Meta announces its AI model SAM with ability to recognise objects within an image

Posted on:
Key Points

It was about time that Facebook's parent company, Meta, hopped on to the artificial intelligence bandwagon..

The company has recently announced its own language model, SAM, that has the ability to identify different objects within an image..

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 company noted...

We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images," the blog post read...

In a demonstration of the new AI model, writing the word 'cat' made the tool draw boxes around each of various cats in a picture, a Reuters report states.. Further, the SAM model and dataset will be available for download under a non-commercial license..