About Me

Jian Liang

梁坚 (Jian Liang, Tim)
Associate Professor
Center for Research on Intelligent Perception and Computing
Institute of Automation, Chinese Academy of Sciences

Room 1505, Intelligent Building, 95 Zhongguancun East Road
100190, Haidian District, Beijing, China

🎖Google Scholar
  liangjian92🌀gmail.com or jian.liang🌀nlpr.ia.ac.cn

Before joining CASIA in June 2021, I was a research fellow at the Vision and Learning Group, National University of Singapore, working with Dr. Jiashi Feng from June 2019 to April 2021. I obtained Ph.D. in Pattern Recognition and Intelligent Systems from CASIA in Jan 2019, under the supervision of Prof. Tieniu Tan and co-supervision of Prof. Ran He and Prof. Zhenan Sun, and received my bachelor degree in Automation from Xi'an Jiaotong University in June 2013.

My current research interests mainly focus on representation learning, knowledge transfer, trustworthy AI (including security, privacy, or robustness in AI), and their applications in various computer vision problems.

I am open to discussion or collaboration. Feel free to drop me an email if you're interested.

News (the past year)

  • 2024/07/12 Our paper on source-free semantic segmentation has finally been accepted to TPAMI.

  • 2024/07/04 Our survey on test-time adaptation has been accepted to IJCV.

  • 2024/07/02 Our paper on open-set test-time adaptation has been accepted to ECCV 2024.

  • 2024/05/02 Three papers have been accepted to ICML 2024.

  • 2024/03/13 Our paper on deepfake detection has been accepted to IJCV.

  • 2024/02/27 Our paper on test-time backdoor defense has been accepted to CVPR 2024.

  • 2024/02/17 Our blogpost on gradient inversion has been accepted to ICLR BlogPosts 2024.

  • 2024/01/16 Two papers have been accepted to ICLR 2024.

  • 2023/11/16 Our paper on heterogeneous federated learning has been accepted to TPAMI.

  • 2023/10/28 Two papers on model selection and uncertainty estimation in domain adaptation have been accepted to NeurIPS DistShift Workshop 2023.

  • 2023/09/22 Our paper on validation of unsupervised domain adaptation methods has been accepted to NeurIPS 2023.

  • 2023/08/04 Our paper on source-free domain adaptation has been accepted to Neural Networks.

  • 2023/07/14 Four papers have been accepted to ICCV 2023.

Recent Work

A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts.
Jian Liang, Ran He, Tieniu Tan.
IJCV, 2024.
[Paper] [Code]

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization.
Jian Liang, Lijun Sheng, Zhengbo Wang, Ran He, Tieniu Tan.
ICML, 2024.
[Paper] [Code]

Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification.
Yongcan Yu, Lijun Sheng, Ran He, Jian Liang.
Arxiv technical report, 2023.
[Paper] [Code]

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation.
Dapeng Hu, Jian Liang, Jun Hao Liew, Chuhui Xue, Song Bai, Xinchao Wang.
Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.
[Paper] [Code]

AdaptGuard: Defending Against Universal Attacks for Model Adaptation.
Lijun Sheng, Jian Liang, Ran He, Zilei Wang, Tieniu Tan.
International Conference on Computer Vision (ICCV), 2023.
[Paper] [Code]

Improving Zero-Shot Generalization for CLIP with Synthesized Prompts.
Zhengbo Wang, Jian Liang, Ran He, Nan Xu, Zilei Wang, Tieniu Tan.
International Conference on Computer Vision (ICCV), 2023.
[Paper] [Code]

TALL: Thumbnail Layout for Deepfake Video Detection.
Yuting Xu, Jian Liang, Ziming Yang, Gengyun Jia, Yanhao Zhang, Ran He.
International Conference on Computer Vision (ICCV), 2023.
[Paper] [Code]

Informative Data Mining for One-shot Cross-Domain Semantic Segmentation.
Yuxi Wang, Jian Liang, Yuran Yang, Zhaoxiang Zhang.
International Conference on Computer Vision (ICCV), 2023.
[Paper] [Code]


Current Students

  • Lijun Sheng (with Prof. Tan), Jiyang Guan (with Prof. He)

  • Yuhe Ding (with Prof. Jiang), Aijing Yu (with Prof. Zhang)

  • Zhengbo Wang (with Prof. Tan), Yuting Xu (with Prof. Zhang)

  • Yanbo Wang (with Prof. He)

  • Yongcan Yu, Kuangpo Guo (with Prof. Tan), Yingsheng Wang (with Prof. He)

  • Shuo Lu, Xiaokun Yang (with Prof. Tan)

Alumni (Since 2019)