Event Location: NSH 1507
Bio: Olga Russakovsky (http://cs.cmu.edu/~orussako) is a postdoctoral research fellow at Carnegie Mellon University. She recently completed a PhD in computer science at Stanford advised by Prof. Fei-Fei Li. Her research is in computer vision, closely integrated with machine learning and human-computer interaction. She led the ImageNet Large Scale Visual Recognition Challenge effort for two year (http://image-net.org/challenges/LSVRC), served as a Senior Program Committee member for WACV’16, and organized multiple workshops and tutorials at premier computer vision conferences. She founded and directs the Stanford AI Laboratory’s outreach camp SAILORS (http://sailors.stanford.edu) designed to expose high school students in underrepresented populations to the field of AI, and helped pioneer the first “Women in Computer Vision” workshop at CVPR’15.

Abstract: Intelligent agents acting in the real world need to perceive, learn from, reason about and interact with their environment. In this talk, I will explore the role that humans play in the design, deployment and environment of computer vision systems. First, large-scale manually labeled datasets have proven instrumental for scaling up visual recognition, but they come at a substantial human cost. I will talk about strategies for making optimal use of human annotation effort for computer vision progress. However, no dataset can foresee all the visual scenarios that a real-world system might encounter. I will argue that seamlessly integrating in human expertise at runtime will become an increasingly important component of open-world computer vision. I will talk both about mathematical frameworks for human-machine collaboration as well as deep reinforcement learning computer vision models that open up new avenues for human-in-the-loop exploration.