The first paper, "Segment Anything," introduced the concept of a promptable segmentation system and the massive SA-1B dataset.
If you're asking about the , you're likely looking for the foundational research papers from Meta AI that introduced these computer vision models. Foundational Research Papers
Depending on your field, you might be looking for these "proper" adaptations:
The most recent advancement, "SAM 3: Segment Anything with Concepts," unifies detection, segmentation, and tracking with text and visual prompts. Specialized "SAM" Papers
The follow-up paper, "SAM 2: Segment Anything in Images and Videos," extends the model to handle video objects in real-time.