Benjin Zhu

PhD Student at CUHK, more details can be found in CV.

Block A, Raycom Infotech Park, Haidian District

Beijing, China, 100190

I got my B.Eng. from Software Engineering College (Excellent Engineer Class) of South China University of Technology (one of the “Project 985” of China) in July 2018. I will become a PhD student at CUHK in Fall 2021.

Currently, I’m a full-time researcher at the BaseDetection Team of MEGVII Technology, focusing on computer vision (e.g., object detection, classification, unsupervised learning, and 3D scene understanding). At MEGVII, I’m mentored by Zeming Li and previously by Dr. Gang Yu, under the supervision of Dr. Jian Sun.

Apart from research, I have built and maintained many codebases for the research in our group. Make research more systematic is also exciting.

In my spare time, I like to travel and take photos of the beautiful world. I have an American Shorthair cat named PiPi and a Munchkin cat named BoBo.


Dec 8, 2020 A collection of self-supervised methods has been release at SelfSup.
Oct 8, 2020 EqCo is available on arXiv.
Jul 8, 2020 The multi task computer vision toolkit cvpods is released! Stay tuned for updates!!! :sparkles:
Jul 7, 2020 AutoAssign is available on arXiv.
Aug 8, 2019 World’s first general 3D object detection codebase Det3D is released! :sparkles:
Jun 15, 2019 We win the nuScenes 3D object Detection challenge of WAD, CVPR 2019, by a large margin. :sparkles:
Feb 18, 2019 I join MEGVII Research! :smile:
Jan 10, 2019 My work - the LiDAR sensing demo at Horizon is demonstrated on CES 2019.
Jun 30, 2018 I graduate with B.E. in Software Engineering (Excellent Engineer Class), SCUT.

selected publications

  1. arXiv
    EqCo: Equivalent Rules for Self-supervised Contrastive Learning
    Benjin, Zhu, Junqiang, Huang, Zeming, Li, Xiangyu, Zhang, and Jian, Sun
    In submission. 2020
  2. arXiv
    AutoAssign: Differentiable Label Assignment for Dense Object Detection
    Benjin, Zhu, Jianfeng, Wang, Zhengkai, Jiang, Fuhang, Zong, Songtao, Liu, Zeming, Li, and Jian, Sun
    In submission. 2020