Helsinki Distinguished Lecture: Alexei Efros (UC Berkeley), “Self-Supervised Visual Learning and Synthesis”
This lecture is part of the Helsinki Distinguished Lecture Series on Future Information Technology
The Helsinki Distinguished Lecture Series on Future Information Technology is organized by HIIT, a joint research institute between University of Helsinki and Aalto University. The series was launched in 2012.
The focus of the seminar series is to highlight the research challenges and solutions faced by current and future information technology, as seen by the internationally leading experts in the field.
Venues alternate between University of Helsinki and Aalto University, the two host universities of HIIT.
Self-Supervised Visual Learning and Synthesis
Speaker: Professor Alexei A. Efros, UC Berkeley
Host: Professor Jaakko Lehtinen
Date: Friday 15.6.2018 at 10:00-11:00
Venue: Lecture hall T1, CS Building, Aalto University, Konemiehentie 2, Espoo
Web page: Helsinki Distinguished Lecture Series on Future IT
Welcome to the next lecture in the Helsinki Distinguished Lecture series on Future Information Technology which will be given by Professor Alexei Efros from UC Berkeley.
The lecture is free of charge and open to everyone interested in the latest research in information technology. Coffee and light refreshments will be served after the lecture.
For catering purposes please sign up through this link on Monday 11.6. at the latest.
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, paired and unpaired image-to-image translation (aka pix2pix and cycleGAN), curiosity-based exploration, and, terrifyingly, #edges2cats.
About the Speaker
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), NSF CAREER award (2006), Sloan Fellowship (2008), Guggenheim Fellowship (2008), Okawa Grant (2008), Finmeccanica Career Development Chair (2010), SIGGRAPH Significant New Researcher Award (2010), ECCV Best Paper Honorable Mention (2010), 3 Helmholtz Test-of-Time Prizes (2013,2017), and the ACM Prize in Computing (2016).