A new state of the art for unsupervised computer vision

Share this & earn $10
Published at : April 26, 2022

Scientists from MIT CSAIL created an algorithm to solve one of the hardest tasks in computer vision: assigning every single pixel of the world a label without any human supervision.
Technical paper: https://arxiv.org/abs/2203.08414
Project website: https://mhamilton.net/stego.html A new state of the art for unsupervised computer vision
MITMassachusetts Institute of TechnologyCSAIL