Downloads · 30 days
660
3% of all-time downloads
tecoa2-clip
chs20/tecoa2-clip
tecoa2-clip is a zero-shot image classification model from chs20. Use it for the zero-shot image classification task on the model card, and read the license before you ship it in a product. It is set up for open_clip. The card lists the license as mit.
[[Paper]](https://arxiv.org/abs/2402.12336) [[GitHub]](https://github.com/chs20/RobustVLM)
All-time downloads
22.5K
Public
Repo size
1.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin1.7 GB · 100%
At a glance
- Task
- Zero-Shot Image Classification
- Library
- open_clip
- License
- mit
- Access
- Public
- Created
- Feb 23, 2024
- Updated
- Jun 16, 2024
- SHA
- 8e043fb9
Model card
From the Hugging Face model README
TeCoA (Mao et al. (2023)) CLIP ViT-L/14 model.
Supervised adversarial fine-tuning from Openai CLIP initialization on ImageNet with infinity-norm and radius 2/255.
Usage
model, _, image_processor = open_clip.create_model_and_transforms('hf-hub:chs20/tecoa2-clip')
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}
}
- Task
- Zero-Shot Image Classification
- Library
- open_clip
- License
- mit
- Created
- Feb 23, 2024
- Updated
- Jun 16, 2024