Deep Learning-Based Vehicle Classification Using an Ensemble of Local Expert and Global Networks

Lee, Jong Taek; Chung, Yunsu

doi:10.1109/CVPRW.2017.127

Deep Learning-Based Vehicle Classification Using an Ensemble of Local Expert and Global Networks

Jong Taek Lee, Yunsu Chung

CVPRW 2017 pp. 920-925

doi:10.1109/CVPRW.2017.127 /cvprw/2017/lee2017cvprw-deep/

Abstract

Vehicle classification has been a challenging problem because of pose variations, weather / illumination changes, inter-class similarity and insufficient training dataset. With the help of innovative deep learning algorithms and large scale traffic surveillance dataset, we are able to achieve high performance on vehicle classification. In order to improve performance, we propose an ensemble of global networks and mixture of K local expert networks. It achieved a mean accuracy of 97.92%, a mean precision of 92.98%, a mean recall of 90.24% and a Cohen Kappa score of 96.75% on unseen test dataset from the MIO-TCD classification challenge.

CVPRW Semantic Scholar

Cite

Text

Lee and Chung. "Deep Learning-Based Vehicle Classification Using an Ensemble of Local Expert and Global Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.127

Markdown

[Lee and Chung. "Deep Learning-Based Vehicle Classification Using an Ensemble of Local Expert and Global Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/lee2017cvprw-deep/) doi:10.1109/CVPRW.2017.127

BibTeX

@inproceedings{lee2017cvprw-deep,
  title     = {{Deep Learning-Based Vehicle Classification Using an Ensemble of Local Expert and Global Networks}},
  author    = {Lee, Jong Taek and Chung, Yunsu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {920-925},
  doi       = {10.1109/CVPRW.2017.127},
  url       = {https://mlanthology.org/cvprw/2017/lee2017cvprw-deep/}
}