Colloquium - Yaoyao Liu, "Learning from Imperfect Data: Incremental Learning and Few-shot Learning"

Abstract: 
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 incremental learning and few-shot learning. Specifically, I will first discuss how to get better exemplars for incremental 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 incremental learning techniques to a more challenging and realistic scenario, e.g., object detection and medical imaging. Lastly, I will briefly mention my work on addressing other challenges and discuss future research directions.

Bio:
Yaoyao Liu is an assistant professor in the School of Information Sciences at the University of Illinois Urbana-Champaign. Previously, he completed his PhD in computer science at Max Planck Institute for Informatics and his BS in electronic information engineering at Tianjin University. He was also a postdoctoral fellow at Johns Hopkins 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 research interests include continual learning, few-shot learning, semi-supervised learning, generative models, 3D geometry models, and medical imaging. His work was listed in the “top 100 most cited CVPR papers over the last five years” by Google Scholar Metric. He is also a recipient of the 2024 ECVA PhD Award.