Meta, the parent company of Facebook, has announced the launch of a new artificial intelligence model called the Segment Anything Model (SAM). The new model is capable of identifying individual objects within an image, even if it has not encountered those objects during its training.
SAM is designed to identify objects within images and videos, and it can do so even when those objects are not clearly defined. The model is capable of identifying multiple objects within an image and can even pick out individual objects within a group.
According to the announcement post by Meta, it says its Segment Anything Model, or SAM, could identify objects in images and videos even in cases where it had not encountered those items in its training. The new model is capable of identifying objects in images and videos with great accuracy, even in cases where the objects are partially occluded or have low contrast.
Using SAM, objects can be selected by clicking on them or writing text prompts. In one demonstration, writing the word “cat” prompted the tool to draw boxes around each of several cats in a photo.
One of the key features of SAM is its ability to be trained on a wide range of datasets. This means that the model can learn to recognize objects that are not typically found in a particular dataset, making it a highly versatile tool for a range of applications.
Meta has teased several features that deploy the type of generative AI popularized 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.