Jindong Gu

Postdoctoral Researcher, University of Oxford

I am a Postdoc at University of Oxford, working with Prof. Philip H. S. Torr. Prior to that, I received my Ph.D. Degree from University of Munich in 2022, advised by Prof. Volker Tresp.
My research goal is to build Reliable AI by making AI models explainable, robust, and efficient. Especially, I am interested in robust vision models, vision-language models, and generative vision models.


[Hiring!] I am looking for visiting students/interns for our group in the area of robustness.
Please drop me an email (jindong DOT gu AT outlook DOT com) if interested.

News

  • 02 / 2023:   One paper has been accepted to CVPR 2023.
  • 11 / 2022:   I join Torr Vision Group as Postdoctoral Researcher at University of Oxford.
  • 08 / 2022:   I join Google Responsible AI Team as a Research Intern.
  • 07 / 2022:   Four papers on Robustness of Vision Systems have been accepted to ECCV 2022.
  • 04 / 2021:   I join Microsoft Research Asia as a Research Intern.
  • 03 / 2021:   One paper has been accepted as oral to CVPR 2021.
  • 01 / 2021:   One paper has been accepted to ICLR 2021.
  • 10 / 2020:   I join Tencent AI Lab as a Research Intern.

Education

  • 09 / 2017 - 10 / 2022:   Ph.D. Degree, Computer Science in University of Munich
  • 03 / 2022 - 08 / 2022:   Visiting Ph.D. Student, Engineering Science in University of Oxford
  • 04 / 2016 - 07 / 2017:   Master Degree, Computer Science in University of Munich
  • 09 / 2011 - 03 / 2016:   Double Bachelor Degrees, University of Wuppertal and Wuhan University

Experience

  • 11 / 2022 - present:   Postdoctoral Researcher at University of Oxford, Oxford, UK
  • 08 / 2022 - 11 / 2022:   Research Intern at Google Brain, New York, USA
  • 04 / 2021 - 02 / 2022:   Research Intern at Microsoft Research Asia, Beijing, China
  • 08 / 2020 - 03 / 2021:   Research Intern at Tencent AI Lab, Shenzhen, China
  • 09 / 2017 - 08 / 2020:   Doctoral Researcher at Siemens Technology, Munich, Germany

Selected Publications

    • Do DALL-E and Flamingo Understand Each Other? [PDF][cn Blog]
      Hang Li, Jindong Gu, Rajat Koner, Sahand Sharifzadeh, Volker Tresp
      Preprint, 2022
    • Are Vision Transformers robust to Patch-wise Perturbation? [PDF][CODE]
      Jindong Gu, Volker Tresp, Yao Qin
      European Conference on Computer Vision (ECCV) , 2022
    • SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness [PDF]
      Jindong Gu, Hengshuang Zhao, Volker Tresp, Phillip Torr
      European Conference on Computer Vision (ECCV) , 2022
    • Towards Efficient Adversarial Training on Vision Transformers [PDF]
      Boxi Wu*, Jindong Gu*, Zhifeng Li, Deng Cai, Xiaofei He, Wei Liu
      European Conference on Computer Vision (ECCV) , 2022
    • Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal [PDF][CODE]
      Liu Xinwei, Jian Liu, Yang Bai, Jindong Gu, Tao Chen, Xiaojun Jia, Xiaochun Cao
      European Conference on Computer Vision (ECCV) , 2022
    • Simple Distillation Baselines for Improving Small Self-supervised Models [PDF] [CODE]
      Jindong Gu, Wei Liu, Yonglong Tian
      Workshop in ICCV , 2021
    • Capsule Network is Not More Robust than Convolutional Network [PDF][cn Blog]
      Jindong Gu, Volker Tresp, Han Hu
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2021
    • Effective and Efficient Vote Attack on Capsule Networks [PDF][CODE]
      Jindong Gu, Baoyuan Wu, Volker Tresp
      International Conference on Learning Representations (ICLR) , 2021
    • Interpretable Graph Capsule Networks for Object Recognition [PDF] [CODE]
      Jindong Gu
      AAAI Conference on Artificial Intelligence (AAAI) , 2021
    • Improving the Robustness of Capsule Networks to Image Affine Transformations [PDF]
      Jindong Gu, Volker Tresp
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2020
    • Search for Better Students to Learn Distilled Knowledge [PDF][Blog]
      Jindong Gu, Volker Tresp
      European Conference on Artificial Intelligence (ECAI) , 2020
    • Saliency Methods for Explaining Adversarial Attacks [PDF]
      Jindong Gu, Volker Tresp
      Human-Centric Machine Learning Workshop in NeurIPS , 2019
    • Understanding Individual Decisions of CNNs via Contrastive Backpropagation [PDF] [CODE]
      Jindong Gu, Volker Tresp
      Asian Conference on Computer Vision (ACCV), 2018

Professional Activities

  • Conference Reviewer:
    - International Conference on Machine Learning (ICML) 2022-2023
    - International Conference on Learning Representations (ICLR) 2022-2023
    - Advances in Neural Information Processing Systems (NeurIPS) 2021-2022
    - European Conference on Computer Vision (ECCV) 2022-
    - IEEE International Conference on Computer Vision (ICCV) 2021-2023
    - IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021-2023
  • Journal Reviewer:
    - Elsevier - Neurocomputing
    - Elsevier - Pattern Recognition
    - Transactions of Machine Learning Research (TMLR)
    - IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
    - IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
    - IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Invited Talks

  • 02 / 2023: Robustness of vision system, Sheffield Lab, Noah's Ark Lab
  • 12 / 2022: Robustness of sparse predictions and dense predictions of deep neural networks, University of Surrey
  • 06 / 2022: Explainability of Visual Recognition Models, DataFun
  • 02 / 2022: Explainability and Robustness of Deep Visual Classification Models, University of Tübingen
  • 11 / 2021: On the Robustness of Vision Transformer to Patch Perturbation, Google Brain
  • 09 / 2021: Adversarial Training on Semantic Segmentation, University of Oxford
  • 01 / 2021: Knowledge Distillation meets Neural Architecture Search and Self-supervised Learning, SmartThing
  • 08 / 2020: Explaining Individual Convolution Neural Network-based Image Classifications, Chinese University of Hong Kong

Patents and Inventions

  • Verification of classification decisions in Convolutional Neural Networks [PDF]
    Jindong Gu
    US Patent: US 2022/0019870 A1
  • Method and processing unit for computer-implemented analysis of a classification model [PDF]
    Jindong Gu
    US Patent: US 2020/0334489 A1
  • Siemens Inventions: 8 AI Inventions in Siemens Technology, Germany [Link]

Honours and Awards

  • Google Stipend
  • Chinese Government Award for Outstanding Self-financed Students Abroad
  • CVPR22 Doctoral Consortium Travel Award
  • University of Oxford Visiting Grant
Great Honor to be in this Academic Family Tree [PDF] and [Link], which includes three Nobel prize winners!