Hongguang Zhang

I am a PhD candidate in the College of Engineering and Computer Science (CECS) at the Australian National University.

I obtained the M.Eng from National University of Defense Technology (NUDT). Before that, I graduated from Shanghai Jiao Tong University (SJTU) for B.Eng in Electrical Engineering and Automation.

My main research topics are computer vision and machine learning. I am currently doing research works on zero-shot learning, few-shot learning, domain adaptation with deep learning approaches. I am also interested in some low-level vision tasks, e. g. single image deblurring.

Computer Vision, Machine Learning

Publications [Google Scholar]

(*: equal contribution)
  • Multi-stage Second-order Few-shot Similarity Learning in Image Classification and Action Recognition
    Hongguang Zhang, Hongdong Li, Piotr Koniusz.
    arxiv preprint, 2019

  • A Deeper Look at Power Normalizations in Classical and Few-shot Fine-grained Setting
    Piotr Koniusz*, Hongguang Zhang*.
    arxiv preprint, 2019

  • Deep Stacked Hierarchical Multi-patch Network for Image Deblurring
    Hongguang Zhang, Yuchao Dai, Hongdong Li, Piotr Koniusz.
    IEEE Conference on Computer Vision and Pattern Recognition, 2019
  • [bib][paper]

  • Few-shot Learning via Saliency-guided Hallucination of Samples
    Hongguang Zhang, Jing Zhang, Piotr Koniusz.
    IEEE Conference on Computer Vision and Pattern Recognition, 2019
  • [bib][paper]

  • Power Normalizing Second-order Similarity Network for Few-shot Learning
    Hongguang Zhang, Piotr Koniusz.
    IEEE Winter Conference on Applications of Computer Vision, 2019
  • [bib][paper] [code]

  • Model Selection for Generalized Zero-shot Learning
    Hongguang Zhang, Piotr Koniusz.
    European Conference on Computer Vision Workshops, 2018
  • [bib] [paper]

  • Museum exhibit identification challenge for the supervised domain adaptation and beyond
    Piotr Koniusz*, Yusuf Tas*, Hongguang Zhang, et al.
    European Conference on Computer Vision, 2018 (Oral)
  • [bib] [paper][download]

  • Zero-shot Kernel Learning
    Hongguang Zhang*, Piotr Koniusz*.
    IEEE Conference on Computer Vision and Pattern Recognition, 2018
  • [bib] [paper] [code]

  • A Deeper Look at Power Normalizations
    Piotr Koniusz*, Hongguang Zhang*.
    IEEE Conference on Computer Vision and Pattern Recognition, 2018
  • [bib] [paper]

Honors and awards

  • Data61/CSIRO PhD Top-up Scholarship, 2018
  • ICML Travel Grant, 2017
  • China Scholarship Council PhD Scholarship, 2016
  • Merit Postgraduate Student Innovation Fellowship, NUDT, 2016
  • Kuang-hua Fellowship, NUDT, 2015
  • Outstanding Graduate Award, SJTU, 2014
  • Shanghai Government Scholarship, SJTU, 2013
  • Shanghai Second-class Award of National Undergraduate Electronic Design Contest, SJTU, 2013
  • Academic Excellence Fellowship, SJTU, 2013
  • National Endeavor Fellowship, SJTU, 2013
  • Merit Student, SJTU, 2012-2013

Professional Activities

  • IEEE Student Member, CVF Student Member
  • Co-organized ACCV 2018 Workshop: Museum Exhibit Identification Challenge (Open MIC) for Domain Adaptation and Few-Shot Learning.
  • Reviewer: ICCV, BMVC, WACV
  • Tutor for ENG4528 Computer Vision Semester 1 2019.

Updated:  1 June 2019/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing