ML Anthology

Improving Multiview Face Detection with Multi-Task Deep Convolutional Neural Networks

Cha Zhang, Zhengyou Zhang
WACV 2014 pp. 1036-1041
doi:10.1109/WACV.2014.6835990 /wacv/2014/zhang2014wacv-improving/

Abstract

Multiview face detection is a challenging problem due to dramatic appearance changes under various pose, illumination and expression conditions. In this paper, we present a multi-task deep learning scheme to enhance the detection performance. More specifically, we build a deep convolutional neural network that can simultaneously learn the face/nonface decision, the face pose estimation problem, and the facial landmark localization problem. We show that such a multi-task learning scheme can further improve the classifier's accuracy. On the challenging FDDB data set, our detector achieves over 3% improvement in detection rate at the same false positive rate compared with other state-of-the-art methods.

WACV Semantic Scholar

Cite

Text

Zhang and Zhang. "Improving Multiview Face Detection with Multi-Task Deep Convolutional Neural Networks." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014. doi:10.1109/WACV.2014.6835990

Markdown

[Zhang and Zhang. "Improving Multiview Face Detection with Multi-Task Deep Convolutional Neural Networks." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014.](https://mlanthology.org/wacv/2014/zhang2014wacv-improving/) doi:10.1109/WACV.2014.6835990

BibTeX

@inproceedings{zhang2014wacv-improving,
  title     = {{Improving Multiview Face Detection with Multi-Task Deep Convolutional Neural Networks}},
  author    = {Zhang, Cha and Zhang, Zhengyou},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2014},
  pages     = {1036-1041},
  doi       = {10.1109/WACV.2014.6835990},
  url       = {https://mlanthology.org/wacv/2014/zhang2014wacv-improving/}
}