18 datasets found

Few-shot sound event detection.

Few-shot bioacoustic event detection at the DCASE 2022 challenge.

Few-shot keyword spotting with prototypical networks.

KWS-DailyTalk is a five-shot KWS dataset aimed at detecting 15 different keywords, namely “afternoon”, “airport”, “cash”, “credit card”, “deposit”, “dollar”, “evening”,...

Stance detection aims to identify whether the author of a text is in favor of, against, or neutral to a given target. The main challenge of this task comes two-fold: few-shot...

A framework for gesture customization requiring minimal examples from users, all without degrading the performance of existing gesture sets.

The dataset for calligraphy character classification, including 200 ancient calligraphers and their corresponding calligraphy categories.

A new approach to meta-learning, called meta-meta classification, to learning in small-data settings.

The FewSol dataset is used for training the class-adaptive object detector. It contains 666 objects with a large number of occurrences.

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

The dataset provided for the two tasks consists of 10 different cities from around the world over the course of 2 years. The cities have been split into 3 categories: Core...

A language model that demonstrates capabilities in processing and generating human-like text.

The dataset used for medical image anomaly detection, focusing on few-shot learning and anomaly synthesis.

Few-shot image classification is the task of classifying unseen images to one of N mutually exclusive classes, using only a small number of training examples for each class.

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

The BUSI dataset is a collection of ultrasound images depicting normal, benign, and malignant breast cancer cases along with their corresponding segmentation maps.

The Human Connectome Project (HCP) dataset contains volumetric task fMRI activation maps from the Human Connectome Project 1200 dataset (HCP1200) distribution, for the 965...

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...