ML Anthology

Max-Margin Additive Classifiers for Detection

Subhransu Maji, Alexander C. Berg
ICCV 2009 pp. 40-47
doi:10.1109/ICCV.2009.5459203 /iccv/2009/maji2009iccv-max/

Abstract

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.

ICCV Semantic Scholar

Cite

Text

Maji and Berg. "Max-Margin Additive Classifiers for Detection." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459203

Markdown

[Maji and Berg. "Max-Margin Additive Classifiers for Detection." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/maji2009iccv-max/) doi:10.1109/ICCV.2009.5459203

BibTeX

@inproceedings{maji2009iccv-max,
  title     = {{Max-Margin Additive Classifiers for Detection}},
  author    = {Maji, Subhransu and Berg, Alexander C.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2009},
  pages     = {40-47},
  doi       = {10.1109/ICCV.2009.5459203},
  url       = {https://mlanthology.org/iccv/2009/maji2009iccv-max/}
}