Model Compression for Deep Neural Networks: A Survey
Computers · 12.03.2023 · 12 (3) · 60
DOI: 10.3390/computers12030060 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers, online erschienen am 12.03.2023. Verfasst von Zhuo Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 319-mal zitiert (Crossref) und nennt 151 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Li, Z., Li, H., & Meng, L. (2023). Model Compression for Deep Neural Networks: A Survey. Computers, 12(3), 60. https://doi.org/10.3390/computers12030060
Vancouver
Li Z, Li H, Meng L. Model Compression for Deep Neural Networks: A Survey. Computers. 2023;12(3):60. doi:10.3390/computers12030060
BibTeX
@article{Li2023,
author = {Li, Zhuo and Li, Hengyi and Meng, Lin},
title = {Model Compression for Deep Neural Networks: A Survey},
journal = {Computers},
year = {2023},
volume = {12},
number = {3},
pages = {60},
doi = {10.3390/computers12030060}
}
EUVIMED