Delivering Deep Learning to Mobile Devices via Offloading
Delivering Deep Learning to Mobile Devices via Offloading
复制标题
DOI：
10.1145/3097895.3097903
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
Xukan Ran;Haoliang Chen;Zhenming Liu;Jiasi Chen
中科院分区：
文献类型：
--
作者：
Xukan Ran;Haoliang Chen;Zhenming Liu;Jiasi Chen
深度学习有可能使增强现实（AR）设备变得更智能，但目前很少有AR应用程序使用这种技术，因为它是计算密集型的，前端设备无法提供足够的计算能力。我们提出了一个分布式框架，将前端设备与更强大的后端“助手”联系在一起，允许深度学习在本地执行或卸载。这个框架应该能够智能地使用当前对网络条件和后端服务器负载的估计，结合应用程序的需求，来确定最佳策略。这项工作报告了我们在实施这样一个框架，其中前端被假定为智能手机的初步调查。我们的具体贡献包括：（1）开发一个Android应用程序，可以在智能手机上本地或服务器上远程执行实时对象检测;（2）根据视频分辨率、深度学习模型大小和卸载决策等系统参数，对对象检测准确性、延迟和电池消耗之间的权衡进行表征。
Deep learning has the potential to make Augmented Reality (AR) devices smarter, but few AR apps use such technology today because it is compute-intensive, and front-end devices cannot deliver sufficient compute power. We propose a distributed framework that ties together front-end devices with more powerful back-end "helpers" that allow deep learning to be executed locally or to be offloaded. This framework should be able to intelligently use current estimates of network conditions and back-end server loads, in conjunction with the application's requirements, to determine an optimal strategy. This work reports our preliminary investigation in implementing such a framework, in which the front-end is assumed to be smartphones. Our specific contributions include: (1) development of an Android application that performs real-time object detection, either locally on the smartphone or remotely on a server; and (2) characterization of the tradeoffs between object detection accuracy, latency, and battery drain, based on the system parameters of video resolution, deep learning model size, and offloading decision.