dinov2-giant is the largest model in the DINOv2 family of self-supervised vision transformers developed by Meta. It produces rich image embeddings suitable for a wide range of downstream computer vision tasks. The model is available through the Hugging Face Transformers library and is widely used in research and production for image understanding.
Dinov2 Giant is an Other AI product. It focuses on extracting high-quality, general-purpose visual features from images without task-specific supervision. Dinov2 Giant is an open-source project aimed at computer vision researchers and developers. The project is open source (Apache-2.0). The product ships for the web and API.
It is developed by Meta AI (United States), and the product first shipped in 2023. The project is developed in the open on GitHub with 13.1k stars and 1 commits in the last 90 days. Among its 3 catalogued features are self-supervised, feature extraction, and vision transformer.
Latest indexed changes and source events
facebook/dinov2-giant verified by the PulseGate indexer
