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 of self-supervised learning will be presented, including on/off-screen source separation, image forensics, paired and unpaired image-to-image translation (aka pix2pix and cycleGAN), and curiosity-based exploration.
Bio: Alexei (Alyosha) Efros joined UC Berkeley in 2013. Prior to that, he was 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. Efros received his PhD in 2003 from UC Berkeley. He is a recipient of CVPR Best Paper Award (2006), Sloan Fellowship (2008), Guggenheim Fellowship (2008), SIGGRAPH Significant New Researcher Award (2010), 3 Helmholtz Test-of-Time Prizes (1999,2003,2005), and the ACM Prize in Computing (2016).
The Donald B. Gillies Memorial Lectureship in Computer Science was established at the University of Illinois through memorial gifts by family and friends, with a major contribution by the Digital Equipment Corporation.
Professor Gillies, a native of Canada, did his undergraduate work at the University of Toronto, and received his Ph.D. in mathematics from Princeton University in 1953. While in graduate school he worked as a graduate assistant at the Institute for Advanced Study with John von Neumann in the fields of game theory and computer science. Before coming to the University of Illinois in 1956, he spent two years with the National Research Development Corporation at Cambridge University and London, England. He was among the first mathematicians to become involved in the computer field, helping to calculate the first Sputnik orbit and later discovering three new prime numbers in the course of checking out ILLIAC II. Before his death in 1975, he was experimenting with educational uses and networking possibilities of minicomputers.
Donald GilliesProfessor Gillies was an inspiration to his students, taking an interest in both their professional and personal lives. Long before timesharing terminals, minicomputers and microprocessors made “hands on” computer experience commonplace, he recognized the need for students to have this opportunity and implemented a system to provide it. Throughout his work and teaching he stressed the importance of the ethical use of computing machines in contemporary science. Dedicated to the honest uses of technology, environmentally concerned, a man of wit, vigor and understanding, he challenged and stimulated all who knew him.
It is hoped that the Donald B. Gillies Lectureship in Computer Science will continue to enrich the lives of students and colleagues as an appropriate memorial to a man whose intellectual excellence and moral purpose made him a distinguished teacher and scientist.