Dr. Kaiyang Zhou Email: k [dot] zhou [dot] vision [at] gmail [dot] com Note: previous emails have been deprecated (qmul.ac.uk; surrey.ac.uk) Links: Github | Google Scholar

Bio

Kaiyang Zhou obtained his PhD (2020) from the University of Surrey, UK, under the supervision of Tao Xiang and Yongxin Yang. He received his MSc with Distinction (2016) from the University of Bristol, UK, his BSc with 1st class honor (2015) from the Ulster University, UK, and his BEng (2015) from Fujian Normal University, China. He has worked in Samsung AI Center Cambridge, UK, as a research intern from 2018-2019, and in Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, as a research assistant with Yu Qiao from 2016-2017.

Kaiyang's research interests are in computer vision, machine learning, and deep learning. He has published several papers in top conferences of computer vision and machine learning, such as ICCV, ECCV, AAAI, and ICLR. He serves as reviewer for T-PAMI, IJCV, CVPR, AAAI, etc. In addition to the interests and enthusiasm in solving research problems, he is also passionate about developing open-source software to contribute to the research community (e.g., Torchreid and Dassl.pytorch).

Kaiyang will join Chen Change Loy's group at NTU, Singapore, as a postdoctoral research fellow.

Publications

• Domain Generalization with MixStyle
  Kaiyang Zhou, Yongxin Yang, Yu Qiao, Tao Xiang
  International Conference on Learning Representations (ICLR), 2021. (Accepted)
  openreview
• Learning to Generate Novel Domains for Domain Generalization
  Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, Tao Xiang
  European Conference on Computer Vision (ECCV), 2020.
  arxiv
• Domain Adaptive Ensemble Learning
  Kaiyang Zhou, Yongxin Yang, Yu Qiao, Tao Xiang
  Tech report, arXiv, 2020.
  arxiv | code
• Deep Domain-Adversarial Image Generation for Domain Generalisation
  Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, Tao Xiang
  AAAI Conference on Artificial Intelligence (AAAI), 2020.
  arxiv | code | data
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
  Kaiyang Zhou, Tao Xiang
  Tech report, arXiv, 2019.
  arxiv | code
• Learning Generalisable Omni-Scale Representations for Person Re-Identification
  Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang
  arXiv preprint, 2019.
  arxiv | code | models
• Omni-Scale Feature Learning for Person Re-Identification
  Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang
  International Conference on Computer Vision (ICCV), 2019.
  arxiv | code | models
• Video Summarisation by Classification with Deep Reinforcement Learning
  Kaiyang Zhou, Tao Xiang, Andrea Cavallaro
  British Machine Vision Conference (BMVC), 2018
  arxiv
• Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward
  Kaiyang Zhou, Yu Qiao, Tao Xiang
  AAAI Conference on Artificial Intelligence (AAAI), 2018
  arxiv | theano code | pytorch code | data
• Detecting Humans in RGB-D Data with CNNs
  Kaiyang Zhou, Adeline Paiement, Majid Mirmehdi
  IAPR International Conference on Machine Vision Applications (MVA), 2017
  pdf | matlab code