A new state of the art for unsupervised vision

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.

Related Keywords

Zhoutong Zhang ,Williamt Freeman ,Mark Hamilton ,Andrea Vedaldi ,Noah Snavely ,Bharath Hariharan ,International Conference On Learning Representations ,Artificial Intelligence Laboratory ,University Of Oxford ,Geometry Group ,Cornell University ,Microsoft ,Energy Based Graph ,Visual Geometry Group ,Assistant Professor Bharath Hariharan ,Associate Professor Noah Snavely ,Cornell Tech ,Learning Representations ,Computer Science And Artificial Intelligence Laboratory Csail ,Sail ,Computer Vision ,Otego ,Abeling Images ,Semantic Segmentation ,Medical Diagnostics ,Oco Stuff ,Ino Algorithm ,Imagenet ,Elf Supervised Transformer With Energy Based Graph Optimization ,