DMS: Dynamic Model Scaling for Quality-Aware Deep Learning Inference in Mobile and Embedded Devices
Recently, deep learning has brought revolutions to many mobile and embedded systems that interact with the physical world using continuous video streams. Although there have been significant efforts to reduce the computational overheads of deep learning inference in such systems, previous approaches...
Main Authors: | Woochul Kang, Daeyeon Kim, Junyoung Park |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8907822/ |
Similar Items
-
Power- and Time-Aware Deep Learning Inference for Mobile Embedded Devices
by: Woochul Kang, et al.
Published: (2019-01-01) -
Deep Neural Network Compression Technique Towards Efficient Digital Signal Modulation Recognition in Edge Device
by: Ya Tu, et al.
Published: (2019-01-01) -
Fast Convolutional Neural Networks in Low Density FPGAs Using Zero-Skipping and Weight Pruning
by: Mário P. Véstias, et al.
Published: (2019-11-01) -
On-Device Deep Learning Inference for Efficient Activity Data Collection
by: Nattaya Mairittha, et al.
Published: (2019-08-01) -
Human Segmentation Based on Compressed Deep Convolutional Neural Network
by: Jun Miao, et al.
Published: (2020-01-01)