Segment Anything

ICCV 2023  ·  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 ·

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at https://segment-anything.com to foster research into foundation models for computer vision.

PDF Abstract ICCV 2023 PDF ICCV 2023 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Zero-Shot Instance Segmentation LVIS v1.0 val SAM (ViTDet-H prompt) AP 44.7 # 2
Compare
Event-based Object Segmentation MVSEC-SEG SAM mIoU 0.26 # 8
Compare
Event-based Object Segmentation RGBE-SEG SAM mIoU 0.26 # 8
Compare

Methods
Add Remove

Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy