Pruning CNNs for LiDAR-based Perception in Resource Constrained Environments

M. Vemparala, Anmol Singh, Ahmed Mzid, Nael Fasfous, Alexander Frickenstein, Florian Mirus, Hans-Joerg Voegel, N. Nagaraja, W. Stechele
{"title":"Pruning CNNs for LiDAR-based Perception in Resource Constrained Environments","authors":"M. Vemparala, Anmol Singh, Ahmed Mzid, Nael Fasfous, Alexander Frickenstein, Florian Mirus, Hans-Joerg Voegel, N. Nagaraja, W. Stechele","doi":"10.1109/ivworkshops54471.2021.9669256","DOIUrl":null,"url":null,"abstract":"Deep neural networks provide high accuracy for perception. However they require high computational power. In particular, LiDAR-based object detection delivers good accuracy and real-time performance, but demands high computation due to expensive feature-extraction from point cloud data in the encoder and backbone networks. We investigate the model complexity versus accuracy trade-off using reinforcement learning based pruning for PointPillars, a recent LiDAR-based 3D object detection network. We evaluate the model on the validation dataset of KITTI (80/20-splits) according to the mean average precision (mAP) for the car class. We prune the original PointPillars model (mAP 89.84) and achieve 65.8% reduction in floating point operations (FLOPs) for a marginal accuracy loss. The compression corresponds to 31.7% reduction in inference time and 35% reduction in GPU memory on GTX 1080 Ti.","PeriodicalId":256905,"journal":{"name":"2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ivworkshops54471.2021.9669256","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Deep neural networks provide high accuracy for perception. However they require high computational power. In particular, LiDAR-based object detection delivers good accuracy and real-time performance, but demands high computation due to expensive feature-extraction from point cloud data in the encoder and backbone networks. We investigate the model complexity versus accuracy trade-off using reinforcement learning based pruning for PointPillars, a recent LiDAR-based 3D object detection network. We evaluate the model on the validation dataset of KITTI (80/20-splits) according to the mean average precision (mAP) for the car class. We prune the original PointPillars model (mAP 89.84) and achieve 65.8% reduction in floating point operations (FLOPs) for a marginal accuracy loss. The compression corresponds to 31.7% reduction in inference time and 35% reduction in GPU memory on GTX 1080 Ti.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
资源受限环境下基于激光雷达感知的cnn剪枝
深度神经网络提供了较高的感知精度。然而,它们需要很高的计算能力。特别是,基于激光雷达的目标检测具有良好的准确性和实时性,但由于编码器和骨干网络中点云数据的特征提取成本高,因此需要高计算量。我们使用基于强化学习的PointPillars剪枝来研究模型复杂性与精度之间的权衡,PointPillars是一种最新的基于激光雷达的3D物体检测网络。我们根据汽车类别的平均精度(mAP)在KITTI (80/20- splitting)验证数据集上评估模型。我们对原始的PointPillars模型(mAP 89.84)进行了修剪,在边际精度损失的情况下,浮点运算(FLOPs)减少了65.8%。压缩对应于在GTX 1080 Ti上减少31.7%的推理时间和35%的GPU内存。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Trajectory Planning with Comfort and Safety in Dynamic Traffic Scenarios for Autonomous Driving Unsupervised Joint Multi-Task Learning of Vision Geometry Tasks An adaptive cooperative adaptive cruise control against varying vehicle loads* Fundamental Design Criteria for Logical Scenarios in Simulation-based Safety Validation of Automated Driving Using Sensor Model Knowledge Parameter-Based Testing and Debugging of Autonomous Driving Systems
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1