Vitreg4 B16 Mim

🚀 vit_reg4_b16_mim

A ViT reg4 image encoder pre - trained using Masked Image Modeling (MIM), suitable as a general - purpose feature extractor or backbone for downstream tasks.

🚀 Quick Start

This is a ViT reg4 image encoder pre - trained with Masked Image Modeling (MIM). It has not been fine - tuned for specific classification tasks and can be used as a general - purpose feature extractor or a backbone for downstream tasks such as object detection, segmentation, or custom classification.

✨ Features

• General - Purpose Use: Can be used as a feature extractor or backbone for various downstream tasks.
• Diverse Training Data: Trained on a large and diverse dataset of about 11M images.

📦 Installation

The README does not provide installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

import torch
import birder
from PIL import Image

(net, model_info) = birder.load_pretrained_model("vit_reg4_b16_mim_300", inference=True)

# Get the image size the model was trained on
size = birder.get_size_from_signature(model_info.signature)

# Create an inference transform
transform = birder.classification_transform(size, model_info.rgb_stats)

image = Image.open("path/to/image.jpeg")
input_tensor = transform(image).unsqueeze(dim=0)
with torch.inference_mode():
    embedding = net.embedding(input_tensor)
    # embedding is a tensor with shape of (1, 768)

Advanced Usage

import torch
import birder
from PIL import Image

# Must first download the model files
(net, cfg) = birder.load_model_with_cfg("models/vit_reg4_b16_mim.json", "models/vit_reg4_b16_mim_300.pt")
net.eval()

# Get the image size the model was trained on
size = birder.get_size_from_signature(cfg["signature"])

# Create an inference transform
transform = birder.classification_transform(size, cfg["rgb_stats"])

image = Image.open("path/to/image.jpeg")
input_tensor = transform(image).unsqueeze(dim=0)
with torch.inference_mode():
    embedding = net.embedding(input_tensor)
    # embedding is a tensor with shape of (1, embedding_size)

📚 Documentation

Model Details

📄 License

This model is licensed under the Apache - 2.0 license.

🔧 Technical Details

The README does not provide detailed technical implementation information, so this section is skipped.

📖 Citation

@misc{dosovitskiy2021imageworth16x16words,
      title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale}, 
      author={Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby},
      year={2021},
      eprint={2010.11929},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2010.11929}, 
}

@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}, 
}

@misc{he2021maskedautoencodersscalablevision,
      title={Masked Autoencoders Are Scalable Vision Learners}, 
      author={Kaiming He and Xinlei Chen and Saining Xie and Yanghao Li and Piotr Dollár and Ross Girshick},
      year={2021},
      eprint={2111.06377},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2111.06377}, 
}