A Discriminatively Trained, Multiscale, Deformable Part Model

June 2008

A Discriminatively Trained, Multiscale, Deformable Part Model

Authors:

Pedro Felzenszwalb, David McAllester, and Deva Ramanan
Conference Paper
Proceedings of (CVPR) Computer Vision and Pattern Recognition

Abstract:

This paper describes a discriminatively trained, multiscale, deformable part model for object detection. Our system achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge. It also outperforms the best results in the 2007 challenge in ten out of twenty categories. The system relies heavily on deformable parts. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL challenge. Our system also relies heavily on new methods for discriminative training. We combine a margin-sensitive approach for data mining hard negative examples with a formalism we call latent SVM. A latent SVM, like a hidden CRF, leads to a non-convex training problem. However, a latent SVM is semi-convex and the training problem becomes convex once latent information is specified for the positive examples. We believe that our training methods will eventually make possible the effective use of more latent information such as hierarchical (grammar) models and models involving latent three dimensional pose.
@conference{Felzenszwalb-2008-121224,
author = {Pedro Felzenszwalb And David McAllester And Deva Ramanan},
title = {A Discriminatively Trained, Multiscale, Deformable Part Model},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2008},
month = {June},
}
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.