Representation Learning Without Human Annotation

[CFAR Rising Star Lecture]
Representation Learning Without Human Annotation by Dr Li Junnan
04 Apr 2022 | 9:00am (Singapore Time)

Representation learning has been the key factor of success for many deep learning models. While conventional representation learning relies on a larger amount of human-annotated data, learning without human annotation has become the modern trend. 

In this talk, Dr Li Junnan will introduce several key directions to advance representation learning with few human annotations, namely (1) self-supervised learning, (2) semi-supervised learning, and (3) weakly-supervised vision-language pre-training. The talk will focus on state-of-the-art methods and recent developments.

Li Junnan, Lead Research Scientist, Salesforce, NUS
Dr Li Junnan
Lead Research Scientist, Salesforce Research Asia, Singapore
B.Eng. (Electronic Engineering): University of Hong Kong
Ph.D. (Computer Science): National University of Singapore

Li Junnan is currently a lead research scientist at Salesforce Research Asia. He obtained his PhD at the National University of Singapore in 2019. He has published in many top-tier venues in machine learning and computer vision, such as NeurIPS, ICLR, CVPR, ICCV, etc. His main research interests include vision-and-language, self-supervised / semi-supervised / weakly-supervised learning. His ultimate research goal is to build general-purpose AI models that can self-learn without human involvement.