Graduate Student Researcher
My current research interests lie at the intersection of visual recognition and robotics, where I am interested in generalizable end-to-end models for perception and action. Previously, I have worked on a method for semantic segmentation in video using dyanmic CNN architectures as well as domain adaptation for segmentation and detection models. In undergrad, I contributed to a project applying semi-supervised learning techniques to historical photographs to discover trends in fashion and hairstyle over the past century.
Kate Rakelly is a PhD student at UC Berkeley, where she worsk with Sergey Levine and Alyosha Efros as part of BAIR. She did her undergrad also at UC Berkeley, where she worked with Shiry Ginosar and Alyosha Efros in computer vision as well as Claire Tomlin in control.