Shallow Networks for High-accuracy Road Object-detection

Khalid Ashraf, Bichen Wu, Forrest N. Iandola, Matthew W. Moskewicz, Kurt Keutzer

2017

Abstract

The ability to automatically detect other vehicles on the road is vital to the safety of partially-autonomous and fully-autonomous vehicles. Most of the high-accuracy techniques for this task are based on R-CNN or one of its faster variants. In the research community, much emphasis has been applied to using 3D vision or complex R-CNN variants to achieve higher accuracy. However, are there more straightforward modifications that could deliver higher accuracy? Yes. We show that increasing input image resolution (i.e. upsampling) offers up to 12 percentage-points higher accuracy compared to an off-the-shelf baseline. We also find situations where earlier/shallower layers of CNN provide higher accuracy than later/deeper layers. We further show that shallow models and upsampled images yield competitive accuracy. Our findings contrast with the current trend towards deeper and larger models to achieve high accuracy in domain specific detection tasks.

Paper Citation

in Harvard Style

Ashraf K., Wu B., Iandola F., Moskewicz M. and Keutzer K. (2017). Shallow Networks for High-accuracy Road Object-detection . In Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-242-4, pages 33-40. DOI: 10.5220/0006214900330040

in Bibtex Style

@conference{vehits17,
author={Khalid Ashraf and Bichen Wu and Forrest N. Iandola and Matthew W. Moskewicz and Kurt Keutzer},
title={Shallow Networks for High-accuracy Road Object-detection},
booktitle={Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2017},
pages={33-40},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006214900330040},
isbn={978-989-758-242-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Shallow Networks for High-accuracy Road Object-detection
SN - 978-989-758-242-4
AU - Ashraf K.
AU - Wu B.
AU - Iandola F.
AU - Moskewicz M.
AU - Keutzer K.
PY - 2017
SP - 33
EP - 40
DO - 10.5220/0006214900330040