Bolei Zhou

Assistant Professor
Computer Science Department, University of California, Los Angeles
Office: 295D, Engineering VI, UCLA

I study interpretable human-AI interaction for computer vision and machine autonomy. I am also interested in understanding various human-centric properties of current AI models beyond their accuracy, such as explainability, interpretability, steerability, generalization, fairness and bias.

Some of the earlier works I co-authored are Class Activation Mapping (CAM), Places, ADE20K, Network Dissection.

News

Apr 19, 2022 MetaDrive simulator is updated to facilitate research on RL generalizability, safe exploration, and Multi-Agent traffic simulation.
Jan 2, 2022 After wonderful 3 years at CUHK, I moved to UCLA CS to continue my academic journey.
Oct 8, 2021 honored to be in the ICCV Mentors and the PhD Consortium. Come to join Mentorship Social Session.
Oct 8, 2021 I gave a tutorial talk on Human-centric AI at ICCV’21 Tutorial on Trustworthy and Explainable Computer Vision, I also shared the story of my rejection experiences at ICCV@SSLL workshop.
Sep 29, 2021 Two papers are accepted to NeurIPS’21, one on efficient GAN training and the other on Multi-Agent RL.
Sep 15, 2021 Expert Guided Policy Optimization is accepted to the 5th Conference on Robot Learning (CoRL).
Sep 10, 2021 Homepage is rebuilt through Jekyll :sparkles:

Selected Publications

  1. TPAMI
    MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
    Quanyi Li*, Zhenghao Peng*, Lan Feng, Qihang Zhang, Zhenghai Xue, and Bolei Zhou
    IEEE Transactions on Pattern Analysis and Machine Intelligence (minor revision) (TPAMI) , 2022
  2. CVPR
    Improving GAN Equilibrium by Raising Spatial Awareness
    Jianyuan Wang, Ceyuan Yang, Yinghao Xu, Yujun Shen, Hongdong Li, and Bolei Zhou
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2022
  3. CVPR
    3D-aware Image Synthesis via Learning Structural and Textural Representations
    Yinghao Xu, Sida Peng, Ceyuan Yang, Yujun Shen, and Bolei Zhou
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2022
  4. ICLR
    Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization
    Quanyi Li, Zhenghao Peng, and Bolei Zhou
    International Conference on Learning Representations (ICLR) , 2022
  5. NeurIPS
    Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization
    Zhenghao Peng, Quanyi Li, Chunxiao Liu, and Bolei Zhou
    Neural Information Processing Systems (NeurIPS) , 2021
  6. NeurIPS
    Data-Efficient Instance Generation from Instance Discrimination
    Ceyuan Yang, Yujun Shen, Yinghao Xu, and Bolei Zhou
    Neural Information Processing Systems (NeurIPS) , 2021
  7. CoRL
    Safe Driving via Expert Guided Policy Optimization
    Zhenghao Peng*, Quanyi Li*, Chunxiao Liu, and Bolei Zhou
    Conference on Robot Learning (CoRL) , 2021
  8. CVPR Oral
    Closed-form factorization of latent semantics in GANs
    Yujun Shen, and Bolei Zhou
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Oral) , 2021
  9. CVPR Oral
    Generative hierarchical features from synthesizing images
    Yinghao Xu, Yujun Shen, Jiapeng Zhu, Ceyuan Yang, and Bolei Zhou
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Oral) , 2021
  10. IJCV
    Semantic hierarchy emerges in deep generative representations for scene synthesis
    Ceyuan Yang, Yujun Shen, and Bolei Zhou
    International Journal of Computer Vision (IJCV) , 2021
  11. TPAMI
    InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs
    Yujun Shen, Ceyuan Yang, Xiaoou Tang, and Bolei Zhou
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2020
  12. PNAS
    Understanding the role of individual units in a deep neural network
    David Bau, Jun-Yan Zhu, Hendrik Strobelt, Agata Lapedriza, Bolei Zhou, and Antonio Torralba
    Proceedings of the National Academy of Sciences (PNAS) , 2020