robustified CLIP ViT-L/14@336px using hcaptcha masks (geometric image overlays) on visual-layer/imagenet-1k-vl-enriched.
for source code and example usage see: https://github.com/ETH-DISCO/advx-bench
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.