MetaJul 29, 2024
SAM 2
Meta's Segment Anything Model 2, which segments any object in images and tracks it through videos from simple clicks or boxes.
- Type
- Vision
- Context
- —
- Weights
- Open
Tag
#Vision Models
Every The Latent Daily story, tool, model and resource tagged “Vision Models”.
2 items
Models tagged #Vision Models
OpenAIJan 5, 2021
CLIP ViT-L/14
OpenAI's contrastive image-text model that embeds images and text in a shared space, enabling zero-shot classification and image search.
- Type
- Vision
- Context
- —
- Weights
- Open