Prof. YUE Xiangyu 岳翔宇教授

Assistant Professor (MIEEE)
Education: B.Eng. (NJU), M.S. (Stanford), Ph.D. (UC Berkeley)
Research Area: AI, Big Data and Multimedia Processing
Tel: (852) 3943-8357
Fax: (852) 2603-5032
Address: Rm 814, Ho Sin Hang Engineering Building, CUHK
Email: xyyue [@] ie.cuhk.edu.hk
Website: xyue.io

Research Interests

  • Machine Learning
  • Computer Vision
  • Transfer Learning
  • Label-Efficient Learning


Dr. Xiangyu Yue received his Ph.D. from Department of Electrical Engineering and Computer Sciences at University of California, Berkeley. He received his M.S. from the Electrical Engineering Department at Stanford University in 2016 and B.Eng from the Department of Automation at Nanjing University in 2014. He had research experiences at Google Research, Google [X] Robotics, Baidu AI Lab, Tencent AI Lab, etc. His research broadly spans across machine learning, transfer learning, label-efficient learning, computer vision, with applications in autonomous driving, robotics, medical imaging, etc. He received the prestigious Lotfi A. Zadeh Prize awarding outstanding Ph.D. graduates in EECS department at UC Berkeley.

Recent Selected Publications

  • X. Yue, Z. Zheng, S. Zhang, Y. Gao, T. Darrell, K. Keutzer, and A. S. Vincentelli, “Prototypical Cross-domain Self-Supervised Learning for Few-shot Unsupervised Domain Adaptation”, Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  • X. Yue, Y. Zhang, S. Zhao, A. S. Vincentelli, K. Keutzer, and B. Gong, “Domain Randomization and Pyramid Consistency: Simulation-to-Real Transfer without Accessing Target Domain Data”, International Conference on Computer Vision (ICCV), 2019.
  • S. Zhao*, B. Li*, X. Yue*, Y. Gu, P. Xu, R. Hu, H. Chai, and K. Keutzer, “Multi-source Domain Adaptation for Semantic Segmentation”, Neural Information Processing Systems (NeurIPS), 2019.
  • S. Zhao, X. Yue, S. Zhang, B. Li, H. Zhao, B. Wu, R. Krishna, J. Gonzalez, A. S. Vincentelli, S. Seshia, and K. Keutzer, “A Review of Single-Source Deep Unsupervised Visual Domain Adaptation”, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021.
  • B. Wu, A. Wan*, X. Yue*, P. Jin, S. Zhao, N. Golmant, A. Gholaminejad, J. Gonzalez, and K. Keutzer, “Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions”, Conference on Computer Vision and Pattern Recognition (CVPR), 2018.