47 datasets found

HuffPost dataset for few-shot text classification, consisting of news headlines published in HuffPost between 2012 and 2018.

Aspect Category Detection (ACD) dataset for few-shot one-class ACD is collected from Yel-pAspect (Bauman et al., 2017; Li et al., 2019), which is a large-scale multi-domain...

Few shot learning framework to reduce inter-observer variability in medical images

The MVTec and VisA datasets are used for few-shot anomaly detection.

The CANet dataset is a benchmark for few-shot semantic segmentation.

The PANet dataset is a benchmark for few-shot semantic segmentation.

The proposed Semantic Meta-Learning (SML) framework for few-shot semantic segmentation.

Few-shot keyword spotting with prototypical networks.

Few-shot part segmentation for 3D shapes

Few-shot learning aims to generalize unseen classes that appear during testing but are unavailable during training. The performance of prototypical networks in extreme few-shot...

Visual discrimination puzzles dataset created for few-shot learning problems

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

Colored-Kuzushiji is used for few-shot classification tasks.

The UT-Zappos50K dataset is a fine-grained shoe catalog, characterized by its smaller scale and relatively stable and simple content.

MiniImageNet, TieredImageNet, and CUB are used for few-shot learning tasks.

Few-shot Name Entity Recognition on StackOverflow

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

The proposed method Memory-Augmented Relation Network (MRN) for few-shot learning.

Few-shot segmentation targets to segment new classes with few annotated images provided. It is more challenging than traditional semantic segmentation tasks that segment known...

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.