Yesterday, Wednesday, Meta, the company that owns Facebook, published an artificial intelligence model that can recognize elements within images, along with a data set of annotations on them, which it said was the largest of its kind ever, according to a report. Reuters.
The company's research division said its model, known as the Segmentation of Anything Model, or SAM, can identify elements in photos and videos even if he has not interacted with those elements during his training.
With SAM, items can be selected by clicking on them or typing in their name. In one demonstration, typing the word "cat" prompted the tool to place boxes on each of the cats in the image.
Major technology companies have been announcing their breakthroughs in artificial intelligence since the uproar caused by the Microsoft-backed Chat GPT chatbot, Open Ai, which led to a wave of Investments and a race to dominate the arena.
Mark Zuckerberg, CEO of Meta, said integrating such "creative assistants" of AI into Meta applications was a priority this year.
Meta internally uses technology similar to the SAM model for tasks such as tagging images, reviewing prohibited content, and determining which posts to filter for Facebook and Instagram users.
The company said that the launch of the "SAM" model will expand access to this type of technology.
Source: Reuters
Post a Comment