Dawei Zhou Ph.D Student State Key Laboratory of Integrated Services Networks (ISN) Xidian University Email: dwzhou.xidian@gmail.com [Google Scholar] [GitHub] Supervisor: Prof. Nannan Wang News | Research Interest | Education | Publications | Projects | Services

Research Interest

I am broadly interested in the field of cross-domain image synthesis, domain generalization and adversarial learning. Currently, I focus on the following research topics:

• Adversarial machine learning.
• Trustworthy machine learning.
• Deep learning-aided medical image analysis.

Education

• 2022.3-now      Ph.D in School of Telecommunications Engineering, Xidian University.       Supervisor: Prof. Nannan Wang & Prof. Tongliang Liu
• 2019.9-2022.2      M.S. in School of Telecommunications Engineering, Xidian University.       Supervisor: Prof. Nannan Wang & Prof. Tongliang Liu
• 2015.9-2019.6      B.E. in School of Telecommunications Engineering, Xidian University.        Supervisor: Prof. Nannan Wang

Publications

Journals:

• Towards Multi-domain Face Synthesis via Domain-Invariant Representations and Multi-level Feature Parts. [PDF]
  D. Zhou, N. Wang, C .Peng, Y. Yu, X. Yang and X. Gao.
  In IEEE Transactions on Multimedia, 2021.
• Synthesizing High-b-Value Diffusion–weighted Imaging of the Prostate Using Generative Adversarial Networks. [PDF]
  L. Hu, D. Zhou, Y. Zha, L. Li, H. He, W. Xu, L. Qian, Y. Zhang, C. Fu, H. Hu and J. Zhao.
  In Radiology: Artificial Intelligence, 2021.
• Advanced zoomed diffusion-weighted imaging vs. full-field-of-view diffusion-weighted imaging in prostate cancer detection: a radiomic features study. [PDF]
  L. Hu, D. Zhou, C. Fu, T. Benkert, C. Jiang, R. Li, L. Wei and J. Zhao.
  In European Radiology, 2020.

Conferences:

• Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration.
  D. Zhou, Y. Chen, N. Wang, D. Liu, X. Gao and T. Liu.
  In ICML, 2023.
• Phase-aware Adversarial Defense for Improving Adversarial Robustness.
  D. Zhou, N. Wang, H. Yang, X. Gao and T. Liu.
  In ICML, 2023.
• Modeling Adversarial Noise for Adversarial Training. [PDF] [Code]
  D. Zhou, N. Wang, B. Han and T. Liu.
  In ICML, 2022.
• Improving Adversarial Robustness via Mutual Information Estimation. [PDF] [Code]
  D. Zhou, N. Wang, X. Gao, B. Han, X. Wang, Y. Zhan and T. Liu.
  In ICML, 2022.
• Removing Adversarial Noise in Class Activation Feature Space. [PDF] [Code]
  D. Zhou, N. Wang, C .Peng, X. Gao, X. Wang, J. Yu and T. Liu.
  In ICCV, 2021.
• Towards Defending against Adversarial Examples via Attack-Invariant Features. [PDF] [Code]
  D. Zhou, T. Liu, B. Han, N. Wang, C. Peng and X. Gao.
  In ICML, 2021.

Projects

• Design of Communication Receiver Based on Machine Learning (Cooperation with Huawei).

Services

• Reviewer for NeurIPS 2022.
• Reviewer for UAI 2022.
• Reviewer for KDD 2022.
• Reviewer for IJCAI 2022.
• Reviewer mentee for ICLR 2022.
• Reviewer for CICAI 2021.
• Reviewer for IJCAI WSRL 2021.
• Reviewer for ICIG 2021.

Awards

A Top Reviewer for UAI 2022.