Fare4 Clip

🚀 Open Clip - FARE CLIP ViT-L/14

This is a FARE CLIP ViT-L/14 model. It undergoes unsupervised adversarial fine - tuning from Openai CLIP initialization on ImageNet with infinity - norm and radius 4/255.

🚀 Quick Start

This FARE CLIP ViT-L/14 model is initialized from Openai CLIP and fine - tuned on ImageNet with specific parameters.

💻 Usage Examples

Basic Usage

model, _, image_processor = open_clip.create_model_and_transforms('hf-hub:chs20/fare4-clip')

📄 License

This project is licensed under the MIT license.

📚 Documentation

[Paper] [GitHub]

📚 Citation

If you find this model useful, please consider citing our paper:

@article{schlarmann2024robustclip,
    title={Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models}, 
    author={Christian Schlarmann and Naman Deep Singh and Francesco Croce and Matthias Hein},
    year={2024},
    journal={ICML}
}