Pose estimation made better, easier, and faster with video semi-supervised learning on the cloud
Dan Biderman, Matt Whiteway, Cole Hurwitz, Nicholas Greenspan, Robert Lee, Ankit Vishnubhotla, Michael Schartner, Julia Huntenberg, Richard Warren, Dillon Noone, Federico Pedraja, The International Brain Lab The International Brain Lab, Nathaniel Sawtell, Liam Paninski · COSYNE 2023
Computer vision algorithms now allow neuroscientists to quantify animal movement in unprecedented detail, shedding new light on problems in motor control, social behavior, navigation, and beyond. Existing models are only trained with labeled frames (supervised learning). Although effective in many cases, the supervised approach requires extensive image annotation, struggles to generalize to new videos, and produces noisy outputs that hinder downstream analyses. We address each of these limitations by introducing unlabeled video clips to model training and inference, and exploiting their spatio
Sat, Mar 11, 2023