Biography

I am now a Research Scientist at Ant Research. From Jul. 2018 to Oct. 2023, I worked as a Senior Research Scientist at Tencent AI Lab. In June 2018, I obtained my PhD degree from the National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Bao-Gang Hu and Prof. Ran He. From Oct. 2016 to Oct. 2017, I spent a wonderful year as a visiting student at the Computer Vision and Machine Learning Lab (CVML) at the University at Albany, State University of New York, supervised by Prof. Siwei Lyu. I received my BS degree from Hunan University in June 2013, major in Computer Science and Technology.

My research focuses on Trustworthy and Generative AI, in particular, adversarial machine learning and digital avatar reconstruction and animation. I am interested in theory, algorithms, and applications of these topics, especially for real-world scenarios where both performance and operational efficiency matter. 

👏👏We have opening positions for research interns at Ant Research, focusing on cutting-edge research in digital avatar, e.g., gaussian avatars, high-fidelity 2D/3D audio/video animation, etc. If you are interested, please feel free to contact me.

News

• 2024/04/25 -- One paper about adversarial training is accepted to IJCV.

• 2023/09/22 -- One paper about motion generation is accepted to NeurIPS 2023.

• 2023/08/15 -- One paper about Fast Adversarial Training is accepted to TIP.

• 2023/07/14 -- Three papers about Talking head synthesis/Deepfake detection/Backdoor learning are accepted to ICCV 2023.

• 2023/05/02 -- One paper about one-shot 3D facial reconstruction and animation is accepted to Siggraph 2023 as a conference paper.

• 2023/02/28 -- Three papers about 2D/3D (NeRF)-based facial reconstruction and animation are accepted to CVPR 2023.

• 2022/09/15 -- Two papers about Adversarial Machine Learning are accepted to NeurIPS 2022.

• 2022/08/27 -- One paper is accepted to Pattern Recognition.

• 2022/08/11 -- One paper is accepted to TCSVT.

• 2022/07/21 -- One paper is accepted to T-PAMI.

• 2022/07/09 -- Two papers are accepted to ECCV 2022.

• 2022/06/30 -- One paper is accepted to ACM MM 2022.

• 2022/03/03 -- Two papers are accepted to CVPR 2022.

Publications 

1. Regional Adversarial Training for Better Robust Generalization
   Chuanbiao Song1(co-first author), Yanbo Fan1(co-first author), Aoyang Zhou1(co-first author), Baoyuan Wu, Yiming Li, Zhifeng Li, Kun He
   [International Journal of Computer Vision, IJCV 2024]

2. UCF: Uncovering Common Features for Generalizable Deepfake Detection
   Zhiyuan Yan, Yong Zhang, Yanbo Fan, Baoyuan Wu
   [ICCV 2023]

3. Toontalker: Cross-domain face reenactment
   Yuan Gong, Yong Zhang, Xiaodong Cun, Fei Yin, Yanbo Fan, Xuan Wang, Baoyuan Wu, Yujiu Yang
   [ICCV 2023]

4. Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs
   Peng Jin, Yang Wu, Yanbo Fan, Zhongqian Sun, Yang Wei, Li Yuan
   [NeurIPS 2023]

5. Fast adversarial training with adaptive step size
   Zhichao Huang, Yanbo Fan*(corresponding author), Chen Liu, Weizhong Zhang, Yong Zhang, Mathieu Salzmann, Sabine Süsstrunk, Jue Wang
   [Transactions on Image Processing (TIP 2023)]

6. NOFA: NeRF-based One-shot Facial Avatar Reconstruction.
   Wangbo Yu, Yanbo Fan*(corresponding author), Yong Zhang, Xuan Wang, Fei Yin, Yunpeng Bai, Yan-Pei Cao, Ying Shan, Yang Wu, Zhongqian Sun, Baoyuan Wu.
   [Siggraph 2023, conference paper]

7. High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors.
   Yunpeng Bai, Yanbo Fan*(corresponding author), Xuan Wang, Yong Zhang, Jingxiang Sun, Chun Yuan, Ying Shan
   [CVPR 2023]

8. 3D GAN Inversion with Facial Symmetry Prior.
   Fei Yin, Yong Zhang, Xuan Wang, Tengfei Wang, Xiaoyu Li, Yuan Gong, Yanbo Fan, Xiaodong Cun, Ying Shan, Cengiz Oztireli, Yujiu Yang
   [CVPR 2023] 

9. DPE: Disentanglement of Pose and Expression for General Video Portrait Editing.
   Youxin Pang, Yong Zhang, Weize Quan, Yanbo Fan, Xiaodong Cun, Ying Shan, Dong-ming Yan
   [CVPR 2023] 

10. Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation.
    Zeyu Qin1, Yanbo Fan1(co-first author), Yi Liu, Li Shen, Yong Zhang, Jue Wang, Baoyuan Wu.
    [NeurIPS 2022]

11. Stability Analysis and Generalization Bounds of Adversarial Training.
    Jiancong Xiao, Yanbo Fan*(corresponding author), Ruoyu Sun, Jue Wang, Zhi-Quan Luo.
    [NeurIPS 2022, spotlight] 

12. Robust Physical-World Attacks on Face Recognition.
    Xin Zheng1, Yanbo Fan1 (co-first author), Baoyuan Wu, Yong Zhang, Jue Wang, Shirui Pan.
    [Pattern Recognition 2022] 

13. Towards Real-World Video Deblurring by Exploring Blur Formation Process.
    Mingdeng Cao, Zhihang Zhong, Yanbo Fan, Jiahao Wang, Yong Zhang, Jue Wang, Yujiu Yang, Yinqiang Zheng.
    [ECCV workshop, 2022] 

14. VDTR: Video Deblurring with Transformer.
    Mingdeng Cao, Yanbo Fan*(corresponding author), Yong Zhang, Jue Wang, Yujiu Yang.
    [TCSVT 2022]

15. Generalizable Black-Box Adversarial Attack with Meta Learning.
    Fei Yin, Yong Zhang, Baoyuan Wu, Yan Feng, Jingyi Zhang, Yanbo Fan, Yujiu Yang.
    [T-PAMI 2022]

16. A Large-scale Multiple-objective Method for Black-box Attack against Object Detection.
    Siyuan Liang, Longkang Li, Yanbo Fan, Xiaojun Jia, Jingzhi Li, Baoyuan Wu, Xiaochun Cao.
    [ECCV 2022]

17. StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN.
    Fei Yin, Yong Zhang, Xiaodong Cun, Mingdeng Cao, Yanbo Fan, Xuan Wang, Qingyan Bai, Baoyuan Wu, Jue Wang, Yujiu Yang.
    [ECCV 2022]

18. HyP Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval.
    Chengyin Xu, Zenghao Chai, Zhengzhuo Xu, Chun Yuan, Yanbo Fan*(corresponding author), Jue Wang
    [ACM MM 2022]

19. High-Fidelity GAN Inversion for Image Attribute Editing.
    Tengfei Wang, Yong Zhang, Yanbo Fan, Jue Wang, Qifeng Chen.
    [CVPR 2022]

20. Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution.
    Yan Feng, Baoyuan Wu, Yanbo Fan, Li Liu, Zhifeng Li, Shu-Tao Xia.
    [CVPR 2022] 

21. Semi-supervised Robust Training with Generalized Perturbed Neighborhood.
    Yiming Li, Baoyuan Wu, Yan Feng, Yanbo Fan, Yong Jiang, Zhifeng Li, Shutao Xia.
    [Pattern Recognition 2022] 

22. Random Noise Defense Against Query-Based Black-Box Attacks.
    Zeyu Qin, Yanbo Fan, Hongyuan Zha, Baoyuan Wu.
    [NeurIPS 2021] 

23. Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection.
    Siyuan Liang, Baoyuan Wu, Yanbo Fan, Xingxing Wei, Xiaochun Cao.
    [ICCV 2021] 

24. DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis.
    Shulan Ruan, Yong Zhang, Kun Zhang, Yanbo Fan, Fan Tang, Qi Liu, Enhong Chen.
    [ICCV 2021] 

25. Sparse Adversarial Attack via Perturbation Factorization.
    Yanbo Fan, Baoyuan Wu, Tuanhui Li, Yong Zhang, Mingyang Li, Zhifeng Li, Yujiu Yang.
    [ECCV 2020]

26. Average Top-k Loss for supervised learning
    Siwei Lyu, Yanbo Fan* (corresponding author), Yiming Ying, Bao-Gang Hu.
    [T-PAMI 2020]

27. 3D Single-Person Concurrent Activity Detection Using Stacked Relation Network.
    Yi Wei, Wenbo Li, Yanbo Fan, Linghan Xu, Ming-Ching Chang, Siwei Lyu.
    [AAAI 2020] 

28. Context-aware Feature and Label Fusion for Facial Action Unit Intensity Estimation with Partially Labeled Data.
    Yong Zhang, Haiyong Jiang, Baoyuan Wu, Yanbo Fan, Qiang Ji.
    [ICCV 2019] 

29. Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables.
    Yan Xu, Baoyuan Wu, Fumin Shen, Yanbo Fan, Yong Zhang, Heng Tao Shen and Wei Liu.
    [CVPR 2019] 

30. Compressing Convolutional Neural Networks via Factorized Convolutional Filters.
    Tuanhui Li, Baoyuan Wu, Yujiu Yang, Yanbo Fan, Yong Zhang, and Wei Liu.
    [CVPR 2019] 

31. Learning with Average Top-k Loss.
    Yanbo, Fan, Siwei Lyu, Yiming Ying and Bao-Gang Hu.
    [NeurIPS 2017] 

32. Self-Paced Learning: An Implicit Regularization Perspective.
    Yanbo, Fan, Ran He, Jian Liang and Bao-Gang Hu.
    [AAAI 2017] 

33. Global and Local Consistent Multi-view Subspace Clustering.
    Yanbo, Fan, Ran He and Bao-Gang Hu.
    [ACPR 2015, oral] 

Preprints 

34. Adversarial rademacher complexity of deep neural networks.
    Jiancong Xiao, Yanbo Fan, Ruoyu Sun, Zhi-Quan Luo
    [arXiv:2211.14966]

35. Understanding Adversarial Robustness Against On-manifold Adversarial Examples.
    Jiancong Xiao, Liusha Yang, Yanbo Fan, Jue Wang, Zhi-Quan Luo
    [arXiv:2210.00430]

36. Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis.
    Jiancong Xiao, Zeyu Qin, Yanbo Fan, Baoyuan Wu, Jue Wang, Zhi-Quan Luo
    [arXiv:2210.00557]

37. Robust Localized Multi-view Subspace Clustering.
    Yanbo Fan, Jian Liang, Ran He, Bao-Gang Hu and Siwei Lyu.
    [arXiv:1705.07777] 

Patents

1. Methods and devices for adversarial attack on image caption, 2022.

2. A facial expression recognition method and device, 2021.

3. A head decoration processing method and device, 2020.

4. Rejection subspace learning with adaptive threshold for face detection, 2019.