Max-Margin Additive Classifiers for Detection

被引：69

作者：

Maji, Subhransu ^{[1
]}

Berg, Alexander C. ^{[2
]}

机构：

[1] Univ Calif Berkeley, EECS, Berkeley, CA 94720 USA

[2] Columbia Univ, CS, New York, NY 10027 USA

来源：

2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2009年

关键词：

D O I：

10.1109/ICCV.2009.5459203

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We present methods for training high quality object detectors very quickly. The core contribution is a pair of fast training algorithms for piece-wise linear classifiers, which can approximate arbitrary additive models. The classifiers are trained in a max-margin framework and significantly outperform linear classifiers on a variety of vision datasets. We report experimental results quantifying training time and accuracy on image classification tasks and pedestrian detection, including detection results better than the best previous on the INRIA dataset with faster training.

引用

页码：40 / 47

页数：8