CISE Seminar: Judy Hoffman, Assistant Professor, Georgia Tech
Date: March 31, 2023
Location: 8 Saint Mary’s Street, PHO 203
Georgia Institute of Technology
Reliable Vision for a Changing World
The visual world is constantly changing. The appearance of a scene can vary based on camera conditions, layout of objects, or times of day. To truly create vision systems that will be reliable in the face of our diverse world, we need to tackle two key problems: distribution generalization and adaptation. In this talk we will discuss recent directions in domain generalization for Sim2Real transfer as well as for reliable domain adaptation. Finally, we will conclude with highlighting some recent efforts to improve the efficiency of large vision systems.
Dr. Judy Hoffman is an Assistant Professor in the School of Interactive Computing at Georgia Tech, a member of the Machine Learning Center, and a Diversity and Inclusion Fellow. Her research lies at the intersection of computer vision and machine learning with specialization in domain adaptation, transfer learning, adversarial robustness, and algorithmic fairness. She has received numerous awards including NSF CAREER, Google Research Scholar Award, Samsung AI Researcher of the Year Award, NVIDIA female leader in computer vision award, AIMiner top 100 most influential scholars in Machine Learning, and MIT EECS Rising Star. In addition to her research, she co-founded and continues to advise for Women in Computer Vision, an organization which provides mentorship and travel support for early-career women in the computer vision community. Prior to joining Georgia Tech, she was a Research Scientist at Facebook AI Research. She received her PhD in Electrical Engineering and Computer Science from UC Berkeley in 2016 after which she completed Postdocs at Stanford University and UC Berkeley.
Faculty Host: Brian Kulis
Student Host: Andres Chavez Armijos