Meta has launched a new Artificial Intelligence (AI) model named Segment Anything Model that is capable of identifying particular objects within an image. The company says the Segment Anything AI Model can already take a photo and individually identify the pixels comprising everything in the picture so that one or more items can be separated from the rest of the image.
Segment Anything AI Model to Become the Next Big Thing
SAM could be used to help power applications in numerous domains that require finding and segmenting any object in any image. it can improve creative applications such as extracting image regions for collages or video editing. SAM could also be used to aid the scientific study of natural occurrences on Earth or even in space, for example, by localizing animals or objects to study and track in the video.
“Segmentation—identifying which image pixels belong to an object—is a core task in computer vision and is used in a broad array of applications, from analyzing scientific imagery to editing photos,” Meta wrote in a blog post. Ross Girshick, a research scientist at Meta, said; “Our resulting model shows impressive capabilities to handle types of images that were not seen during training, like ego-centric images, microscopy, or underwater photos.”
How Does the Model Work?
Meta said that by 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. Meta uses similar technologies for activities like tagging photos, moderating prohibited content, and determining which posts to recommend to users of Facebook and Instagram.
Also read: India Unveils Its First AI News Anchor Sana
