FARE4-ViT-B-16-laion2B-s34B-b88K

[Paper] [GitHub]

Robust perceptual metric, based on CLIP model laion/CLIP-ViT-B-16-laion2B-s34B-b88K

Adversarially fine-tuned with FARE (Schlarmann et al. (2024)) on ImageNet with infinity-norm and radius 4/255.

Performance on the perceptual similarity task NIGHTS:

Clean     L-inf, eps=4/255     L2, eps=3
90.6      71.5                 65.5

Usage

model, _, image_processor = open_clip.create_model_and_transforms('hf-hub:chs20/FARE4-ViT-B-16-laion2B-s34B-b88K')

Citation

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

@inproceedings{croce2024adversarially,
  title={Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics},
  author={Croce, Francesco and Schlarmann, Christian and Singh, Naman Deep and Hein, Matthias},
  year={2025},
  booktitle={{SaTML}}
}

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