Associate Professor (tenure-track)
John Hopcroft Center for Computer Science
Shanghai Jiao Tong University

His research interests range across computer vision and machine learning.Now, he is leading a group for explainable AI. The related topics include interpretable CNNs, explainable generative networks,unsupervised semanticization of pre-trained neural networks, and unsupervised/weakly-supervised learning of neural networks. He aims to 1) end-to-end learn interpretable neural networks, and/or 2) unsupervisedly transform the black-box knowledge representation of pre-trained neural networks into a hierarchical and semantically interpretable graph. He believes a symbolic/graphical representation of CNN knowledge can ensure high transferability of features and help weakly-supervised learning from small data and will lead the future development of deep learning.

• Quanshi Zhang, Ying Nian Wu, and Song-Chun Zhu, "Interpretable Convolutional Neural Networks," in CVPR, 2018

• Quanshi Zhang, Ruiming Cao, Feng Shi, Ying Nian Wu, and Song-Chun Zhu, "Interpreting CNN Knowledge via an Explanatory Graph," in AAAI, 2018

• Quanshi Zhang, Wenguan Wang, and Song-Chun Zhu, "Examining CNN Representations with respect to Dataset Bias," in AAAI, 2018

• Quanshi Zhang, Ruiming Cao, Ying Nian Wu, and Song-Chun Zhu, "Mining Object Parts from CNNs via Active Question-Answering," in CVPR 2017

• Quanshi Zhang, Ruiming Cao, Ying Nian Wu, and Song-Chun Zhu, "Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning," in AAAI 2017

• Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, Ryosuke Shibasaki, "Object Discovery: Soft Attributed Graph Mining," in IEEE Transactions on PAMI 38(3):532-545, 2016.