Dinov2.giant.patch 14

🚀 DINOv2 giant

This is an image feature extraction model based on the adapter of the facebook/dinov2 - giant base model, which can extract robust visual features without supervision.

🚀 Quick Start

There is no specific quick - start content in the original document.

✨ Features

• It belongs to the DINO and DINOv2 series, which can extract image features.
• It is an adapter of the facebook/dinov2 - giant base model.
• The library used is refiners.

📦 Installation

There is no installation step content in the original document.

💻 Usage Examples

There is no code example content in the original document.

📚 Documentation

There is no detailed documentation content in the original document.

🔧 Technical Details

There is no technical implementation details content in the original document.

📄 License

This project is licensed under the Apache - 2.0 license.

📚 Citation

@misc{oquab2023dinov2,
  title   = {DINOv2: Learning Robust Visual Features without Supervision},
  author  = {Oquab, Maxime and Darcet, Timothée and Moutakanni, Theo and Vo, Huy V. and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and Howes, Russell and Huang, Po-Yao and Xu, Hu and Sharma, Vasu and Li, Shang-Wen and Galuba, Wojciech and Rabbat, Mike and Assran, Mido and Ballas, Nicolas and Synnaeve, Gabriel and Misra, Ishan and Jegou, Herve and Mairal, Julien and Labatut, Patrick and Joulin, Armand and Bojanowski, Piotr},
  journal = {arXiv:2304.07193},
  year    = {2023}
}