Lei Zhao （赵雷）

📍San Marcos, TX, USA

[Github] [LinkedIn] [x.com] [Email] [Website]

I am a Computer Science PhD student at Texas State University, advised by Dr. Chul-Ho Lee [Website]. My current research focuses on Machine Learning Systems(MLSys) and Graph Neural Networks (GNNs).

I have a bit of a "hacker" past that defines my personality. I prefer building the infrastructure from scratch to master every detail. I have experience deploying websites on cloud platforms. I like to squeeze every bit of performance out of hardwares.

🎓Education

Aug 2024 - Present	Texas State University Ph.D. Student in Computer Science (Advisor: Chul-Ho Lee) 🎯 Machine Learning Systems, Graph Neural Networks
Sep 2021 - June 2024	China University of Geosciences M.Eng. in Electronic and Information (Advisor: Longsheng Wei) 🎯 Computer Vision, Image Quality Assessment
Sep 2008 - June 2012	Hubei University of Technology B.Eng. in Electrical Engineering and Automation

📰Publications

A Pavement Crack Segmentation Method Based on Deformable Convolution and Enhanced Perceive Network.[Paper]

Lei Zhao, Longsheng Wei, Zhi Ma, Zhiheng Liu. Multimedia Tools and Applications, 84(19):20995–21016, 2025.

Design the network structure based on DCN and customized UperNet
Reduce the UperNet layers and simplify the PPM head as pavement crack detection relies on local textual details rather than global semantic information.
Adopt deformable convolution as pavement cracks are usually strips rather than square
Fuse features from different heads and the weight of each channel is trainable

Single Human Parsing Based on Visual Attention and Feature Enhancement.[Paper]

Zhi Ma, Lei Zhao, Longsheng Wei. Journal of Advanced Computational Intelligence and Intelligent Informatics, 27(4):561–566, 2023.

Design the network structure based on Cross-Attention and Resnet-101
Add edge sensing module for better perception of edge

Reduced Reference Quality Assessment for Image Retargeting by Earth Mover's Distance.[Paper]

Longsheng Wei, Lei Zhao, Jian Peng. Applied Sciences, 11(20):9776, 2021.

Design the network structure based on SIFT and Saliency features

🗂️Projects

Nov 2022 - April 2023	Building Low-Cost High-Performance GPU Computing Servers for Laboratory Purchased hardware (motherboard, PSU, RAM, GPU, PCIe Splitter, SSD, HDD, etc.) Installed Xubuntu and configured CUDA, Docker, rule-based proxy, NAT traversal, X11 forwarding, etc. Setup dataset server and shared directory with NFS Composed Dockerfile facilitating the quick deployment of frequently-used environments Carried out benchmarks on various combinations of hardware (Intel processor E5v3, E5v2, i7 family, PCIe x1 x4 x8 x16, PCIe 1.0 and 3.0, Nvidia 1080ti, 2080ti, 3090, P102-100, P106-100, etc.) Performance tuning with htop, nvtop, iotop, top, bcache and swap
June 2022 - Aug 2022	EEG and EOG based Real-Time Driver Fatigue Detection [Github] China Graduate Electronics Design Contest Developed a module to translate MATLAB data to Python pickle dump Designed a CNN-based network to fuse EEG and EOG features for real-time driver fatigue detection Prepared slides and poster for demonstration
April 2022 - June 2023	A Malfunction Detection System for Guangzhou Metro System Developed the image preprocessing module to combine the original image and generate images of target areas according to carriage characteristics Adopted YOLOv5 and FastRCNN in the malfunction detection process Developed a module to fuse YOLOv5 and FastRCN recognition results and provide Flask API Composed Docker Compose file facilitating the instant deployment of all modules (frontend, java-backend, python-backend, database)

💼Experience

June 2016 - May 2020	Wuhan Stack Tech Co., Ltd. Founder, Developer Developed websites, chrome extensions, and WeChat applets
July 2012 - May 2016	Ericsson Radio Access Network Engineer System Integration Network Optimization Signals Analysis and Feature Verification against 3GPP Specs
Sep 2010 - June 2011	HGDonline.net Coding Club Web Developer Participated in the revision of university BBS Developed a website named 59score by reverse-engineering the undergraduate registrar system, enabling students to check their grades.

🛠️Skills

Deep Learning Systems: Pipeline bubble optimization, PyTorch profiling, Distributed Data Parallel (DDP), DeepSpeed, 3D parallelism
Programming & Frameworks: Python (PyTorch, OpenCV, TraceViz), C/C++ (OpenMP), CUDA, Shell scripting
Systems & Infrastructure: Linux, Docker Compose, Git, network analysis (Wireshark), Slurm
Web & Tools: JavaScript (AngularJS, Vue.js), PHP (Laravel), API testing (Postman), HTTP debugging (Fiddler), MySQL

🏆Awards

At China University of Geosciences (CUG):
- First Class Scholarship (Awarded twice), Second Class Scholarship (Awarded once)
- Third Class Prize in the China Graduate Electronics Design Contest
At Hubei University of Technology (HBUT):
- Second Class Scholarship (Awarded once), Third Class Scholarship (Awarded twice)
- Outstanding Student

🧾Patents

A Human Body Posture Estimation Method and System Based on Shape Similarity. CN202210752411.0
A Reference-Free Image Quality Evaluation Method Based on Graph Convolution and Multi-scale Features. CN202310801526.9
A Twin Network Single Target Tracking Method and Device. CN202310897743.2
Real-time Semantic Segmentation Method, Device, Electronic Equipment, and Storage Medium for Night Images. CN202310856554.0