Xuguang Wang

Xuguang Wang

Auto-generated profile, based on publicly available information

Xuguang Wang

Suzhou Institute of Nano-Tech and Nano-Bionics (SINANO), Chinese Academy of Sciences, Suzhou, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
10 March 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
YZYangfan Zhou
Yangfan Zhou
Kaizhu HuangKaizhu Huang
Kaizhu Huang
CCCheng Cheng
Cheng Cheng
XWXuguang Wang
Xuguang Wang
AHAmir Hussain
Amir Hussain
XLXin Liu
Xin Liu
AdaBelief, one of the current best optimizers, demonstrates superior generalization ability over the popular Adam algorithm by viewing the exponential moving average of observed gradients. AdaBelief is theoretically appealing in which it has a data-dependent O(√T) regret bound when objective functions are convex, where T is a time horizon. It remains, however, an open problem whether the convergence rate can be further improved without sacrificing its generalization ability. To this end, we make the first attempt in this work and design a novel optimization algorithm called FastAdaBelief that aims to exploit its strong convexity in order to achieve an even faster convergence rate. In particular, by adjusting the step size that better considers strong convexity and prevents fluctuation, our proposed FastAdaBelief demonstrates excellent generalization ability and superior convergence. As an important theoretical contribution, we prove that FastAdaBelief attains a data-dependent O(log T) regret bound, which is substantially lower than AdaBelief in strongly convex cases. On the empirical side, we validate our theoretical analysis with extensive experiments in scenarios of strong convexity and nonconvexity using three popular baseline models. Experimental results are very encouraging: FastAdaBelief converges the quickest in comparison to all mainstream algorithms while maintaining an excellent generalization ability, in cases of both strong convexity or nonconvexity. FastAdaBelief is, thus, posited as a new benchmark model for the research community.

11 January 2022 in Cognitive Computation
Verified
Journal Article
Closed access
PDF file
YZYangfan Zhou
Yangfan Zhou
Kaizhu HuangKaizhu Huang
Kaizhu Huang
CCCheng Cheng
Cheng Cheng
XWXuguang Wang
Xuguang Wang
XLXin Liu
Xin Liu

6 July 2022
Verified
Book Chapter
Closed access
PDF file
BYBowen Yu
Bowen Yu
YZYangfan Zhou
Yangfan Zhou
XLXin Liu
Xin Liu
XWXuguang Wang
Xuguang Wang

1 May 2017
Verified
Conference Paper
Closed access
CHChen Hu
Chen Hu
HWHuaqiang Wu
Huaqiang Wu
XWXuguang Wang
Xuguang Wang
HWHaoyuan Wang
Haoyuan Wang
QHQinglin He
Qinglin He
This paper proposes an efficient feature detection solution called AFD (Auto-adapted Feature Detection) based on FAST and LDB applied to outdoor real-time video stitching system. As FAST features are sensitive to illumination and blur, AFD comes out to optimize it. AFD detects features with local and global auto-adapted FAST threshold. Global score compensation is adopted to get good performance under different outdoor situation as well. We use a multiple grid test method to generate more distinctive descriptors. In order to reduce the computing time and increase accuracy, features are extracted in the region of interest (ROI). The feature detection with low complexity and robustness performs well in the real-time stitching system.

25 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
YZYangfan Zhou
Yangfan Zhou
Kaizhu HuangKaizhu Huang
Kaizhu Huang
CCCheng Cheng
Cheng Cheng
XWXuguang Wang
Xuguang Wang
AHAmir Hussain
Amir Hussain
XLXin Liu
Xin Liu
AdaBelief, one of the current best optimizers, demonstrates superior generalization ability compared to the popular Adam algorithm by viewing the exponential moving average of observed gradients. AdaBelief is theoretically appealing in that it has a data-dependent $O(\sqrt{T})$ regret bound when objective functions are convex, where $T$ is a time horizon. It remains however an open problem whether the convergence rate can be further improved without sacrificing its generalization ability. %on how to exploit strong convexity to further improve the convergence rate of AdaBelief. To this end, we make a first attempt in this work and design a novel optimization algorithm called FastAdaBelief that aims to exploit its strong convexity in order to achieve an even faster convergence rate. In particular, by adjusting the step size that better considers strong convexity and prevents fluctuation, our proposed FastAdaBelief demonstrates excellent generalization ability as well as superior convergence. As an important theoretical contribution, we prove that FastAdaBelief attains a data-dependant $O(\log T)$ regret bound, which is substantially lower than AdaBelief. On the empirical side, we validate our theoretical analysis with extensive experiments in both scenarios of strong and non-strong convexity on three popular baseline models. Experimental results are very encouraging: FastAdaBelief converges the quickest in comparison to all mainstream algorithms while maintaining an excellent generalization ability, in cases of both strong or non-strong convexity. FastAdaBelief is thus posited as a new benchmark model for the research community.

23 May 2022 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
YZYangfan Zhou
Yangfan Zhou
Kaizhu HuangKaizhu Huang
Kaizhu Huang
CCCheng Cheng
Cheng Cheng
XWXuguang Wang
Xuguang Wang
AHAmir Hussain
Amir Hussain
XLXin Liu
Xin Liu
The training process for deep learning and pattern recognition normally involves the use of convex and strongly convex optimization algorithms such as AdaBelief and SAdam to handle lots of “uninformative” samples that should be ignored, thus incurring extra calculations. To solve this open problem, we propose to design bandit sampling method to make these algorithms focus on “informative” samples during training process. Our contribution is twofold: first, we propose a convex optimization algorithm with bandit sampling, termed AdaBeliefBS, and prove that it converges faster than its original version; second, we prove that bandit sampling works well for strongly convex algorithms, and propose a generalized SAdam, called SAdamBS, that converges faster than SAdam. Finally, we conduct a series of experiments on various benchmark datasets to verify the fast convergence rate of our proposed algorithms.