Jie Liu

Jie Liu

Auto-generated profile, based on publicly available information

Jie Liu

College of Electric and Informational Engineering, Lanzhou University of Technology, LanZhou, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2024 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
CSChanghong Shi
Changhong Shi
WLWeirong Liu
Weirong Liu
JMJiahao Meng
Jiahao Meng
XJXiongfei Jia
Xiongfei Jia
JLJie Liu
Jie Liu

13 March 2024 in Neural Processing Letters
Verified
Journal Article
Open access
PDF file
WLWeirong Liu
Weirong Liu
MZMin Zhang
Min Zhang
CSChanghong Shi
Changhong Shi
NZNing Zhang
Ning Zhang
JLJie Liu
Jie Liu
Due to deep neural networks (DNNs) a large number of parameters, DNNs increase the demand for computing and storage during training, reasoning and deployment, especially when DNNs stack deeper and wider. Tensor decomposition can not only compress DNN models but also reduce parameters and storage requirements while maintaining high accuracy and performance. About tensor ring (TR) decomposition of tensor decomposition, there are two problems: (1) The practice of setting the TR rank to be equal in TR decomposition results in an unreasonable rank configuration. (2) The training time of selecting rank through iterative processes is time-consuming. To address the two problems, a TR network compression method by Variational Bayesian (TR-VB) is proposed based on the Global Analytic Solution of Empirical Variational Bayesian Matrix Factorization (GAS of EVBMF). The method consists of three steps: (1) rank selection, (2) TR decomposition, and (3) fine-tuning to recover accumulated loss of accuracy. Experimental results show that, for a given network, TR-VB gives the best results in terms of Top-1 accuracy, parameters, and training time under different compression levels. Furthermore, TR-VB validated on CIFAR-10/100 public benchmarks achieves state-of-the-art performance.