My name is Xin Ding. I received my Ph.D. in Statistics (2021) from The University of British Columbia under the supervision of Professor William J. Welch and Z. Jane Wang.

Currently, I am an associate professor in the School of Artificial Intelligence at Nanjing University of Information Science & Technology. 

My main research interests include deep generative models, knowledge distillation, hand pose estimation, and their applications.

Research Interests:

Generative Adversarial Networks (GANs), Diffusion Models (DM), Knowledge Distillation, Hand Pose Estimation, Self-supervised Learning, etc. 

Publications：

* equal contribution; ^ corresponding author

Preprint

[1] Xin Ding, Yongwei Wang^, Kao Zhang, Z. Jane Wang. CCDM: Continuous conditional diffusion models for image generation[J]. arXiv preprint arXiv:2405.03546, 2024. [Under Review] [PDF] [Code]

[2]  Huangsen Cao, Yongwei Wang, Yinfeng Liu, Sixian Zheng, Kangtao Lv, Zhimeng Zhang, Bo Zhang, Xin Ding, Fei Wu. HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs[J]. arXiv preprint arXiv:2410.06044, 2024. [Under Review]

[3] Kangtao Lv, Huangsen Cao, Kainan Tu, Yihuai Xu, Zhimeng Zhang, Xin Ding, Yongwei Wang. Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models[J]. arXiv preprint arXiv:2410.05951, 2024. [Under Review]

[4] Zhan Shi, Xin Ding*^, Peng Ding, et al. Regression-oriented knowledge distillation for lightweight ship orientation angle prediction with optical remote sensing images[J]. arXiv preprint arXiv:2307.06566, 2023. [Under Review] [PDF][Code]

2024

[1] Xin Ding, Yongwei Wang^, Zuheng Xu. Turning waste into wealth: Leveraging low-quality samples for enhancing continuous conditional generative adversarial networks[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(10): 11802-11810. [AAAI'24, CCF A, AR 23.75%] [PDF][Code]

2023

[1] Xin Ding, Yongwei Wang^, Zuheng Xu, William J. Welch, Z. Jane Wang. Continuous conditional generative adversarial networks: Novel empirical losses and label input mechanisms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(7): 8143-8158.  [T-PAMI'23, SCI 1, IF 23.6] [PDF][Code]

[2] Xin Ding, Yongwei Wang^, Zuheng Xu, Z. Jane Wang, William J. Welch. Distilling and transferring knowledge via cGAN-generated samples for image classification and regression[J]. Expert Systems with Applications, 2023, 213: 119060. [ESWA'23, SCI 1, IF 8.5] [PDF][Code]

[3] Xin Ding, Yongwei Wang^, Z. Jane Wang, William J. Welch. Efficient subsampling of realistic images from GANs conditional on a class or a continuous variable[J]. Neurocomputing, 2023, 517: 188-200.  [Neurocomputing'23, SCI 2, IF 6] [PDF][Code]

2022 and before

[1] Xin Ding^, Yongwei Wang, Zuheng Xu, William J. Welch, Z. Jane Wang. Image generation using continuous conditional generative adversarial networks[M]//Generative Adversarial Learning: Architectures and Applications: Vol. 217. 2022: 87-113. [PDF]

[2] Xin Ding*^, Yongwei Wang*, Zuheng Xu, William J. Welch, Z. Jane Wang. CcGAN: Continuous conditional generative adversarial networks for image generation[C]//International Conference on Learning Representations. 2021. [ICLR'21, AR 28.7%] [PDF][Code]

[3] Yongwei Wang, Xin Ding, Yixin Yang, Li Ding, Rabab Ward, Z Jane Wang. Perception matters: Exploring imperceptible and transferable anti-forensics for GAN-generated fake face imagery detection[J]. Pattern Recognition Letters, 2021, 146: 15-22. [PRL'21, SCI 3, IF 5.1] [PDF]

[4] Xin Ding*^, Qiong Zhang*, William J. Welch. Classification beats regression: Counting of cells from greyscale microscopic images based on annotation-free training samples[C]//Artificial Intelligence: First CAAI International Conference, CICAI 2021, Hangzhou, China, June 5–6, 2021, Proceedings, Part I 1. 2021: 662-673. [CICAI'21, EI, AR 34.5%] [PDF][Code]

[5] Li Ding, Yongwei Wang^, Xin Ding, Kaiwen Yuan, Ping Wang, Hua Huang, Z. Jane Wang. Delving into deep image prior for adversarial defense: A novel reconstruction-based defense framework[C]//Proceedings of the 29th ACM International Conference on Multimedia. 2021: 4564-4572.  [ACM MM'21, CCF A, AR 27.9%] [PDF]

[6] Xin Ding^, Z. Jane Wang, William J. Welch. Subsampling generative adversarial networks: Density ratio estimation in feature space with Softplus loss[J]. IEEE Transactions on Signal Processing, 2020, 68: 1910-1922.   [TSP'20, SCI 1, IF 5.4] [PDF][Code]

[7] Xin Ding^, Ziyi Qiu, Xiaohui Chen. Sparse transition matrix estimation for high-dimensional and locally stationary vector autoregressive models[J]. Electronic Journal of Statistics, 2017, 11: 3871-3902.  [EJS'17, SCI 3, IF 1.281] [PDF]