Journal
PROCEEDINGS OF THE IEEE
Volume 110, Issue 3, Pages 334-354Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JPROC.2022.3153408
Keywords
Deep learning; Pipelines; Transportation; Mobile handsets; Hardware; Software; Libraries; Deep learning (DL); hardware and software accelerator design; mobile security; mobile sensing; optimization
Categories
Funding
- National Science Foundation [CCF2000480, CCF2028858, CCF2028894, CCF2028873, CCF2028876, CCF1909963, CNS1815908, CNS1717356]
Ask authors/readers for more resources
This article provides a comprehensive survey and summary of the current research on adopting and deploying deep learning on mobile devices. It introduces the state-of-the-art DL techniques, optimization pipeline, and popular DL libraries for mobile devices, and provides insights into potential research opportunities for developing DL for mobile devices.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available