Dino Vitb16

🚀 Vision Transformer (base-sized model, patch size 16) trained using DINO

A Vision Transformer (ViT) model trained with the DINO method, offering powerful feature extraction for image-related tasks.

🚀 Quick Start

The Vision Transformer (ViT) is a transformer encoder model (similar to BERT) that has been self - supervised pre - trained on a large set of images, specifically ImageNet - 1k, at a resolution of 224x224 pixels.

✨ Features

• Self - Supervised Learning: Trained in a self - supervised manner on ImageNet - 1k, enabling it to learn rich image representations.
• Patch - Based Input: Images are processed as a sequence of fixed - size patches (16x16), which are linearly embedded.
• [CLS] Token for Classification: A [CLS] token is added at the start of the sequence for classification tasks.
• Absolute Position Embeddings: Absolute position embeddings are added before feeding the sequence into the Transformer encoder layers.
• Feature Extraction: Can be used to extract features for downstream tasks by placing a linear layer on top of the pre - trained encoder.

📦 Installation

No specific installation steps are provided in the original README. However, to use the model, you need to have the transformers library installed. You can install it using the following command:

pip install transformers

💻 Usage Examples

Basic Usage

from transformers import ViTImageProcessor, ViTModel
from PIL import Image
import requests

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

processor = ViTImageProcessor.from_pretrained('facebook/dino-vitb16')
model = ViTModel.from_pretrained('facebook/dino-vitb16')

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, namely ImageNet - 1k, at a resolution of 224x224 pixels.

Images are presented to the model as a sequence of fixed - size patches (resolution 16x16), 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 image classification. See the model hub to look for fine - tuned versions on a task that interests you.

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-2104-14294,
  author    = {Mathilde Caron and
               Hugo Touvron and
               Ishan Misra and
               Herv{\'{e}} J{\'{e}}gou and
               Julien Mairal and
               Piotr Bojanowski and
               Armand Joulin},
  title     = {Emerging Properties in Self-Supervised Vision Transformers},
  journal   = {CoRR},
  volume    = {abs/2104.14294},
  year      = {2021},
  url       = {https://arxiv.org/abs/2104.14294},
  archivePrefix = {arXiv},
  eprint    = {2104.14294},
  timestamp = {Tue, 04 May 2021 15:12:43 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2104-14294.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

📄 License

This model is released under the Apache - 2.0 license.

⚠️ Important Note

The team releasing DINO did not write a model card for this model so this model card has been written by the Hugging Face team.