facebook / dinov2-with-registers-base

Vision Transformer (base-sized model) trained using DINOv2, with registers

Vision Transformer (ViT) model introduced in the paper Vision Transformers Need Registers by Darcet et al. and first released in this repository .

Disclaimer: The team releasing DINOv2 with registers did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) originally introduced to do supervised image classification on ImageNet.

Next, people figured out ways to make ViT work really well on self-supervised image feature extraction (i.e. learning meaningful features, also called embeddings) on images without requiring any labels. Some example papers here include DINOv2 and MAE .

The authors of DINOv2 noticed that ViTs have artifacts in attention maps. It’s due to the model using some image patches as “registers”. The authors propose a fix: just add some new tokens (called "register" tokens), which you only use during pre-training (and throw away afterwards). This results in:

• no artifacts
• interpretable attention maps
• and improved performances.

Visualization of attention maps of various models trained with vs. without registers. Taken from the original paper .

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.

How to use

Here is how to use this model:

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-with-registers-base')
model = AutoModel.from_pretrained('facebook/dinov2-with-registers-base')

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

BibTeX entry and citation info

@misc{darcet2024visiontransformersneedregisters,
      title={Vision Transformers Need Registers}, 
      author={Timothée Darcet and Maxime Oquab and Julien Mairal and Piotr Bojanowski},
      year={2024},
      eprint={2309.16588},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2309.16588}, 
}