README.md

---
base_model:
- facebook/dinov2-base
library_name: transformers
license: mit
tags:
- dino
- vision
---
[[Paper]](https://openreview.net/forum?id=e3scLKNiNg&noteId=e3scLKNiNg) [[GitHub]](https://github.com/fra31/perceptual-metrics)

Robust perceptual metric, based on DINO model `facebook/dinov2-base`.
Adversarially fine-tuned with FARE ([Schlarmann et al. (2024)](https://arxiv.org/abs/2402.12336)) on ImageNet with infinity-norm and radius 4/255.

## Usage
```python
preprocessor = transforms.Compose([
                transforms.Resize(256, interpolation=3),
                transforms.CenterCrop(224),
                transforms.ToTensor(),
                transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
            ])
model = AutoModel.from_pretrained("ch20/dinov2-base-fare4")
```

## Citation
If you find this model useful, please consider citing our papers:
```bibtex
@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}}
}
```

```bibtex
@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}}
}
```