8 datasets found

Few-shot part segmentation for 3D shapes

miniImageNet, tieredImageNet, Caltech-USCD birds-200-2011

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the Mini-Imagenet and CIFAR-FS datasets for few-shot learning tasks.

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...

The CIFAR-FS dataset is a few-shot learning dataset, consisting of 60,000 color images from 100 classes with 600 examples per class.

Few-shot semantic segmentation via prototype augmentation with image-level annotations

PartImageNet and Pascal Part datasets for few-shot part segmentation.

Few-shot part segmentation using few-shot support images and pre-trained image-language model CLIP.