On-demand deep model compression for mobile devices: A usage-driven model selection framework
Recent research has demonstrated the potential of deploying deep neural networks (DNNs) on resource-constrained mobile platforms by trimming down the network complexity using different compression techniques. The current practice only investigate stand-alone compression schemes even though each comp...
Saved in:
Main Authors: | LIU, Sicong, LIN, Yingyan, ZHOU, Zimu, NAN, Kaiming, LIU, Hui, DU, Junzhao |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2018
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/4734 https://ink.library.smu.edu.sg/context/sis_research/article/5737/viewcontent/mobisys18_liu.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
AdaDeep: A usage-driven, automated deep model compression framework for enabling ubiquitous intelligent mobiles
by: LIU, Sicong, et al.
Published: (2021) -
p-Meta: Towards on-device deep model adaptation
by: QU, Zhongnan, et al.
Published: (2022) -
UbiEar: Bringing location-independent sound awareness to the hard-of-hearing people with smartphones
by: LIU, Sicong, et al.
Published: (2017) -
ACSL : adaptive correlation-driven sparsity learning for deep neural network compression
by: He, Wei, et al.
Published: (2021) -
DeepSense: A GPU-based deep convolutional neural network framework on commodity mobile devices
by: HUYNH NGUYEN LOC,, et al.
Published: (2016)