%0 Conference Proceedings
%T Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving
%A Jiaolong Xu
%A Peng Wang
%A Heng Yang
%A Antonio Lopez
%B IEEE International Conference on Robotics and Automation
%D 2019
%F Jiaolong Xu2019
%O ADAS; 600.124; 600.116; 600.118
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3182), last updated on Tue, 25 Jan 2022 11:31:05 +0100
%X Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection. Recent deep convolutional neural network based object detectors have achieved state-of-the-art accuracy. However, such models are trained with numerous parameters and their high computational costs and large storage prohibit the deployment to memory and computation resource limited systems. Low-precision neural networks are popular techniques for reducing the computation requirements and memory footprint. Among them, binary weight neural network (BWN) is the extreme case which quantizes the float-point into just  bit. BWNs are difficult to train and suffer from accuracy deprecation due to the extreme low-bit representation. To address this problem, we propose a knowledge transfer (KT) method to aid the training of BWN using a full-precision teacher network. We built DarkNet-and MobileNet-based binary weight YOLO-v2 detectors and conduct experiments on KITTI benchmark for car, pedestrian and cyclist detection. The experimental results show that the proposed method maintains high detection accuracy while reducing the model size of DarkNet-YOLO from 257 MB to 8.8 MB and MobileNet-YOLO from 193 MB to 7.9 MB.
%U https://ieeexplore.ieee.org/document/8793743
%U http://refbase.cvc.uab.es/files/XWY2018.pdf
%U http://dx.doi.org/10.1109/ICRA.2019.8793743
%P 2379-2384