My Portrait            

Yixiao Ge 葛艺潇

Ph.D. Candidate,
Multimedia Lab (MMLab),
The Chinese University of Hong Kong (CUHK)

  geyixiao831@gmail.com
  SHB 304, CUHK, Hong Kong S.A.R., China

About Me

I am currently a final-year Ph.D. student in Multimedia Lab (MMLab), the Chinese University of Hong Kong (CUHK). I am supervised by Prof. Hongsheng Li and Prof. Xiaogang Wang. Before that, I received bachelor's degree in Measurement and Control Technology and Instrument at Huazhong University of Science and Technology (HUST) in 2017. My research interests include computer vision, deep learning, with focus on unsupervised learning, disentangled learning, domain adaptation, image retrieval and image generation.

News

  • alt text [2021-03] Three papers accepted by CVPR 2021!
  • [2020-09] One paper accepted by NeurIPS 2020.
    [2020-08] We achieved 2nd place in VisDA-2020 Challenge (ECCVW).
    [2020-07] One paper accepted by ECCV 2020 as a Spotlight presentation.
    [2020-07] The OpenUnReID codebase is online.
    [2019-12] One paper accepted by ICLR 2020.
    [2018-09] One paper accepted by NeurIPS 2018.

Publications

2021

Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification

Xiao Zhang*, Yixiao Ge*, Yu Qiao, Hongsheng Li (*Co-first Authors)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network

Rui Liu, Yixiao Ge, Ching Lam Choi, Xiaogang Wang, Hongsheng Li

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Mutual CRF-GNN Network for Few-shot Learning

Shixiang Tang, Dapeng Chen, Lei Bai, Kaijian Liu, Yixiao Ge, Wanli Ouyang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Consensus-Guided Correspondence Denoising

Chen Zhao*, Yixiao Ge*, Jiaqi Yang, Feng Zhu, Rui Zhao, Hongsheng Li (*Co-first Authors)

arXiv preprint, 2021

PDF

2020

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Hongsheng Li

Conference on Neural Information Processing Systems (NeurIPS), 2020

Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID

Yixiao Ge, Shijie Yu, Dapeng Chen

Technique report of top-performing solution to VisDA Challenge (ECCVW), 2020

Self-supervising Fine-grained Region Similarities for Large-scale Image Localization

Yixiao Ge, Haibo Wang, Feng Zhu, Rui Zhao, Hongsheng Li

European Conference on Computer Vision (ECCV), 2020, Spotlight (top-5%)

Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID

Yixiao Ge, Feng Zhu, Rui Zhao, Hongsheng Li

arXiv preprint, 2020

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

Yixiao Ge, Dapeng Chen, Hongsheng Li

International Conference on Learning Representations (ICLR), 2020

Before 2020

FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification

Yixiao Ge*, Zhuowan Li*, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, Hongsheng Li (*Co-first Authors)

Conference on Neural Information Processing Systems (NeurIPS), 2018

Codebase

OpenUnReID: An Open-source Toolbox for Unsupervised or Domain Adaptive Object Re-ID

OpenUnReID Development Team

July 2020

OpenIBL: An Open-source Toolbox for Image-based Localization (Place Recognition)

Yixiao Ge

Jun 2020

Working Experience

Professional Activities

  • Journal Reviewer of IJCV, IEEE TIP, IEEE TCSVT, IEEE TMM, Neurocomputing.
  • Conference Reviewer of NeurIPS 2020, ICLR 2021, CVPR 2021, ICML 2021, ICCV 2021.

Invited Talks

  • [2020-12-07] "Un­/Semi­/Weakly-­supervised Learning for Image and Object Retrieval" at Megvii (旷视).
  • [2020-12-04] "Analysis and Development of OpenUnReID Codebase" at ZhiDX (智东西), see here for records.
  • [2020-11-26] "Un­/Semi­/Weakly­-supervised Learning for Image and Object Retrieval" at Huawei (华为).
  • [2020-11-05] "Unsupervised and Domain Adaptive Object Re-identification" at TechBeat (将门), see here for records.
  • [2020-08-24] Spotlight presentation in ECCV 2020, see here for records.
  • [2020-08-23] Presentation in VisDA Challenge 2020 (ECCVW) as one of the winners, see here for records.

Teaching Experience

I have been a teaching assistant for the following courses at CUHK:
  • ENGG 2740A, Differential Equations for Engineers, Spring 2021.
  • ENGG 2720, Complex Analysis, Fall 2020.
  • ENGG 2420B, Complex Analysis and Differential Equations for Engineers, Fall 2019.
  • ELEG 5491, Introduction to Deep Learning, Spring 2019.
  • ENGG 2420A, Complex Analysis and Differential Equations for Engineers, Fall 2018.