Deep Learning Acceleration Techniques for Real Time Mobile Vision Applications

TL;DR

This paper reviews emerging deep learning acceleration techniques that enable real-time visual recognition on mobile devices, addressing the challenge of deploying computationally intensive algorithms in resource-constrained environments.

Contribution

It provides an overview of recent acceleration methods specifically designed for mobile vision applications, facilitating real-time performance on portable devices.

Findings

Deep learning can be adapted for mobile environments with specialized acceleration techniques.

Emerging hardware and algorithmic strategies enable real-time visual recognition on smartphones.

These techniques expand the potential for smart multimedia applications in mobile and embedded systems.

Abstract

Deep Learning (DL) has become a crucial technology for Artificial Intelligence (AI). It is a powerful technique to automatically extract high-level features from complex data which can be exploited for applications such as computer vision, natural language processing, cybersecurity, communications, and so on. For the particular case of computer vision, several algorithms like object detection in real time videos have been proposed and they work well on Desktop GPUs and distributed computing platforms. However these algorithms are still heavy for mobile and embedded visual applications. The rapid spreading of smart portable devices and the emerging 5G network are introducing new smart multimedia applications in mobile environments. As a consequence, the possibility of implementing deep neural networks to mobile environments has attracted a lot of researchers. This paper presents emerging deep learning acceleration techniques that can enable the delivery of real time visual recognition into the hands of end users, anytime and anywhere.