Context-aware Model Selection for On-Device Object Detection

Seongju Kang, Chaeeun Jeong, K. Chung
{"title":"Context-aware Model Selection for On-Device Object Detection","authors":"Seongju Kang, Chaeeun Jeong, K. Chung","doi":"10.1109/ICOIN50884.2021.9333918","DOIUrl":null,"url":null,"abstract":"A deep neural network (DNN) has become a key technique in many intelligent application domains. Since the DNN model has dozens of layers and millions of levels of parameters, the machine has to execute computation-intensive workloads. Therefore, it is difficult to perform DNN inference in resource-constrained devices such as mobile devices. In this paper, we propose a context-aware model selection for on-device DNN inference. The proposed model selection chooses a DNN model corresponding to a spatiotemporal domain based on the context information of the device. Since a context-aware model detects related objects by spatiotemporal domain, it has a low dimension of parameters. In resource-constrained environments, the proposed context-aware model enables high-accuracy inference at low latency. To evaluate the performance of the proposed model selection, we conduct comparison experiments with the existing object detection model. Through experiments, we confirm that the context-aware model performs better than the existing trained models when on-device object detection is performed. Finally, we discuss the limits of the proposed model selection.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"45 1","pages":"662-666"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Information Networking (ICOIN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOIN50884.2021.9333918","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

A deep neural network (DNN) has become a key technique in many intelligent application domains. Since the DNN model has dozens of layers and millions of levels of parameters, the machine has to execute computation-intensive workloads. Therefore, it is difficult to perform DNN inference in resource-constrained devices such as mobile devices. In this paper, we propose a context-aware model selection for on-device DNN inference. The proposed model selection chooses a DNN model corresponding to a spatiotemporal domain based on the context information of the device. Since a context-aware model detects related objects by spatiotemporal domain, it has a low dimension of parameters. In resource-constrained environments, the proposed context-aware model enables high-accuracy inference at low latency. To evaluate the performance of the proposed model selection, we conduct comparison experiments with the existing object detection model. Through experiments, we confirm that the context-aware model performs better than the existing trained models when on-device object detection is performed. Finally, we discuss the limits of the proposed model selection.
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
设备上对象检测的上下文感知模型选择
深度神经网络(DNN)已成为许多智能应用领域的关键技术。由于深度神经网络模型有数十层和数百万层参数,机器必须执行计算密集型工作负载。因此,在移动设备等资源受限的设备中很难进行深度神经网络推理。在本文中,我们提出了一种用于设备上DNN推理的上下文感知模型选择。提出的模型选择方法是基于设备的上下文信息选择与时空域相对应的DNN模型。由于上下文感知模型通过时空域检测相关对象,因此具有低维参数。在资源受限的环境中,所提出的上下文感知模型能够以低延迟实现高精度推理。为了评估所提出的模型选择的性能,我们与现有的目标检测模型进行了比较实验。通过实验,我们确认上下文感知模型在执行设备上对象检测时比现有的训练模型表现得更好。最后,我们讨论了所提出的模型选择的局限性。
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
A Study on the Cluster-wise Regression Model for Bead Width in the Automatic GMA Welding GDFed: Dynamic Federated Learning for Heterogenous Device Using Graph Neural Network A Solution for Recovering Network Topology with Missing Links using Sparse Modeling Real-time health monitoring system design based on optical camera communication Multimedia Contents Retrieval based on 12-Mood Vector
×
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