Depending on your field, you might be looking for these "proper" adaptations:
The first paper, "Segment Anything," introduced the concept of a promptable segmentation system and the massive SA-1B dataset. Depending on your field, you might be looking
The follow-up paper, "SAM 2: Segment Anything in Images and Videos," extends the model to handle video objects in real-time. Depending on your field
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