metadata
license: mit
library_name: open_clip
pipeline_tag: zero-shot-image-classification
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 Induce Better (Robust) Perceptual Metrics},
author={Croce, Francesco and Schlarmann, Christian and Singh, Naman Deep and Hein, Matthias},
year={2024},
booktitle={{ICML Workshop on Foundation Models in the Wild}}
}
@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}}
}