Author: Lucian Negrea, Reporter
Published: 06-04-2023 18:46
Updated: 04-06-2023 20:03
Facebook-owned Meta Platforms on Wednesday published an artificial intelligence model that can pick out individual objects within an image, along with a dataset of image annotations it said was the largest of its kind.
The company’s research division said in a blog post that its Segment Anything model, or SAM, could identify objects in images and videos even in cases where it did not encounter those elements during training, informs News.ro.
Using SAM, objects can be selected by clicking on them or typing text messages. In one demonstration, typing the word “cat” caused the tool to draw boxes around each cat in a photo.
Big tech companies have been touting their advances in artificial intelligence since Microsoft-backed OpenAI’s ChatGPT chatbot became a sensation in the fall, sparking a wave of investment and a race to dominate the space.
Meta has introduced several features that implement the type of generative AI popularized by ChatGPT, which creates brand new content instead of simply identifying or classifying data like other AIs, although it has yet to release a product.
Examples include a tool that makes surreal videos from text prompts and another that generates children’s book illustrations from prose.
Zuckerberg: AI development is a priority
CEO Mark Zuckerberg said incorporating such generative AI “creative aids” into Meta apps is a priority this year.
Meta already uses technology similar to SAM inside the company for activities such as tagging photos, moderating banned content and determining which posts to recommend to Facebook and Instagram users.
The company said the launch of SAM will expand access to this type of technology.
The SAM model and dataset will be available for download under a non-commercial license. Also, users who upload their own images to a companion prototype must agree to use it for research purposes only.
