Survey on Computer Vision Techniques for Internet-of-Things Devices

TL;DR

This survey reviews recent low-power, energy-efficient deep neural network techniques for deploying computer vision on resource-constrained IoT devices, focusing on compression, architecture search, and optimization methods.

Contribution

It provides a comprehensive overview of recent advances in low-power DNN techniques tailored for IoT devices, highlighting their advantages, disadvantages, and open research challenges.

Findings

Techniques reduce memory and computation requirements

Survey covers convolutional and transformer DNNs

Identifies open research problems in low-power DNN deployment

Abstract

Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute, memory, and energy-hungry, and consequently difficult to deploy on small battery-powered Internet-of-Things (IoT) devices with limited computing resources. Deployment of DNNs on Internet-of-Things devices, such as traffic cameras, can improve public safety by enabling applications such as automatic accident detection and emergency response.Through this paper, we survey the recent advances in low-power and energy-efficient DNN implementations that improve the deployability of DNNs without significantly sacrificing accuracy. In general, these techniques either reduce the memory requirements, the number of arithmetic operations, or both. The techniques can be divided into three major categories: neural network compression, network architecture search and design, and compiler and graph optimizations. In this paper, we survey both low-power techniques for both convolutional and transformer DNNs, and summarize the advantages, disadvantages, and open research problems.