Jian Liang's (梁坚) Homepage

Jian Liang (梁坚, Tim)

Associate Professor
Center for Research on Intelligent Perception and Computing (CRIPAC)
Institute of Automation, Chinese Academy of Sciences (CAS)
Room 1505, Intelligent Building, 95 Zhongguancun East Road
100190, Haidian District, Beijing, China

Email: liangjian92@gmail.com or jian.liang@nlpr.ia.ac.cn
[Webpage@CRIPAC] [Arxiv] [GitHub] [Google Scholar] [Twitter]

About Myself

I am currently an associate professor at Center for Research on Intelligent Perception and Computing (CRIPAC) affiliated to the Institute of Automation, Chinese Academy of Sciences (CAS). From June 2019 to May 2021, I was a research fellow at the Vision and Learning Group, National University of Singapore (NUS), working with Jiashi Feng. Before joining NUS in 2019, I obtained Ph.D. in Pattern Recognition and Intelligent Systems from Institute of Automation, Chinese Academy of Sciences (CASIA) in Jan 2019, under the supervision of Tieniu Tan and co-supervision of Ran He and Zhenan Sun, and received my bachelor degree in Automation from Xi'an Jiaotong University in June 2013.

My current research interests mainly focus on deep representation learning, unsupervised/ self-supervised learning and transfer learning (including domain adaptation), with their applications to vision and multimedia problems.

Education Background

	Ph.D., University of the Chinese Academy of Sciences (UCAS) Pattern Recognition and Intelligent Systems Advisor: Prof. Tieniu Tan (谭铁牛) Co-Advisors: Prof. Ran He (赫然) and Prof. Zhenan Sun (孙哲南) Thesis: Multi-domain learning and its applications in retrieval, clustering, and classification (多域学习及其在检索、聚类和分类中的应用研究)	Sep, 2013 - Jan, 2019
	B.Eng., Xi'an Jiaotong University Automation Thesis supervisor: Prof. Sibo Ge (葛思擘)	June, 2009 - July, 2013

Selected Publications

	Domain Adaptation with Auxiliary Target Domain-Oriented Classifier Jian Liang and Dapeng Hu and Jiashi Feng IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [Paper] [Code]
	Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer Jian Liang and Dapeng Hu and Yunbo Wang and Ran He and Jiashi Feng IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021. [Paper] [Code]
	Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation Jian Liang and Dapeng Hu and Jiashi Feng International Conference on Machine Learning (ICML), 2020. [Paper] [Code] [Slides]
	No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data Mi Luo and Fei Chen and Dapeng Hu and Yifan Zhang and Jian Liang and Jiashi Feng Annual Conference on Neural Information Processing Systems (NeurIPS), 2021. [Paper]