Lightweight Deep Learning for Resource-Constrained Environments: A Survey
It addresses deployment challenges for lightweight devices, but as a survey, it is incremental in summarizing existing methods rather than introducing new ones.
This survey tackles the problem of deploying deep learning models on resource-constrained devices like mobile phones and microcontrollers, providing comprehensive design guidance for lightweight models, compression methods, and hardware acceleration strategies to maintain accuracy.
Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model's accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.