A Survey of Deep Learning on Mobile Devices: Applications, Optimizations, Challenges, and Research Opportunities

Deep learning (DL) has demonstrated great performance in various applications on powerful computers and servers. Recently, with the advancement of more powerful mobile devices (e.g., smartphones and touch pads), researchers are seeking DL solutions that could be deployed on mobile devices. Compared...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the IEEE 2022-03, Vol.110 (3), p.334-354
Main Authors: Zhao, Tianming, Xie, Yucheng, Wang, Yan, Cheng, Jerry, Guo, Xiaonan, Hu, Bin, Chen, Yingying
Format: Article
Language:English
Subjects:
Accelerators
Cloud computing
Communications systems
Deep learning
Deep learning (DL)
Design methodology
Electronic devices
Hardware
hardware and software accelerator design
Human activity recognition
Machine learning
Mobile handsets
mobile security
mobile sensing
Moving object recognition
Optimization
Remote sensing
Security
Smartphones
Software
Speech recognition
Transportation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning (DL) has demonstrated great performance in various applications on powerful computers and servers. Recently, with the advancement of more powerful mobile devices (e.g., smartphones and touch pads), researchers are seeking DL solutions that could be deployed on mobile devices. Compared to traditional DL solutions using cloud servers, deploying DL on mobile devices have unique advantages in data privacy, communication overhead, and system cost. This article provides a comprehensive survey for the current studies of adopting and deploying DL on mobile devices. Specifically, we summarize and compare the state-of-the-art DL techniques on mobile devices in various application domains involving vision, speech/speaker recognition, human activity recognition, transportation mode detection, and security. We generalize an optimization pipeline for bringing DL to mobile devices, including model-oriented optimization mechanisms (e.g., pruning and quantization) and nonmodel-oriented optimization mechanisms (e.g., software accelerator and hardware design). Moreover, we summarize popular DL libraries regarding their support to state-of-the-art models (software) and processors (hardware). Based on our summarization, we further provide insights into potential research opportunities for developing DL for mobile devices.
ISSN:0018-9219
1558-2256
DOI:10.1109/JPROC.2022.3153408