Journal Article

Model Compression for Deep Neural Networks: A Survey

Meng, Lin, Li, Hengyi, Li, Zhuo

2023

Overview

Currently, with the rapid development of deep learning, deep neural networks (DNNs) have been widely applied in various computer vision tasks. However, in the pursuit of performance, advanced DNN models have become more complex, which has led to a large memory footprint and high computation demands. As a result, the models are difficult to apply in real time. To address these issues, model compression has become a focus of research. Furthermore, model compression techniques play an important role in deploying models on edge devices. This study analyzed various model compression methods to assist researchers in reducing device storage space, speeding up model inference, reducing model complexity and training costs, and improving model deployment. Hence, this paper summarized the state-of-the-art techniques for model compression, including model pruning, parameter quantization, low-rank decomposition, knowledge distillation, and lightweight model design. In addition, this paper discusses research challenges and directions for future work.

• Publisher: MDPI AG
• Subject: Accuracy / Algorithms / Artificial intelligence / Artificial neural networks / Complexity / Computer vision / Data compression / Decomposition / deep neural networks / Distillation / Field programmable gate arrays / knowledge distillation / Learning / low-rank decomposition / Machine learning / Machine vision / Methods / model compression / model pruning / Neural networks / parameter quantization / Sparsity