Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2017

Abstract

Deep learning has revolutionized vision sensing applications in terms of accuracy comparing to other techniques. Its breakthrough comes from the ability to extract complex high level features directly from sensor data. However, deep learning models are still yet to be natively supported on mobile devices due to high computational requirements. In this paper, we present DeepMon, a next generation of DeepSense [1] framework, to enable deep learning models on conventional mobile devices (e.g. Samsung Galaxy S7) for continuous vision sensing applications. Firstly, Deep-Mon exploits similarity between consecutive video frames for intermediate data caching within models to enhance inference latency. Secondly, DeepMon leverages approximation technique (e.g. Tucker decomposition) to build up approximated models with negligible impact on accuracy. Thirdly, DeepMon ofloads heavy computation onto integrated mobile GPU to significantly reduce execution time of the model.

Keywords

Continuous vision, Deep learning, Mobile GPU, Mobile sensing

Discipline

Hardware Systems | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

MobiSys 2017: Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services, Niagara Falls, June 19-23

First Page

186

Last Page

186

ISBN

9781450349284

Identifier

10.1145/3081333.3089331

Publisher

ACM

City or Country

New York

Additional URL

http://doi.org./10.1145/3081333.3089331

Download

Share

COinS