The Segment Anything Model (SAM) is a recently introduced foundation model for image segmentation developed by Meta AI. It is designed as a general-purpose, promptable segmentation model that can produce accurate object masks from images in a zero-shot manner (without task-specific training).SAM was trained on the SA-1B dataset, which contains a billion masks, making it highly general. It combines the strengths of interactive segmentation (allowing user guidance) and automatic segmentation (pre-trained knowledge) to work on arbitrary objects.
Data Selection & Data Viewer
Get data insights and find the perfect selection strategy
Learn MoreSelf-Supervised Pretraining
Leverage self-supervised learning to pretrain models
Learn MoreSmart Data Capturing on Device
Find only the most valuable data directly on devide
Learn More