Tree-Based Unidirectional Neural Networks for Low-Power Computer Vision
Tree-Based Unidirectional Neural Networks for Low-Power Computer Vision
复制标题
DOI：
10.1109/mdat.2022.3217016
复制
发表时间：
2023-06
影响因子：
2
通讯作者：
Abhinav Goel;Caleb Tung;Nick Eliopoulos;G. Thiruvathukal;Amy Wang;Yung-Hsiang Lu;James C. Davis
中科院分区：
文献类型：
--
作者：
Abhinav Goel;Caleb Tung;Nick Eliopoulos;G. Thiruvathukal;Amy Wang;Yung-Hsiang Lu;James C. Davis
编者按：卷积神经网络（CNN）为高精度计算机视觉铺平了道路。本文提出了一种基于树的多个浅CNN的层次结构，以实现嵌入式设备的低功耗实现。-Muhammad Shafique，阿布扎比纽约大学
Editor’s notes: Convolutional neural networks (CNNs) have paved paths for highaccuracy computer vision. This article presents a tree-based hierarchy of multiple shallow CNNs to enable their low-power implementations for embedded devices. —Muhammad Shafique, New York University Abu Dhabi