MIT CSAIL scientists created an algorithm called STEGO to solve one of the hardest tasks in computer vision: assigning every pixel in the world a label without any human supervision.
A simpler path to better computer vision
A simpler path to better computer vision
IJGI, Free Full-Text
A new state of the art for unsupervised computer vision
Researchers From Tsinghua University Introduce A Novel Machine
/sustainability/sustainability-15-0402
Unsupervised machine learning in urban studies: A systematic
Deep learning-enabled medical computer vision
Sustainability, Free Full-Text
Learning to compute through art, MIT News