teemosliang/CAFE download history
teemosliang/CAFE is an image segmentation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 411 times (39 in the last 7 days), and 2,068 times in total. It ranks #52,962 among datasets by monthly downloads.
CAFE: Counterfactual Attribute Factuality Evaluation CAFE (Counterfactual Attribute Factuality Evaluation) is a benchmark for evaluating concept-faithful grounding in promptable segmentation models. Given a counterfactually edited image and a text prompt, a model must determine whethe
Open teemosliang/CAFE on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.