Haichuan Zhang
Biography
Haichuan Zhang is a Ph.D. student from the Pennsylvania State University, majoring in Electrical Engineering. He is a member of the Information Processing & Algorithms Laboratory (IPAL) and his supervisor is Prof. Vishal Monga. Previously, he was a science software engineer at the Institute of Multimedia Knowledge Fusion and Engineering after he got his Bachelor's Degree from Xian Jiaotong University, majoring in Computer Science. He proposed a Whole Slide Image (WSI) online annotation and analysis framework, which is used in AIPath Dataset. He loves using cutting-edge technology to solve problems in the real world. His focus area is Machine Learning and Computer Vision. He is currently concentrating on image restoration tasks such as image deblurring, dehazing, denoising, and image generation.
Phone: +1 (814)-996-8125
Email: haichuan@psu.edu
Linkedin: Haichuan Zhang
Google Scholar: Haichuan Zhang
GitHub: 6zhc
Education
08/2021-Present
Pennsylvania State University
School of Electrical Engineering and Computer Science
Ph.D. in Electrical Engineering
GPA: 3.90/4.0
09/2016-06/2020
Xi'an Jiaotong University
School of Computer Science and Technology
B. Eng. in Computer Science and Technology (Honor Science Program)
GPA: 3.60/4.0
07/2018-08/2018
Duke University (Summer Session)
GPA: 4.0/4.0
Work Experience
Based in the United States:
08/2021-Present
The Pennsylvania State University
Information Processing & Algorithms Laboratory
Position: Research Assistant
Developed the convergent network for image Inverse problem, with a focus on non-blind image deblurring.
Participated in the NTIRE challenges, contributing to tasks on Bokeh effect transformation and non-homogeneous dehazing.
Developed the algorithms for phase correction in ultrasound neuromodulation based on CT images, framing it as a model inversion problem.
06/2024-08/2024
NEC Laboratories America, Inc.
Information Processing & Algorithms Laboratory
Position: Research Internship
Developed a fiber sensor data restoration network based on a conditional diffusion model, which transforms low-quality fiber sensor data from cost-effective sensors into high-quality data.
Enabled downstream algorithms (such as fiber data classification models) trained or designed for high-quality data to accurately process low-quality fiber sensor data without requiring retraining or redesign.
Authored an internal report detailing the fiber sensor data restoration system.
Based in China:
07/2020-06/2021
Xi'an Jiaotong University
The Institute of Multimedia Knowledge Fusion and Engineering
Position: Science Software Engineer
Designed machine learning models for the diagnosis of Renal Cell Carcinoma (RCC).
Developed a cloud-based platform for AI-assisted pathological image annotation.
Conducted research on pathology information management and personalized diagnostics.
06/2019-08/2019
Xi'an Suoer Software Technology Co., Ltd.
Position: Software Engineer Intern
Led a team in designing and developing an online shopping platform.
Received the "Outstanding Production Internship Award".
Ongoing Project
Deep, Convergent, Unrolled Non-Blind Image Deconvolution
Information Processing and Algorithms Lab - Pennsylvania State University, University Park
We propose a deep, interpretable neural network by unrolling the widely-used Half-Quadratic Splitting (HQS) algorithm. A structured parametrization scheme is introduced to ensure convergence with minimal impact on network performance.
The convergence of this neural network, under our parametrization, is both theoretically established and empirically validated through simulations.
In comparison with SOTA, our approach outperforms both traditional iterative algorithms and contemporary deep neural networks by approximately 1 dB in PSNR and 0.1 in SSIM, all while ensuring convergence and maintaining interpretability.
The paper titled ”A Convergent Neural Network for Non-Blind Image Deblurring” has been accepted at the 2023 IEEE International Conference on Image Processing (ICIP). Additionally, ”Deep, Convergent, Unrolled Non-Blind Image Deconvolution” has been published at the IEEE Transactions on Computational Imaging (TCI).
High-Resolution Transcranial Ultrasound Neuromodulation at Large Scale
Information Processing and Algorithms Lab - Pennsylvania State University, University Park
We use CT imaging for Skull-Induced Phase Aberration Correction in Ultrasound Neuromodulation.
We developed the Intelligent Time Delay Search (ITDS) algorithm to iteratively optimize time delay profiles for phased ultrasound arrays.
To overcome ITDS’s speed limitations, we used it to generate training data and propose a domain-enriched, Dual-Branch Skull-Induced Phase Aberration Correction Network (DB-SIPAC), a novel machine learning framework designed to efficiently predict time delay profiles.
The paper ``Domain Enriched Learning for Skull Induced Phase Aberration Correction in Ultrasound Neuromodulation" is under review.
Scene Segmentation-Guided Lens Mapping for Bokeh Effect Transformation
Information Processing and Algorithms Lab - Pennsylvania State University, University Park
We developed the Segmentation-Guided Lens Mapping (SGLM) methodology for Bokeh Effect Transformation, which integrates the Foreground Segmentation Module (FSM) and the Lens Mapping Module (LMM) to highlight the distinct optical properties of various lenses.
The FSM is designed to accurately predict the foreground alpha matte through its Semantic Prediction Branch and Detail Prediction Branch, ensuring sharpness is preserved in the foreground while the bokeh effect is transformed in the out-of-focus regions.
The LMM utilizes multiple encoders and decoders, enabling the conversion of bokeh effects across different lenses, with each encoder and decoder specifically tailored to a particular lens.
Publications
The complete list of publications can be viewed on Google Scholar.
Image Inverse Problem:
Zhang H, Biswas R, Kiani M, Monga, V. Domain Enriched Learning for Skull Induced Phase Aberration Correction in Ultrasound Neuromodulation. Under journal review.
Zhao Y, Li Y, Zhang H, Monga V, Eldar YC. Deep, convergent, unrolled half-quadratic splitting for image deconvolution [j]. published in IEEE Transactions on Computational Imaging. (Link: https://doi.org/10.1109/TCI.2024.3377132)
Zhao Y, Li Y, Zhang H, Monga V, Eldar YC. A convergent neural network for non-blind image deblurring[C] in 2023 IEEE International Conference on Image Processing (ICIP) 2023 Oct 8 (pp. 1505-1509). IEEE. (Link: https://doi.org/10.1109/ICIP49359.2023.10222656)
Hoang T, Zhang H, Yazdani A, Monga V. TransER: Hybrid Model and Ensemble-Based Sequential Learning for Non-Homogenous Dehazing[C] in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023 (pp. 1670-1679). (Link: https://doi.org/10.1109/cvprw59228.2023.00168)
Conde MV, Kolmet M, Seizinger T, et al. Lens-to-lens bokeh effect transformation. NTIRE 2023 challenge report[C] in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023 (pp. 1643-1659). (Link: https://doi.org/10.1109/CVPRW59228.2023.00166)
Ancuti CO, Ancuti C, Vasluianu FA, et al. NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report[C] in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023 (pp. 1808-1824). (Link: https://doi.org/10.1109/CVPRW59228.2023.00180)
Medical Image Problem:
Gao Z, Shi J, Zhang X, Li Y, Zhang H, Wu J, et al. Nuclei Grading of Clear Cell Renal Cell Carcinoma in Histopathological Image by Composite High-Resolution Network[C] in 2021 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI).2021. (Link: https://doi.org/10.1007/978-3-030-87237-3_13）
Wu J, Mao A, Bao X, Zhang H, Gao Z, Wang C, Gong T, Li C. Pimip: An open source platform for pathology information management and integration[C] in 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2021 Dec 9 (pp. 2088-2095). IEEE. (Link: https://doi.org/10.1109/BIBM52615.2021.9669424)
Wu J, Zhang R, Gong T, Bao X, Gao Z, Zhang H, Wang C, Li C. A precision diagnostic framework of renal cell carcinoma on whole-slide images using deep learning[C] in 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2021 Dec 9 (pp. 2104-2111). IEEE. (Link: https://doi.org/10.1109/BIBM52615.2021.9669870)
Wu J, Zhang R, Gong T, Zhang H, Wang C, Li C. A personalized diagnostic generation framework based on multi-source heterogeneous data[C] in 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2021 Dec 9 (pp. 2096-2103). IEEE. (Link: https://10.1109/BIBM52615.2021.9669427)
Wu J, Tang K, Zhang H, et al. Structured Information Extraction of Pathology Reports with Attention-based Graph Convolutional Network[C] in 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2020 Dec 16 (pp. 2395-2402). IEEE. (Link: https://doi.org/10.1109/BIBM49941.2020.9313347)
Shi J, Gao Z, Zhang H, et al. Effects of annotation granularity in deep learning models for histopathological images[C], published in 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2019 Nov 18 (pp. 2702-2708). IEEE. (Link: https://doi.org/10.1109/BIBM47256.2019.8983158)
Puttapirat P, Zhang H, Deng J, et al. OpenHI2—Open source histopathological image platform[C], published in 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2019 Nov 18 (pp. 2696-2701). IEEE. (Link: https://doi.org/10.1109/BIBM47256.2019.8983322)
Puttapirat P, Zhang H, Deng J, et al., OpenHI: Open Platform for Histopathological Image Annotation [J], published in International Journal of Data Mining and Bioinformatics, 2019, 22(4): 328-349. (Link: https://doi.org/10.1504/IJDMB.2019.101393)
Puttapirat P, Zhang H, Lian Y, et al. OpenHI-An open source framework for annotating histopathological image[C], published in 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2018 Dec 3 (pp. 1076-1082). IEEE. (Link: https://doi.org/10.1109/BIBM.2018.8621393)
Patent
Li C, Puttapirat P, Zhang H, inventors; Xian Jiaotong University, assignee. Cloud-based large-scale pathological image collaborative annotation method and system. United States patent, US 11392634, Issued on Jul 19, 2022.
李辰，帕戈姆·普塔皮拉特，张海川，基于云端的大型病理学图像协作注释方法及系统， Chinese patent, CN 109949907, Issued on Jul 13, 2021.
李辰，吴佳伦，高泽宇，张海川，帕戈姆·普塔皮拉特，一种病理图像预后特征权重计算方法及系统，Chinese patent, CN 109949907, Filled on Jul 19, 2022.
Honors & Awards
Milton and Albertha Langdon Memorial Graduate Fellowship, Pennsylvania State University, June 2024.
Outstanding Production Internship Award, Xi'an Suoer Software Technology Co., Ltd. , July 2019
VEX U Robot Skills Challenge World Champion, 2017-2018 VEX Robotics World Championship, May 2018
VEX U Excellent Award, 2017-2018 VEX Robotics World Championship, May 2018
VEX U Robot Skills Challenge Asian Open Champion, 2017-2018 VEX Robotics Asian Open Champion, Dec 2017
VEX U Robotics Asian Open League Finalist, 2017-2018 VEX Robotics Asian Open Champion, Dec 2017
1st Prize, 2017 National College Students Mathematical Modeling Contest for Undergraduate Group Shaanxi Division, Nov 2017
Siyuan Scholarship for Academic Excellence, Xian Jiaotong University, Sep 2017