Close the Gap between Deep Learning and Mobile Intelligence by Incorporating Training in the Loop
Close the Gap between Deep Learning and Mobile Intelligence by Incorporating Training in the Loop
复制标题
DOI：
10.1145/3343031.3350904
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Cong Wang;Y. Xiao;Xing Gao;Li Li-Li;Jun Wang
中科院分区：
文献类型：
--
作者：
Cong Wang;Y. Xiao;Xing Gao;Li Li-Li;Jun Wang
预先训练好的深度学习模型可以部署在移动设备上进行推理。但是，在此之后，它们通常不会更新。在本文中，我们进一步将深层神经网络的训练融入到电池供电的移动设备上，克服了由于缺乏标签数据而带来的困难。我们设计并实现了一种新的框架，通过数据配对来扩大样本空间，并在隐私、存储和计算约束下学习深度度量。并对深度行为认证进行了实例分析。我们的实验表明，在三个公共数据集上的准确率超过95%，与传统的多类分类相比，在数据较少的情况下，准确率提高了15%，并且对暴力攻击的鲁棒性达到99%。我们在各种智能手机机型上展示了训练性能，其中训练100个纪元只需不到10分钟，通过功能转移可以提高3-5倍。我们还分析了内存、能量和计算开销。我们的结果表明，训练比观看视频消耗的能量更低，因此可以在移动设备上间歇性地安排训练。
Pre-trained deep learning models can be deployed on mobile devices to conduct inference. However, they are usually not updated thereafter. In this paper, we take a step further to incorporate training deep neural networks on battery-powered mobile devices and overcome the difficulties from the lack of labeled data. We design and implement a new framework to enlarge sample space via data paring and learn a deep metric under the privacy, memory and computational constraints. A case study of deep behavioral authentication is conducted. Our experiments demonstrate accuracy over 95% on three public datasets, a sheer 15% gain from traditional multi-class classification with less data and robustness against brute-force attacks with 99% success. We demonstrate the training performance on various smartphone models, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer. We also profile memory, energy and computational overhead. Our results indicate that training consumes lower energy than watching videos so can be scheduled intermittently on mobile devices.