profile image

Weijian Deng

Final Year PhD Student

About Me

I am a Computer Science PhD student at Australian National University, working with Dr Liang Zheng, Prof Stephen Gould and Dr Yumin Suh. Before that, I received the M.Phil in Computer Science from the University of the Chinese Academy of Sciences in 2019, advised by Prof Jianbin Jiao. I obtained the B.Eng. from Beijing Jiaotong University in 2016, advised by Dr Jupeng Li.

Research Topic: Model (Out-of-Distribution) Generalization.

My PhD research is Unsupervised Model Evaluation. Over the past three years, I have been exploring an answer to one question: Are Labels Always Necessary for Model Evaluation? Specifically, the goal is to estimate the model generalization on various unlabeled test datasets. Please check our [ TPAMI 2022/CVPR 2021 work] and [ ICML 2021 work]. Here are [some slides] to introduce my research.

[Curriculum Vitae; Google Scholar]

News

  • [Jan 2023] Submitted PhD thesis
  • [Dec 2022] Completed PhD oral presentation
  • [Oct 2022] One paper on multi-task learning is accepted to WACV 2023
  • [Oct 2022] Honoured to receive NeurIPS 2022 Scholar Award (Travel Award)
  • [Sep 2022] One paper on model invariance and generalization is accepted to NeurIPS 2022 [Paper]
  • [Jul 2022] Honoured to be recognized by ICML 2022 as a top 10% reviewer
  • [Jun 2022] We will organize the CVPR 2022 Tutorial on ["Evaluating Models Beyond the Textbook: Out-of-distribution and Without Labels"]
  • [May 2022] One paper on fine-grained clasification is accepted to IEEE TIP [Paper]
  • [Dec 2021] One paper on model decision understanding is accepted to IEEE TPAMI [Project]
  • [May 2021] One paper is accepted to ICML 2021 [Paper, Project]
  • [Mar 2021] One paper is accepted to CVPR 2021 [Paper, Project]
  • [Jul 2020 - Sep 2020] Summer intern in NEC Labs America. Wonderful experience with my talented mentors Yumin Suh, Xiang Yu, Masoud Faraki, and Manmohan Chandraker.
  • [Aug 2020] VisDA-2020 challenge successfully ends. Congratulations to the [final teams]!
    • Big thanks to all committee members Kate Saenko, Liang Zheng, and Xingchao Peng!
  • [Jun 2020] Honoured to be recognized by ECCV2020 as a top reviewer
  • [Jan 2020] One paper is accepted to IEEE TCSVT [Paper]
  • [Jul 2020] Honoured to be recognized by ECCV2020 as a top reviewer [Link]
  • [Jul 2019] Study PhD program at The Australian National University. My reseach is supported by Australian Governmen Scholarship [AGRTP].
  • [Jun 2019] Receive M.Eng. from the University of the Chinese Academy of Sciences
  • [Jun 2019] Win 3rd place out of 84 participants in vehicle re-identification in CVPR 2019 AI-City Challenge
    • [Paper, Code]
  • [Jul 2018 - Nov 2018] Reserch assistant in Singapore University of Technology and Design (SUTD)
  • [Mar 2018] One paper is accepted to CVPR 2018 [Paper, Code]
  • [Jul 2017] One paper is accepted to ICCV 2017 [Paper, Code]

Publications

project name

On the Strong Correlation Between Model Invariance and Generalization

Weijian Deng, Stephen Gould, and Liang Zheng

NeurIPS 2022 (Spotlight) [Paper, OpenReview, Slides, Poster, BibTex]

project name

Fine-grained Classification via Categorical Memory Networks

Weijian Deng, Joshua Marsh, Stephen Gould, Liang Zheng

IEEE TIP 2022 [ BibTex, Paper]

project name

AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?

Weijian Deng and Liang Zheng

IEEE TPAMI 2022 [Project, BibTex, Paper]

project name

What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?

Weijian Deng, Stephen Gould, and Liang Zheng

ICML 2021 [Paper, BibTex, Project, Slides, Poster]

project name

Are Labels Always Necessary for Classifier Accuracy Evaluation?

Weijian Deng and Liang Zheng

CVPR 2021 [Paper, Project, BibTex, Poster, Slides]

project name

Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification

Weijian Deng, Liang Zheng, Qixiang Ye, Guoliang Kang, Yi Yang, Jianbin Jiao

CVPR 2018 [Paper, Code, BibTex, Poster]

project name

Rethinking Triplet Loss for Domain Adaptation

Weijian Deng, Liang Zheng, Yifan Sun, Jianbin Jiao

IEEE TCSVT 2020 [Paper, BibTex]

(Journal version of "Domain alignment with triplets")

project name

Split to Learn: Gradient Split for Multi-Task Human Image Analysis

Weijian Deng, Yumin Suh, Xiang Yu, Masoud Faraki, Liang Zheng, Manmohan Chandraker

WACV, 2023 [ Paper, US Patent, Poster, Slides, BibTex ]

project name

SVDNet for Pedestrian Retrieval

Yifan Sun, Liang Zheng, Weijian Deng, Shengjin Wang

ICCV 2017 (Spotlight) [Paper, Code, BibTex, Poster]

More on Google Scholar

Selected Projects

CVPR 2022 Tutorial on "Evaluating Models Beyond the Textbook: Out-of-distribution and Without Labels "

Organizers: Liang Zheng (Australian National University), Ludwig Schmidt (University of Washington), Aditi Raghunathan (Carnegie Mellon University), Weijian Deng (Australian National University)

Our proposed tutorial will give a broad overview of machine learning evaluation with a focus on the two aforementioned issues: evaluation without labels and out-of-distribution. [Tutorial Page]

Visual Domain Adaptation Challenge (VisDA 2020 in conjunction with ECCV 2020)

Organizers: Kate Saenko (Boston University), Liang Zheng (Australian National University), Xingchao Peng (Boston University), Weijian Deng (Australian National University)

This year we focus on domain adaptive instance retrieval, where the source and target domains have completely different classes (instance IDs). The particular task is to retrieve the pedestrian instances of the same ID as the query image. [Chanllenge Page]

The Third Place in Vehicle Re-identification in CVPR 2019 AI-City Challenge

Win 3rd place out of 84 participants [Paper, Code]