Meta releases AI model ‘SAM,’ can identify items within images

Facebook parent Meta released an artificial intelligence (AI) model that can pick out the different items within the photographs, Fox News reported.
Meta’s research division said that it has published a Segment Anything Model (SAM) and the corresponding dataset to foster research into foundation models for computer vision. In its statement, Meta said that SAM can identify the objects within images and videos – even in cases where it had not encountered those items in its training.
“The model is designed and trained to be prompt, so it can transfer zero-shot to new image distributions and tasks,” Meta said in a blog post.
“We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive – often competitive with or even superior to prior fully supervised results,” it added.

Deepika Shakya

Recent Posts

Gut Microbes and Hormones: The Hidden Drivers of Your Sweet Tooth

The relationship between gut microbes, hormones, and dietary preferences is a fascinating area of study…

1 hour ago

Environmental Impact of ChatGPT: Linked to Los Angeles Wildfires Debate

AI systems like ChatGPT have been linked to environmental concerns, with reports showing their significant…

1 hour ago

Kathmandu Court Grants Rabi Lamichhane Bail of Rs 6 Million in Fraud Case

Rabi Lamichhane, RSP chief and ex-home minister, secures bail in the Swarnalakshmi Cooperative fraud case…

2 hours ago

Metformin: A Diabetes Drug That May Help Prevent Skin Cancer

Metformin, the widely prescribed drug for managing type 2 diabetes, has recently gained attention for…

2 hours ago

Wildfire Smoke 10 Times More Toxic Than Pollution, Stanford Report Reveals

California wildfires leave destruction in their wake, with Stanford experts warning of the underestimated dangers…

2 hours ago

Kenya’s Minister Justin Muturi Speaks Out on Son’s Abduction

Report of Kenya's child abduction shows around 44 percent of child has been abducted between…

2 hours ago