-
CobNet: Cross Attention on Object and Background
Few-shot segmentation aims to segment images containing objects from previously unseen classes using only a few annotated samples. -
FewCLUE dataset
The FewCLUE dataset is a Chinese few-shot learning evaluation benchmark. -
RL-CZSL-ATTR and RL-CZSL-ACT
Two large-scale benchmark datasets for reference-limited compositional zero-shot learning (RL-CZSL). -
Few-shot Name Entity Recognition on StackOverflow
Few-shot Name Entity Recognition on StackOverflow -
Putting nerf on a diet: Semantically consistent few-shot view synthesis
A dataset for training and testing semantically consistent few-shot view synthesis models -
Customized Image Editing
The dataset used in the paper for image editing tasks -
Jasmine and Basmati, and Arborio and Karacadag datasets
Two datasets for binary image classification: Jasmine and Basmati, and Arborio and Karacadag. -
ScanObjectNN
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...