CC-3M
Emerging1papers using it
2025first seen
The 'CC3M' dataset contains a large collection of image-text pairs used to evaluate the robustness of contrastive language-image pretraining models like CLIP against backdoor attacks.
The 'CC3M' dataset contains a large collection of image-text pairs used to evaluate the robustness of contrastive language-image pretraining models like CLIP against backdoor attacks.