Zhedong Zheng
Assistant Professor at University of Macau
Municipality of Macau, Macau, Macao
Summary
🤩
Rockstar🎓
Top SchoolZhedong Zheng is a tenure-track Assistant Professor at the University of Macau with 11 years of research and engineering experience in computer vision and representation learning, particularly image and person re-identification. He completed a Ph.D. at the University of Technology Sydney and held a postdoctoral fellowship at NUS under leading vision researchers, with internships at NVIDIA and Baidu that grounded his work in applied ML. Zhedong maintains an active open-source presence—his Person_reID_baseline_pytorch repo and contributions to NVlabs' DG-Net and pytorch-metric-learning reflect hands-on expertise in metric learning, GANs, and multi-GPU model engineering. He combines rigorous academic publication with practical code optimizations and model integrations, often bridging research prototypes to usable baselines. Notably, his consistent early academic excellence (four first-class scholarships at Fudan) and history of refining community toolkits show a blend of teaching, research, and production-ready development.
11 years of coding experience
Bachelor of Science (B.S.) Computer Science, Bachelor of Science (B.S.) Computer Science at Fudan UniversityXiangming High SchoolDoctor of Philosophy (Ph.D.) Computer science, Doctor of Philosophy (Ph.D.) Computer science at University of Technology Sydney
Stackoverflow
1reputation
0reached
2answers
0questions
Github Skills (21)
pytorch10
python10
machine-learning10
deep-learning10
swin-transformer10
computer-vision10
dcgan9
testing9
unit-testing9
multiple-gpu9
cgan9
model-testing9
trainings9
multi-gpu9
modeling9
Programming languages (12)
Github contributions (5)
layumi/Person_reID_baseline_pytorch
Jan 2018 - Dec 2022
:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
Role in this project:
ML Engineer
ML EngineerContributions:4 releases, 660 commits, 25 PRs in 5 years
Contributions summary:Zhedong primarily focused on implementing and testing different deep learning models for person and vehicle re-identification, a computer vision task. They integrated Swin Transformer V2 models and made adjustments to the training and testing pipelines to accommodate the new models. Additionally, they addressed variable usage within the code and added data input modifications for improved compatibility.
reid-baselinegait-recognitionmetric-learningre-rankingperson-reid
NVlabs/DG-Net
Jul 2019 - Mar 2022
Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral)
Role in this project:ML Engineer
ML EngineerContributions:50 commits, 1 PR, 52 pushes in 2 years 8 months
Contributions summary:Zhedong primarily focused on updating and refining the existing machine learning model within the DG-Net project. Their commits include removing unused libraries, addressing multi-GPU utilization, and fixing errors related to specific configurations, such as the use of "normal". They also updated the teacher model and adapted the code to incorporate different GAN types. These changes suggest ongoing development and optimization of the core deep learning components.
pytorchpersondeep-learningjointgenerative
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.