A discriminatively trained, multiscale, deformable part model

DMCA

A discriminatively trained, multiscale, deformable part model (2008)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Pedro Felzenszwalb , David Mcallester , Deva Ramanan

Venue:	In IEEE Conference on Computer Vision and Pattern Recognition (CVPR-2008
Citations:	550 - 11 self

BibTeX

@INPROCEEDINGS{Felzenszwalb08adiscriminatively,
    author = {Pedro Felzenszwalb and David Mcallester and Deva Ramanan},
    title = {A discriminatively trained, multiscale, deformable part model},
    booktitle = {In IEEE Conference on Computer Vision and Pattern Recognition (CVPR-2008},
    year = {2008}
}

OpenURL

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. 1.

Keyphrases

deformable part model latent svm latent information discriminative training new method hard negative example object detection hidden crf effective use deformable part difficult benchmark twenty category non-convex training problem two-fold improvement positive example dimensional pose pascal challenge training problem pascal person detection challenge training method average precision margin-sensitive approach

DMCA