Hongjun Wang (王弘焌)

Profile Photo

The University of Hong Kong

hjwang@connect.hku.hk

Google Scholar

Github

  Biography

He is currently a Ph.D. student in Department of Statistics and Actuarial Science, The University of Hong Kong, co-supervised by Prof. Kai Han and Prof. Guosheng Yin. Before that, he received his M.E. degree supervised by Prof. Liang Lin and B.E. degree in School of Computer in Sun Yat-sen University (SYSU).

  Research Interests

  • Open Set Recognition
  • Domain Shift
  • Trustworthy ML model

  Educations & Experience


  Selected Publications

    Self-Ensemble Adversarial Training for Improved Robustness
    Hongjun Wang, Yisen Wang
    International Conference on Learning Representations (ICLR), 2022. 
    @inproceedings{wang2022selfensemble,
  title={Self-ensemble Adversarial Training for Improved Robustness},
  author={Hongjun Wang and Yisen Wang},
  booktitle={ICLR},
  year={2022}
}
    A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning
    Hongjun Wang, Guanbin Li, Xiaobai Liu, Liang Lin
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020. 
    @article{wang2020hamiltonian,
  title={A Hamiltonian Monte Carlo method for probabilistic adversarial attack and learning},
  author={Wang, Hongjun and Li, Guanbin and Liu, Xiaobai and Lin, Liang},
  journal={T-PAMI},
  year={2020}
}
    Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
    Hongjun Wang*, Guangrun Wang*, Ya Li, Dongyu Zhang, Liang Lin
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. (Oral) 
    @inproceedings{wang2020transferable,
  title={Transferable, controllable, and inconspicuous adversarial attacks on person re-identification with deep mis-ranking},
  author={Wang, Hongjun and Wang, Guangrun and Li, Ya and Zhang, Dongyu and Lin, Liang},
  booktitle={CVPR},
  year={2020}
}
    CamDrop: A New Explanation of Dropout and A Guided Regularization Method for Deep Neural Networks
    Hongjun Wang, Guangrun Wang, Guanbin Li, Liang Lin
    ACM International Conference on Information and Knowledge Management (CIKM), 2019. (Oral) 
    @inproceedings{wang2019camdrop,
  title={Camdrop: A new explanation of dropout and a guided regularization method for deep neural networks},
  author={Wang, Hongjun and Wang, Guangrun and Li, Guanbin and Lin, Liang},
  booktitle={CIKM},
  year={2019}
}

  Honors & Awards

  • Outstanding Graduate,
    2021
  • Outstanding Thesis Award,
    2021 and 2018
  • National Scholarship ( 1st⁄442 and 1st⁄72),
    2020 and 2017
  • SIGIR Travel Award,
    2019
  • Outstanding Student Scholarship,
    2016 - 2020
  • National First-level Athelete of Swimming,
    2013

  Services & Talks