RRNet: Repetition-Reduction Network for Energy Efficient Depth Estimation

RRNet: Repetition-Reduction Network for Energy Efficient Depth Estimation

Lightweight neural networks that employ depthwise convolution have a significant computational advantage over those that use standard convolution because they involve fewer parameters; however, they also require more time, even with graphics processing units (GPUs). We propose a Repetition-Reduction...

Full description

Bibliographic Details
Main Authors: Sangyun Oh, Hye-Jin S. Kim, Jongeun Lee, Junmo Kim
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Computer vision
deep neural network
depth estimation
encoder–decoder network
lightweight neural network
machine learning
Online Access:https://ieeexplore.ieee.org/document/9110910/

Internet

https://ieeexplore.ieee.org/document/9110910/

Similar Items