13 datasets found

Few-shot segmentation aims to segment images containing objects from previously unseen classes using only a few annotated samples.

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

Two large-scale benchmark datasets for reference-limited compositional zero-shot learning (RL-CZSL).

Intent detection dataset for few-shot learning

Intent detection dataset for few-shot learning

Intent detection dataset for few-shot learning

Few-shot Name Entity Recognition on StackOverflow

The Banking77 dataset is a specialized dataset for intent classification in the banking domain.

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

The dataset used in the paper for image editing tasks

Two datasets for binary image classification: Jasmine and Basmati, and Arborio and Karacadag.

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...