Wencan Zhang
Contact
Hi! I am a post-doc research fellow at the department of computer science, National University of Singapore. Now I am a member of the NUS UbiComp Lab led by Prof. Brian Lim.
My research interest aims at improving the interpretability of machine learning models by aligning human perception and reasoning. As a group, we develop interpretable models under various applications and evaluate the interaction with real users. The broader research interests include human centered AI, data privacy, human computer interaction.
For more details about me and my research, please check out my CV.
Research
Publications
|
Towards Relatable Explainable AI with the Perceptual Process Wencan Zhang, Brian Y. Lim Conference on Human Factors in Computing Systems (CHI), 2022. pdf tech blog |
|
Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learning Wencan Zhang, Mariella Dimiccoli, Brian Y. Lim Conference on Human Factors in Computing Systems (CHI), 2022. pdf tech blog |
|
Exploiting Explanations for Model Inversion Attacks Zhao, Xuejun, Wencan Zhang, Xiaokui Xiao, and Brian Lim. International Conference on Computer Vision (ICCV), 2021. pdf video |
|
Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations Danding Wang, Wencan Zhang, Brian Y. Lim Artificial Intelligence, 2021. pdf video |
Teaching
Phenomena and Theories of Human-Computer Interaction
Teaching Assistant
National University of Singapore, 2019-2022.
Software Engineering Project
Teaching Assistant
National University of Singapore, 2019.