CS Distinguished Lecturer: Prof. Alexei A. Efros from UC Berkeley
Professor Alexei A. Efros from UC Berkeley
Host: Yong Jae Lee
When: Thursday, May 11th at 3:10pm
Where: 1131 Kemper Hall
Title: Self-Supervised Visual Learning and Synthesis
Abstract: Computer vision has made impressive gains through the use of deep learning models, trained with large-scale labeled data. However, labels require expertise and curation and are expensive to collect. Can one discover useful visual representations without the use of explicitly curated labels? In this talk, I will present several case studies exploring the paradigm of self-supervised learning — using raw data as its own supervision. Several ways of defining objective functions in high-dimensional spaces will be discussed, including the use of General Adversarial Networks (GANs) to learn the objective function directly from the data. Applications in image synthesis will be shown, including automatic colorization, image-to-image translation, and, terrifyingly, #edges2cats.
Alexei (Alyosha) Efros joined UC Berkeley in 2013 as associate professor of Electrical Engineering and Computer Science. Prior to that, he spent nine years on the faculty of Carnegie Mellon University, and has also been affiliated with École Normale Supérieure/INRIA and University of Oxford. His research is in the area of computer vision and computer graphics, especially at the intersection of the two. He is particularly interested in using data-driven techniques to tackle problems where large quantities of unlabeled visual data are readily available. Alyosha received his PhD in 2003 from UC Berkeley. He is a recipient of CVPR Best Paper Award (2006), NSF CAREER award (2006), Sloan Fellowship (2008), Guggenheim Fellowship (2008), Okawa Grant (2008), SIGGRAPH Significant New Researcher Award (2010), the Helmholtz Test-of-Time Prize (2013), and the ACM Prize in Computing (2017).
1131 Kemper Hall