Compacting Deep Neural Networks for Internet of Things: Methods and Applications

TL;DR

This paper provides a comprehensive overview of methods to reduce the size and computational demands of deep neural networks for IoT devices, covering techniques like compression, knowledge distillation, and structural modifications.

Contribution

It categorizes and compares various DNN compacting techniques specifically for IoT applications, filling a gap in survey literature.

Findings

Network model compression effectively reduces DNN size.

Knowledge Distillation transfers knowledge to smaller models.

Structural modifications improve efficiency without significant accuracy loss.

Abstract

Deep Neural Networks (DNNs) have shown great success in completing complex tasks. However, DNNs inevitably bring high computational cost and storage consumption due to the complexity of hierarchical structures, thereby hindering their wide deployment in Internet-of-Things (IoT) devices, which have limited computational capability and storage capacity. Therefore, it is a necessity to investigate the technologies to compact DNNs. Despite tremendous advances in compacting DNNs, few surveys summarize compacting-DNNs technologies, especially for IoT applications. Hence, this paper presents a comprehensive study on compacting-DNNs technologies. We categorize compacting-DNNs technologies into three major types: 1) network model compression, 2) Knowledge Distillation (KD), 3) modification of network structures. We also elaborate on the diversity of these approaches and make side-by-side comparisons. Moreover, we discuss the applications of compacted DNNs in various IoT applications and outline future directions.