Knowledge Transfer for Face Recognition
Zhengming Ding, Graduate Student, Northeastern University
Wednesday, December 6, 1:00-2:00pm; Hariri Institute for Computing (111 Cummington Mall, Boston)
Abstract: It is essential to adapt previous well-organized knowledge to facilitate the challenging face recognition tasks, e.g., missing modality and one-shot issues. First of all, transfer learning may fail if no target evaluated face data are available in the training stage. This problem arises when the data are the multi-modal face. To overcome this, we first borrow an auxiliary database with complete modalities, then consider knowledge transfer across databases and across modalities within databases simultaneously in a unified framework. Secondly, one-shot face recognition measures the ability to recognize persons with only seeing them once, which is a hallmark of human visual intelligence. It is challenging for existing machine learning approaches to mimic this way since limited data cannot well represent the data variance. We propose to build a large-scale face recognizer, which is capable to fight off the data imbalance difficulty. To seek a more effective general classifier, we develop a novel generative model attempting to synthesize meaningful data for one-shot classes by adapting the data variances from other normal classes.
Bio: Zhengming Ding received the B.Eng. degree in information security and the M.Eng. degree in computer software and theory from University of Electronic Science and Technology of China (UESTC), China, in 2010 and 2013, respectively. He is currently working toward the Ph.D. degree in the Department of Electrical and Computer Engineering, Northeastern University, USA. His research interests include machine learning and computer vision. Specifically, he devotes himself to develop scalable algorithms for challenging problems in transfer learning and deep learning scenario. He was the recipient of the Student Travel Grant of Pittcon 18, CVPR 17, FG 17, IJCAI 16, AAAI 16, ACM MM 14 and ICDM 14. He received the National Institute of Justice (NIJ) Fellowship. He was the recipient of the best paper award (SPIE) and the best paper candidate of ACM Multimedia 2017. He has served as the reviewers for IEEE journals: IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Pattern Analysis and Machine Intelligence, etc. He is an IEEE and AAAI student member.