Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
复制标题
DOI：
10.1109/icpr48806.2021.9412388
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Yoshitomo Matsubara;M. Levorato
中科院分区：
文献类型：
--
作者：
Yoshitomo Matsubara;M. Levorato
边缘计算范式将具有计算能力的设备-边缘服务器-放置在网络边缘，以帮助移动设备执行数据分析任务。直观地说，将计算密集型任务分流到边缘服务器可以减少它们的执行时间。然而，将移动设备连接到边缘服务器的无线信道的恶劣条件可能会降低边缘卸载实现的总体捕获到输出延迟。在这里，我们专注于通过深度神经网络(DNNS)支持远程目标检测的边缘计算，并开发了一个框架来减少在无线链路上传输的数据量。我们提出的核心思想建立在最近将DNN拆分成分别由移动设备和边缘服务器执行的部分(即头部和尾部模型)的方法之上。然后，使用无线链路将头部模型最后一层的输出传输到边缘服务器，而不是DNN输入。以前的大多数工作都集中在分类任务上，而没有改变DNN的结构。这里，我们的重点是用于三个不同目标检测任务的DNN，它们呈现了一个更加复杂的结构，并修改了网络结构以：(I)通过在头部模型的早期层中引入瓶颈层来实现网络内压缩，以及(Ii)使用卷积神经网络对不包含感兴趣对象的图像进行预过滤。结果表明，在这些极点解不能提供令人满意的性能的参数区域内，所提出的方法代表了局部计算和边缘计算之间的有效中间选择。代码和经过训练的模型可在https://github.com/yoshitomo-matsubaralhnd-ghnd-object-detectors.上找到
The edge computing paradigm places compute-capable devices - edge servers - at the network edge to assist mobile devices in executing data analysis tasks. Intuitively, offloading compute-intense tasks to edge servers can reduce their execution time. However, poor conditions of the wireless channel connecting the mobile devices to the edge servers may degrade the overall capture-to-output delay achieved by edge offloading. Herein, we focus on edge computing supporting remote object detection by means of Deep Neural Networks (DNNs), and develop a framework to reduce the amount of data transmitted over the wireless link. The core idea we propose builds on recent approaches splitting DNNs into sections - namely head and tail models - executed by the mobile device and edge server, respectively. The wireless link, then, is used to transport the output of the last layer of the head model to the edge server, instead of the DNN input. Most prior work focuses on classification tasks and leaves the DNN structure unaltered. Herein, our focus is on DNNs for three different object detection tasks, which present a much more convoluted structure, and modify the architecture of the network to: (i) achieve in-network compression by introducing a bottleneck layer in the early layers on the head model, and (ii) prefilter pictures that do not contain objects of interest using a convolutional neural network. Results show that the proposed technique represents an effective intermediate option between local and edge computing in a parameter region where these extreme point solutions fail to provide satisfactory performance. The code and trained models are available at https://github.com/yoshitomo-matsubaralhnd-ghnd-object-detectors.