Literature Review of Deep Network Compression

Deep networks often possess a vast number of parameters, and their significant redundancy in parameterization has become a widely-recognized property. This presents significant challenges and restricts many deep learning applications, making the focus on reducing the complexity of models while maintaining their powerful performance. In this paper, we present an overview of popular methods and review recent works on compressing and accelerating deep neural networks. We consider not only pruning methods but also quantization methods, and low-rank factorization methods. This review also intends to clarify these major concepts, and highlights their characteristics, advantages, and shortcomings.

Automated summary

This paper provides an overview of popular methods for compressing and accelerating deep neural networks, including pruning, quantization, and low-rank factorization. The focus is on reducing redundancy in model parameters while maintaining performance advantages.