Guoqing Li

Dr. Guoqing Li

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 January 2021 in Pattern Recognition
Verified
Journal Article
Closed access
GLGuoqing Li
Guoqing Li
MZMeng Zhang
Meng Zhang
JLJiaojie Li
Jiaojie Li
FLFeng Lv
Feng Lv
GTGuodong Tong
Guodong Tong

1 March 2020 in Separation and Purification Technology
Verified
Journal Article
Closed access
HSHaixiang Sun
Haixiang Sun
XLXubing Luo
Xubing Luo
JLJiahui Liu
Jiahui Liu
GLGuoqing Li
Guoqing Li
YZYanwei Zhang
Yanwei Zhang
QNQingshan Niu
Qingshan Niu

10 June 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
TCTinghuan Chen
Tinghuan Chen
BDBin Duan
Bin Duan
QSQi Sun
Qi Sun
MZMeng Zhang
Meng Zhang
GLGuoqing Li
Guoqing Li
BYBei Yu
Bei Yu
Compared with traditional convolutions, grouped convolutional neural networks are promising for both model performance and network parameters. However, existing models with the grouped convolution still have parameter redundancy. In this article, concerning the grouped convolution, we propose a sharing grouped convolution structure to reduce parameters. To efficiently eliminate parameter redundancy and improve model performance, we propose a Bayesian sharing framework to transfer the vanilla grouped convolution to be the sharing structure. Intragroup correlation and intergroup importance are introduced into the prior of the parameters. We handle the Maximum Type II likelihood estimation problem of the intragroup correlation and intergroup importance by a group LASSO-type algorithm. The prior mean of the sharing kernels is iteratively updated. Extensive experiments are conducted to demonstrate that on different grouped convolutional neural networks, the proposed sharing grouped convolution structure with the Bayesian sharing framework can reduce parameters and improve prediction accuracy. The proposed sharing framework can reduce parameters up to 64.17%. For ResNeXt-50 with the sharing grouped convolution on ImageNet dataset, network parameters can be reduced by 96.875% in all grouped convolutional layers, and accuracies are improved to 78.86% and 94.54% for top-1 and top-5, respectively.

11 August 2021 in Journal of Real-Time Image Processing
Verified
Journal Article
Closed access
PDF file
GLGuoqing Li
Guoqing Li
MZMeng Zhang
Meng Zhang
QZQianru Zhang
Qianru Zhang
ZLZhijian Lin
Zhijian Lin

31 August 2024 in Information Sciences
Verified
Journal Article
Closed access
GLGuoqing Li
Guoqing Li
RLRengang Li
Rengang Li
TLTuo Li
Tuo Li
CSChaoyao Shen
Chaoyao Shen
XZXiaofeng Zou
Xiaofeng Zou
NLNanjun Li
Nanjun Li

1 August 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
GLGuoqing Li
Guoqing Li
MZMeng Zhang
Meng Zhang
JZJingwei Zhang
Jingwei Zhang
QZQianru Zhang
Qianru Zhang