5 datasets found

The FewCLUE dataset is a Chinese few-shot learning evaluation benchmark.

Few-shot Name Entity Recognition on StackOverflow

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature...

A dataset for training and testing semantically consistent few-shot view synthesis models

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen...