40 datasets found

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.

A dataset for few-shot font generation with dual memory.

Temporal Action Localization (TAL) in few-shot learning. Our work addresses the inherent limitations of conventional single-prompt learning methods that often lead to...

A benchmark dataset for few-shot image-to-image translation

Birds dataset consists of 28752 images of birds, each described by a Fisher vector representation.

A benchmark dataset for few-shot image-to-image translation

A benchmark dataset for few-shot image-to-image translation

Few-shot unsupervised image-to-image translation with a content conditioned style encoder