We look forward to seeing you online on Thursday, 4/13 for the Vision Speaker Series.
In recent years, artificial intelligence (AI) has achieved great success in many fields. Although impressive advances have been made, AI algorithms still suffer from an important limitation: they rely on static and large-scale datasets. In contrast, human beings naturally possess the ability to learn novel knowledge from real-world imperfect data such as a small number of samples or a non-static continual data stream. Attaining such an ability is particularly appealing and will push the AI models one step further toward human-level Intelligence.
In this talk, I will present my work on addressing these challenges in the context of continual learning and few-shot learning. Specifically, I will first discuss how to get better exemplars for continual learning based on optimization. I parameterize exemplars and optimize them in an end-to-end manner to obtain high-quality memory-efficient exemplars. Then, I will present my work on how to apply continual learning techniques to a more challenging and realistic scenario, object detection. I will provide algorithm design on a transformer-based incremental object detection framework. I will briefly mention my work on addressing other challenges and discuss future research directions.
Yaoyao Liu is a postdoctoral fellow in the Department of Computer Science at Johns Hopkins University, working with Prof. Alan L. Yuille. He received his Ph.D. in Computer Science at Max Planck Institute for Informatics, where he was advised by Prof. Bernt Schiele and Prof. Qianru Sun. As part of the European Laboratory for Learning and Intelligent Systems (ELLIS) Ph.D. Program, he was also co-supervised by Dr. Christian Rupprecht and Prof. Andrea Vedaldi in the Visual Geometry Group (VGG) at the University of Oxford. From 2018 to 2019, he was a research intern at the National University of Singapore, working with Prof. Tat-Seng Chua and Prof. Qianru Sun. Prior to this, he obtained his bachelor’s degree from Tianjin University. His research lies at the intersection of computer vision and machine learning – with a special focus on building intelligent visual systems that are continual and data-efficient. His work was selected as “top 200 most cited CVPR papers over the last five years” by Google Scholar Metric and featured in the National University of Singapore News.