160 datasets found

The NA-Birds dataset is larger than CUB200-2011, has 555 bird species, 23,929 training images and 24,633 test images.

The GTZAN dataset is a comprehensive collection of 1000 audio tracks, each 30 seconds long, representing ten diverse music genres.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used three tasks: single-modal and multi-modal image translations, and GAN...

A million event-stream classification dataset for spiking neural networks

The dataset used in this paper is the CIFAR10 dataset, which contains 60,000 32x32 color images in 10 classes, with 6,000 images per class.

The dataset used in this paper for 3D point cloud classification and semantic segmentation tasks.

Sentinel-2 sea ice classification dataset for training a deep learning model to classify polar sea ice as thick/snow-covered, young/thin, or open water.

UCR Time Series Archive is a collection of time series datasets from various domains. It is used for training and testing deep neural networks for time series classification tasks.

The UCR Time Series Classification Archive contains 168 datasets for time series classification.

The credit10 dataset is a subset of the open dataset GiveMeSomeCredit, containing 8429 examples in the training set and 3614 examples in the testing set, with each example...

The dataset used for the experiments of the paper "CORE-PERIPHERY PRINCIPLE GUIDED REDISIGN OF SELF-ATTENTION IN TRANSFORMERS"

The Physionet 2016 dataset is a collection of heart sound recordings used for heart sound classification.

University of Pavia is a popular benchmark dataset for semantic segmentation.

The Hospital expenditures dataset represents a binary classification task of predicting whether a person would have high or low utilization of medical expenditures.

The Hospital readmission dataset represents a binary classification task where label 1 means that patient is readmitted within 30 days.

The German credit dataset is a dataset used for classification tasks, and it contains sensitive attributes such as credit history.

The MIT-BIH dataset contains 48 hours of two-channel ambulatory ECG signals obtained from 47 subjects.

The dataset used in the paper is the Adult dataset and the Hospital Readmission dataset.

Caltech-UCSD Birds (CUB) dataset is a dataset of bird images.

The ISIC 2017 skin lesion classification dataset contains 2000 training, 150 validation, and 600 test images.