Booz Allen Hamilton Colloquium: Kostas Daniilidis, University of Pennsylvania
Friday, September 23, 2022
3:30 p.m.-4:30 p.m.
Jeong H. Kim Engineering Building, Room 1110
301 405 3114
Speaker: Kostas Daniilidis, Professor, University of Pennsylvania, Department of Computer and Information Science
Title: Data Efficiency through Symmetry and Event-based Processing in Robot Perception
Abstract: Scaling up data and computation is regarded today as the key to achieving unprecedented performance in many visual tasks. Given the lack of scale in real-world experience, robotics has turned to simulation as the vehicle for scaling up. Biological perception is characterized though by principles of efficiency implemented through symmetry and efficient sensing. In this talk, we will present a framework for achieving equivariance in vision by design rather than data augmentation and using orders of magnitude lower capacity models than competing approaches. Then, we will show how the new paradigm of event-based vision can facilitate visual motion and reconstruction tasks with asynchronous low-bandwidth processing.
Bio: Kostas Daniilidis has been faculty at the University of Pennsylvania since 1998. He is an IEEE Fellow. He was the director of the GRASP laboratory from 2008 to 2013. He obtained his PhD in Computer Science from the University of Karlsruhe (now KIT), 1992. He is co-recipient of the Best Conference Paper Award at ICRA 2017. Kostas’ main interest today is in geometric deep learning, event-based neuromorphic vision, and their applications in vision based manipulation and navigation.