Liyi Zhang

Liyi Zhang

Auto-generated profile, based on publicly available information

Liyi Zhang

School of Information Engineering, Tianjin University of Commerce, Tianjin, China

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
25 June 2013 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
JDJizhong Duan
Jizhong Duan
YLYu Liu
Yu Liu
LZLiyi Zhang
Liyi Zhang
It is difficult to solve Magnetic Resonance (MR) image reconstruction problems with linear combinations of total variation and ℓ1 norm regularization terms. In order to solve these compound regularization problems, we propose an efficient algorithm in this letter. The proposed algorithm adopts the Bregman iteration technique to convert the original constrained problem to a sequence of unconstrained problems, which are then solved using operator splitting and variable splitting techniques. Simulation experiments demonstrate that significant improvement of the quality of reconstructed images is achieved by the proposed algorithm when compared to previous methods.

3 December 2020 in Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering)
Verified
Journal Article
Closed access
PDF file
YZYuan Zhang
Yuan Zhang
LZLiyi Zhang
Liyi Zhang
YSYunshan Sun
Yunshan Sun
Background: In computed tomography (CT), it is often not possible for the subject to remain stationary during a scan. Unfortunately, a patient motion would result in degraded spatial resolution and image artifacts. It is desirable to improve reconstruction quality and reduce motion artifacts caused by patient motion. Methods: In this work, a method was proposed to eliminate the influence of the motion on image quality based on phase correlation method. Based on our previous work, projections were first taken by Radon transform and motion parameters were estimated by the phase-only correlation of projections in Radon domain. In addition, an improved image reconstruction algorithm was performed to compensate for the motion effects. Results: Experimental results proved that the proposed method could not only obtain high precision and good real-time performance, but also ensure a superior artifact reduction. Conclusion: Besides, the efficacy of the proposed method have been demonstrated on both simulated and human head experiments.

2 September 2022 in arXiv
Verified
Preprint
Open access
PDF file
LZLiyi Zhang
Liyi Zhang
DBDavid M. Blei
David M. Blei
CNChristian A. Naesseth
Christian A. Naesseth
Variational inference often minimizes the "reverse" Kullbeck-Leibler (KL) KL(q||p) from the approximate distribution q to the posterior p. Recent work studies the "forward" KL KL(p||q), which unlike reverse KL does not lead to variational approximations that underestimate uncertainty. This paper introduces Transport Score Climbing (TSC), a method that optimizes KL(p||q) by using Hamiltonian Monte Carlo (HMC) and a novel adaptive transport map. The transport map improves the trajectory of HMC by acting as a change of variable between the latent variable space and a warped space. TSC uses HMC samples to dynamically train the transport map while optimizing KL(p||q). TSC leverages synergies, where better transport maps lead to better HMC sampling, which then leads to better transport maps. We demonstrate TSC on synthetic and real data. We find that TSC achieves competitive performance when training variational autoencoders on large-scale data.