect Partially Labeled People",
   booktitle = "Proceedings of the 2003 International Conference on Intelligent Robots and Systems (IROS'03)",
   year = "2003",
}

The Robotics Institute

Menu