I now work as an engineer in the Robotics Lab at Horizon Robotics, focusing on manipulation algorithms and improving their real-world applicability. Before that, I earned my master’s degree in computer science from Shanghai Jiao Tong University under the supervision of Prof. Lizhuang Ma. My research focused on monocular lane detection and segmentation, as well as learning with limited human supervision. I also worked on autonomous parking at Momenta, contributing to the mass production of its APA software.
Education
- 2013.9 - 2016.6: Qingdao No.2 High School
- 2016.9 - 2020.6: Harbin Institute of Technology, Weihai (BEng in information security)
- 2020.9 - 2023.3: Shanghai Jiao Tong University DMCV Lab (MSc in computer science)
Work
- 2021.6 - 2022.12: Shanghai AI Lab & SenseTime (Internship).
- 2023.4 - 2026.8: Momenta.
- 2026.8 - now: Horizon Robotics.
Selected Publications
Rethinking Efficient Lane Detection via Curve Modeling CVPR 2022
Zhengyang Feng, Shaohua Guo, Xin Tan, Ke Xu, Min Wang, Lizhuang Ma
DMT: Dynamic Mutual Training for Semi-Supervised Learning Pattern Recognition 2022
Zhengyang Feng, Qianyu Zhou, Qiqi Gu, Xin Tan, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation ICCV 2021
Qiqi Gu, Qianyu Zhou, Minghao Xu, Zhengyang Feng, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
See full listing of my publications & preprints at Google Scholar.
Open-Source Contributions
- Author of PytorchAutoDrive, a unified platform for self-driving perception tasks.
- Author of Python package importmagician.
- Contributed code to pytorch/vision, OpenPerceptionX/OpenLane, karstenBehrendt/unsupervised_llamas.
Academic Services
- Reviewer for ACMMM, TMM, TVC, Neurocomputing, ICME, ICONIP, etc.
Awards
- 2nd place at 7th BMTT MOTChallenge (MOTSynth-MOT-CVPR22)
Email: zyfeng97@outlook.com
