Abstract

Automated visual recognition is in increasingly high demand. However, despite tremendous performance improvement in recent years, state-of-the-art deep visual models learned using large-scale benchmark datasets still fail to generalize to the diverse visual world. In this talk I will discuss a general purpose semi-supervised learning algorithm, domain adversarial learning, which facilitates transfer of information between different visual environments and across different semantic tasks thereby enabling recognition models to generalize to previously unseen worlds. I’ll demonstrate applications of this approach to different visual tasks, such as semantic segmentation in driving scenes and transfer between still image object recognition and video action recognition.

Bio

Judy Hoffman is a postdoctoral researcher at UC Berkeley. Her research lies at the intersection of computer vision and machine learning with a specific focus on semi-supervised learning algorithms for domain adaptation and transfer learning. She received a PhD in Electrical Engineering and Computer Science from UC Berkeley in 2016. She is the recipient of the NSF Graduate Research Fellowship, the Rosalie M. Stern Fellowship, and the Arthur M. Hopkin award for seriousness of purpose and high academic achievement. She is also a founder of the WiCV workshop (women in computer vision) co-located at CVPR annually.

Host: Abhinav Gupta

Admin Contact: Chris Downey cdowney@andrew.cmu.edu