Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving

2018/04/17 by Jiaolong Xu, Xu, Jiaolong, Peng Wang +5 · 2 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Autonomous Vehicle Technology and Safety #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Industrial Vision Systems and Defect Detection #cs.CV

paper · pdf · doi:10.48550/arxiv.1804.06332

Accepted by ICRA 2019

openalex publication_date 2018/04/17 · arxiv created 2019/05/25 · arxiv updated 2019/05/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 1 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.

Citations

• Distilling the Knowledge in a Neural Network
• The Pascal Visual Object Classes (VOC) Challenge
• ImageNet classification with deep convolutional neural networks
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Ternary Neural Networks with Fine-Grained Quantization
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
• Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights

Cited by

• Hardware-Aware DNN Compression for Homogeneous Edge Devices
• Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions

Related

• SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
• Binary DAD-Net: Binarized Driveable Area Detection Network for\n Autonomous Driving
• R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
• Run-time Introspection of 2D Object Detection in Automated Driving Systems Using Learning Representations
• Enabling Incremental Knowledge Transfer for Object Detection at the Edge