TY - JOUR
T1 - A Survey of Methods for Low-Power Deep Learning and Computer Vision
AU - Goel, Abhinav
AU - Tung, Caleb
AU - Lu, Yung-Hsiang
AU - Thiruvathukal, George K.
N1 - Abhinav Goel, Caleb Tung, Yung-Hsiang Lu, and George K. Thiruvathukal
"A Survey of Methods for Low-Power Deep Learning and Computer Vision" 2020 IEEE 6th World Forum on Internet of Things (WF-IoT), New Orleans, LA, USA 2020, https://doi.org/10.6084/m9.figshare.12021300.v1
PY - 2020/1/1
Y1 - 2020/1/1
N2 - Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
AB - Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
KW - deep learning
KW - computer vision
KW - neural networks
KW - low-power systems
UR - https://ecommons.luc.edu/cs_facpubs/241
UR - https://arxiv.org/abs/2003.11066
U2 - 2003.11066v1
DO - 2003.11066v1
M3 - Article
JO - Computer Science: Faculty Publications and Other Works
JF - Computer Science: Faculty Publications and Other Works
ER -