2021 IBIIS & AIMI Hybrid Retreat

September 27th & 28th, 1:00pm – 4:15pm

Self-Supervision for Learning from the Bottom Up

Why do self-supervised learning? A common answer is: "because data labeling is expensive." In this talk, I will argue that there are other, perhaps more fundamental reasons for working on self-supervision. First, it should allow us to get away from the tyranny of top-down semantic categorization and force meaningful associations to emerge naturally from the raw sensor data in a bottom-up fashion. Second, it should allow us to ditch fixed datasets and enable continuous, online learning, which is a much more natural setting for real-world agents. Third, and most intriguingly, there is hope that it might be possible to force a self-supervised task curriculum to emerge from first principles, even in the absence of a pre-defined downstream task or goal, similar to evolution. In this talk, I will touch upon these themes to argue that, far from running its course, research in self-supervised learning is only just beginning.


Alexei (Alyosha) Efros is a Professor of Electrical Engineering and Computer Science  at UC Berkeley and member of the BAIR Lab. 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 the Sloan Fellowship (2008), Guggenheim Fellowship (2008), Okawa Grant (2008), SIGGRAPH Significant New Researcher Award (2010), 3 PAMI-TC Helmholtz Test-of-Time Prizes (1999,2003,2005), the ACM Prize in Computing (2016), and Diane McEntyre Award for Excellence in Teaching Computer Science (2019). 

Monday, September 27th - Open to All Stanford

1:00 - 1:15pm

Welcome & Introduction
– Curt Langlotz & Kristen Yeom

1:15 - 1:55pm

Keynote Talk – Alexei (Alyosha) Efros, PhD

Professor of Electrical Engineering and Computer Science
UC Berkeley

1:55 - 2:15pm

Fireside Chat

Alexei Efros
Akshay Chaudhari
Mirabela Rusu

2:15 - 2:30pm

Group Zoom Photo & Break

2:30 - 3:15pm

AIMI Industry Affiliates Introductions

3:15 - 4:15pm

Panel Discussion: Career Transitions

Moderators: Natasha Diba Sheybani & Rogier van der Sluijs
Panelists:  Akshay Chaudhari, Mirabela Rusu, Nishith Khandwala, Sarah Mattonen, & Yuhao Zhang


Closing Remarks & Adjourn

Tuesday, September 28th - IBIIS & AIMI only

James H. Clark Center - 318 Campus Drive

1:00 - 1:05pm

Introduction – Kristen Yeom

Location: Clark S360

1:05 - 1:15pm

Resources in the School of Medicine – Johanna Kim

Location: Clark S360

1:15 - 2:15pm

Faculty Introductions

Location: Clark S360

2:15 - 2:30pm


2:30 - 4:00pm

Poster Session

Location: Clark Courtyard

4:00 - 4:15pm

Poster Vote & Announce Poster Prize Winners

Location: Clark Courtyard


Closing Remarks & Adjourn