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 isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.