Meta unveils AI model that can detect items within images

Facebook-owner Meta published an artificial intelligence model on Wednesday that can identify objects within an image, thanks to a dataset of image annotations that the company said was the largest ever of its kind.

Meta’s research division said in a blog post that its Segment Anything Model, or SAM, could identify objects in images and videos even when it had not encountered those items in its training. 

Using SAM, objects can be identified by either clicking on them or through text prompts. In one demonstration, writing the word ‘cat’ prompted the tool to draw boxes around each of several cats in a photo.

Big tech companies have been trumpeting their artificial intelligence breakthroughs since Microsoft-backed OpenAI's ChatGPT chatbot became a sensation in the fall, triggering a wave of investments and a race to dominate the space.

Meta has teased several features that deploy the type of generative AI popularised by ChatGPT, which creates brand new content instead of simply identifying or categorizing data like other AI, although it has not yet released a product.

Examples include a tool that spins up surrealist videos from text prompts and another that generates children's book illustrations from prose.

Chief executive Mark Zuckerberg has said that incorporating such generative AI "creative aids" into Meta's apps is a priority this year.

Meta does already use technology similar to SAM internally for activities like tagging photos, moderating prohibited content and determining which posts to recommend to users of Facebook and Instagram.

The company said SAM's release would broaden access to that type of technology.

The SAM model and dataset will be available for download under a non-commercial license. Users uploading their own images to an accompanying prototype likewise must agree to use it only for research purposes.