Dinov2 Large

🚀 Vision Transformer (large-sized model) trained using DINOv2

This is a Vision Transformer (ViT) model trained with the DINOv2 method, offering powerful feature extraction capabilities for vision tasks.

🚀 Quick Start

The Vision Transformer (ViT) is a transformer encoder model (similar to BERT) that has been self - supervised pretrained on a large set of images. You can use the raw model for feature extraction. Check the model hub to find fine - tuned versions for tasks that interest you.

✨ Features

• Self - supervised Pretraining: The model is pretrained in a self - supervised manner on a large image collection, enabling it to learn robust visual features without explicit labels.
• Feature Extraction: It can be used for extracting features from raw images, which can then be utilized for various downstream tasks.
• Flexibility: You can train a standard classifier by adding a linear layer on top of the pre - trained encoder for specific tasks.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoImageProcessor, AutoModel
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

processor = AutoImageProcessor.from_pretrained('facebook/dinov2-large')
model = AutoModel.from_pretrained('facebook/dinov2-large')

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
last_hidden_states = outputs.last_hidden_state

📚 Documentation

Model description

The Vision Transformer (ViT) is a transformer encoder model (BERT - like) pretrained on a large collection of images in a self - supervised fashion.

Images are presented to the model as a sequence of fixed - size patches, which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.

Note that this model does not include any fine - tuned heads.

By pre - training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre - trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image.

Intended uses & limitations

You can use the raw model for feature extraction. See the model hub to look for fine - tuned versions on a task that interests you.

BibTeX entry and citation info

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

📄 License

This model is released under the Apache 2.0 license.