23 datasets found

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

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.

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

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

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 proposed MG-ViT model is used for few-shot learning on the Agri-ImageNet and ACFR apple detection tasks.

The MiniVSPW dataset is a benchmark for few-shot video object segmentation.

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

A dataset of datasets for learning to learn from few examples.

MiniImageNet, Caltech-UCSD Birds 200-2011, TieredImageNet, OfficeHome

This dataset is used for few-shot novel view synthesis.

The MiniImagenet dataset is a benchmark for few-shot learning, consisting of 60,000 images from 21 classes, each with 300 images.