Shuhan Tan

I am currently a PhD student at The University of Texas at Austin, advised by Professor Kristen Grauman. I obtained my bachelor's degree from Sun Yat-Sen University in 2021.

Before my PhD, I worked happily with Prof. Bolei Zhou at CUHK as a research assistant, and was fortunate to work as a research intern at Uber ATG, advised by Prof. Raquel Urtasun and Prof. Shenlong Wang. Previously, I had the luck worked with Prof. Kate Saenko and Dr. Xingchao Peng at Boston University and Prof. Wei-Shi Zheng at iSEE, Sun Yat-sen University.

My research interests lie on Machine Learning, Computer Vision and Robot Learning. I am currently interested in tackling problems with real-world variance with adaptive vision learning.

Email  /  CV  /  Scholar  /  LinkedIn


The University of Texas at Austin
PhD in Computer Science • Aug. 2021 -

Sun Yat-Sen University
B.E. in Computer Science • Sep. 2016 - Jun. 2021
Ranking: 2/189

Research Experience

The University of Texas at Austin
Research Assistant • Aug. 2021 -
Adviser: Professor Kristen Grauman

The Chinese University of Hong Kong
Research Assistant • Sep. 2020 - Mar. 2021
Adviser: Professor Bolei Zhou

Uber ATG Toronto
Research Intern • Sep. 2019 - Aug. 2020
Adviser: Professor Raquel Urtasun, Professor Shenlong Wang

Boston University
Research Assistant • July 2019 - Sep. 2019
Adviser: Professor Kate Saenko, Dr. Xingchao Peng

Sun Yat-Sen University
Undergraduate Researcher • Sep. 2017 - June 2019
Adviser: Professor Wei-Shi Zheng


[08/2021] I started my PhD study at UT Austin.

[03/2021] Our paper is accepted to CVPR 2021.

[12/2020] I received the SenseTime Scholarship (21 out of all AI-focus undergraduate students in China).

[08/2020] Our paper is accepted to TASK-CV workshop at ECCV 2020.

[02/2020] Our paper is accepted to CVPR 2020 (oral).

PontTuset SceneGen: Learning to Generate Realistic Traffic Scenes.
Shuhan Tan*, Kelvin Wong*, Shenlong Wang, Sivabalan Manivasagam, Mengye Ren, Raquel Urtasun.

CVPR 2021.

Paper / Video / Bibtex

Generate realistic traffic scences automatically.

PontTuset Class-imbalanced Domain Adaptation: An Empirical Odyssey.
Shuhan Tan, Xingchao Peng, Kate Saenko.

TASK-CV Workshop, ECCV 2020.

Paper / Bibtex

Align feature distributions across domains while the label distributions of the two domains are also different.

PontTuset LidarSIM: Realistic LiDAR Simulation by Leveraging the Real World
Sivabalan Manivasagam, Shenlong Wang, Kelvin Wong, Wenyuan Zeng, Mikita Sazanovich, Shuhan Tan, Bin Yang, Wei-Chiu Ma and Raquel Urtasun.

CVPR 2020 (Oral).

Paper / Supplement / Bibtex

Realistic sensor simulation for LiDAR.


Biomarker Localization by Combining CNN Classifier and Generative Adversarial Network
Rong Zhang, Shuhan Tan, Ruixuan Wang, Siyamalan Manivannan, Jingjing Chen, Haotian Lin, Wei-Shi Zheng.

MICCAI 2019.

Paper / Bibtex

We proposed a novel deep neural network architecture to effectively localize potential biomarkers in medical images, when only the image-level labels are available during model training.


Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration
Shuhan Tan, Jiening Jiao, Wei-Shi Zheng

CVPR 2019.

Paper / Supplement / Bibtex

We proposed a practical weakly supervised setting for open-set domain adaptation, where two scarcely-labeled domains collaboratively learn from each other.

Invited for presentation at WebVision 2019.

PontTuset Improving the Fairness of Deep Generative Models without Retraining.
Shuhan Tan, Yujun Shen, Bolei Zhou.
arXiv.2012.04842 preprint

Paper / Project page / Code / Colab

Mitigate biases of GAN models without retraining.

Selected Honors

Distinguished Graduate Thesis, Sun Yat-sen University

SenseTime Scholarship (21 out of all AI-focus undergraduate students in China)


Reviewer: CVPR2022, ECCV 2022

Updated March 2022.

Special thanks to Jon Barron for website template.