In object detection, reducing computational cost is as important as improving accuracy for most practical usages. This paper proposes a novel network structure, which is an order of magnitude lighter than other state-of-the-art networks while maintaining the accuracy. Based on the basic principle of more layers with less channels, this new deep neural network minimizes its redundancy by adopting recent innovations including C.ReLU and Inception structure. We also show that this network can be trained efficiently to achieve solid results on well-known object detection benchmarks: 84.9% and 84.2% mAP on VOC2007 and VOC2012 while the required compute is less than 10% of the recent ResNet-101.
@article{arxiv.1611.08588,
title = {PVANet: Lightweight Deep Neural Networks for Real-time Object Detection},
author = {Sanghoon Hong and Byungseok Roh and Kye-Hyeon Kim and Yeongjae Cheon and Minje Park},
journal= {arXiv preprint arXiv:1611.08588},
year = {2016}
}
Comments
Presented at NIPS 2016 Workshop on Efficient Methods for Deep Neural Networks (EMDNN). Continuation of arXiv:1608.08021. The affiliation has been corrected