Date: Friday, September 13
Time: 12-1 p.m.
Location: BA 3200 and Online via Zoom. Enlarge image to scan QR code for Zoom link or visit: https://utoronto.zoom.us/meeting/register/tZMlf-ivqDojHNz0DpI-ubd4pMLEDyMBZdWc#/registration
There is no registration for this event. However, seating is limited, so arriving early is recommended.
Talk title: “Deep Internal Learning” – Deep Learning Without Prior Examples
Abstract:
In this talk I will show how Deep-Learning can be performed without any prior examples, by training on a single image/video – the test input alone. The strong recurrence of information inside a single natural image/video provides powerful internal examples which suffice for self-supervision of Deep-Networks, thus giving rise to true “Zero-Shot Learning”. I will show the power of this approach to a variety of problems, including: super-resolution (in space and in time), image-segmentation, transparent layer separation, image-dehazing, diverse image/video generation, and more.
Bio:
Michal Irani is a Professor at the Weizmann Institute of Science, Israel. She joined the Weizmann Institute in 1997, where she is currently the Dean of the Faculty of Mathematics and Computer-Science. Michal's research interests center around Computer-Vision, Image-Processing, Artificial-Intelligence, and Video information analysis. She also works on decoding visual information from Brain activity. Michal received a BSc degree in Mathematics and Computer Science from the Hebrew University of Jerusalem, and MSc and PhD degrees in Computer Science from the same institution. During 1993-1996 she was a member of the Vision Technologies Laboratory at the Sarnoff Research Center (Princeton). Michal's prizes and honors include the David Sarnoff Research Center Technical Achievement Award (1994), the Yigal Alon three-year Fellowship for Outstanding Young Scientists (1998), the Morris L. Levinson Prize in Mathematics (2003), the Maria Petrou Prize (awarded by the IAPR) for outstanding contributions to the fields of Computer Vision and Pattern Recognition (2016), the Landau Prize in Artificial Intelligence (2019), and the Rothschild Prize in Mathematics and Computer Science (2020). She received the ECCV Best Paper Award in 2000 and in 2002, and was awarded the Honorable Mention for the Marr Prize in 2001 and in 2005. In 2017 Michal received the Helmholtz Prize – the “Test of Time Award” (for the paper “Actions as space-time shapes”).