Xiang Gu (古祥) Assistant Professor Department of Information Science, School of Mathematics and Statistics, Xi'an Jiaotong University, P.R.China. Email: xianggu@xjtu.edu.cn, [Google page] [GitHub]

Biography

I'm an assistant professor at the Department of Information Science, School of Mathematics and Statistics, Xi^'an Jiaotong University. I got my PhD degree in Applied Mathematics in March 2024, from the School of Mathematics and Statistics, Xi^'an Jiaotong University, supervised by Prof. Zongben Xu and co-supervised by Prof. Jian Sun. Before that, I got my B.S. in Statistics in June 2017 from the School of Mathematics, Southeast University.

Research Interests

My research interests include optimal transport, transfer learning, and theory and algorithm of foundation models.

Publication

• Xin Wei, Xiang Gu, Jian Sun. Multi-scale Part-based Feature Representation for 3D Domain Generalization and Adaptation. IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2024. (CCF-A)
• Xiang Gu, Xi Yu, Yan Yang, Jian Sun, Zongben Xu. Adversarial Reweighting with $\alpha$-Power Maximization for Domain Adaptation. International Journal of Computer Vision (IJCV), 2024. [code] [Official Version] (CCF-A)
• Xiaole Tang, Xin Hu, Xiang Gu, Jian Sun. Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration. International Conference on Machine Learning (ICML), 2024. (CCF-A)
• Xi Yu, Xiang Gu (Co-First Author), Jian Sun. Contrasting Augmented Features for Domain Adaptation with Limited Target Domain Data. Pattern Recognition, 2023.


• Xiang Gu, Liwei Yang, Jian Sun, Zongben Xu. Optimal Transport-Guided Conditional Score-Based Diffusion Model. Conference on Neural Information Processing Systems (NeurIPS), 2023. [Code] [Poster] [Slides] [OpenReview] [Project Page] (CCF-A)


• Xi Yu, Xiang Gu (Co-First Author), Haozhi Liu, Jian Sun. Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model. Conference on Neural Information Processing Systems (NeurIPS), 2023. (CCF-A)


• Xiang Gu, Jian Sun, and Zongben Xu.   Adversarial Data Splitting for Domain Generalization. Science China Information Sciences (SCIS), 2023. (CCF-A)


• Fan Wang, Xiang Gu, Jian Sun, and Zongben Xu.   Learning-based Local Weighted Least Squares for Algebraic Multigrid Method. Journal of Computational Physics (JCP), 2023.


• Zixiang Zhao, Jiangshe Zhang, Xiang Gu, Chengli Tan, Shuang Xu, Yulun Zhang, Radu Timofte, Luc Van Gool. Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023. (CCF-A)


• Liwei Yang, Xiang Gu (Co-First Author), and Jian Sun. Generalized Semantic Segmentation by Self-supervised Source Domain Projection and Multi-level Contrastive Learning. Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI, Oral), 2023. (CCF-A)


• Yucheng Yang, Xiang Gu (Co-First Author), and Jian Sun. Prototypical Partial Optimal Transport for Universal Domain Adaptation. Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023. (CCF-A)


• Xin Wei, Xiang Gu, and Jian Sun. Learning Generalizable Part-based Feature Representation for 3D Point Clouds. Conference on Neural Information Processing Systems (NeurIPS), 2022. (CCF-A)


• Xiang Gu, Yucheng Yang, Wei Zeng, Jian Sun, and Zongben Xu. Keypoint-Guided Optimal Transport with Application in Heterogeneous Domain Adaptation. Conference on Neural Information Processing Systems (NeurIPS), 2022. [Poster] [Code] (CCF-A)


• Xiang Gu, Jian Sun and Zongben Xu. Unsupervised and Semi-supervised Robust Spherical Space Domain Adaptation. IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2022. [Appendix] [Code] (CCF-A)


• Xiang Gu, Xi Yu, Yan Yang, Jian Sun and Zongben Xu. Adversarial Reweighting for Partial Domain Adaptation. Conference on Neural Information Processing Systems (NeurIPS), 2021. [Slides] [Code] (CCF-A)


• Xiang Gu, Jian Sun and Zongben Xu. Spherical Space Domain Adaptation with Robust Pseudo-label Loss. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2020. [Supp.] [Code] (CCF-A)

Academic Service

Reviewer for Journals: IEEE Transactions on Pattern Analysis and Machine Intelligence, International Jornal of Computer Vision, IEEE Transactions on Image Processing, etc.

PC Member: CVPR, ICCV, NeurIPS, ICLR, ICML, ECCV, AAAI, etc.

Correspondence

Email: xianggu@xjtu.edu.cn

Office: No.434, Building of Mathematics (数学楼), Xingqing Campus of Xi'an Jiaotong University

Address: No.28, Xianning West Road, Xi'an, Shaanxi, 710049, P. R. China.
(西安市咸宁西路28号, 710049)