← Jargon

Jargoncomputer vision· 5 claims· 1 episode

Segment Anything

A foundational model released by Meta that can segment (identify and extract) all objects in an image and can be directed to find specific items through prompts (points, boxes, or text); generalizes across domains without task-specific training.

As defined in You need to learn AI in 2024! (And here is your roadmap)


Where it comes up · 1