visionPublished: April 5, 2023
Segment anything
By Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, Ross Girshick
Research TL;DR
"Introduces the Segment Anything Model (SAM) and a massive dataset for zero-shot image segmentation. Enables interactive visual segmenting on arbitrary images."
Abstract
We introduce the Segment Anything project: a new task, model, and dataset for image segmentation. Using our efficient model in a loop, we built the largest segmentation dataset to date, with over 1 billion masks on 11M licensed and privacy-respecting images.