160 datasets found

The dataset used in the paper is ImageNet32x32, a down-sampled version of ImageNet.

Brain tumor MRI dataset used for classification of brain tumors into Meningioma, Glioma, and Pituitary tumor

The dataset used in this paper is a malware dataset containing 10,896 malware files belonging to 9 different malware families.

Places205 is a dataset of 2.5 million images from 205 categories, with 12,000 images per category.

Chem2Bio2RDF dataset for biomedical entity classification task, containing 295,911 nodes and 727,997 edges

UC Merced Land Use Dataset (Yang & Newsam, 2010) contains remote sensing satellite images of 21 classes, with 100 images in each class.

The UEA archive is a collection of multivariate time series datasets where classification is of importance.

The UCR archive is a collection of univariate time series datasets where classification is of importance.

The Pavia University dataset was acquired by ROSIS airborne sensor over the University of Pavia, Italy, in 2003. The original HSI comprises 610×340 pixels and 115 spectral bands.

Electrocardiogram (ECG) dataset used for cardiac irregularity classification

The Stanford Online Products (SOP) dataset contains 120,053 product images covering 22,634 categories. The training set is composed of 59,551 images of the first 11,318...

Geometry Sharing Network (GS-Net) for 3D point cloud classification and segmentation

The dataset used in the paper for attention-oriented data analysis and attention-based adversarial defense.

Visual restoration and recognition are traditionally addressed in pipeline fashion, i.e. denoising followed by classification. Instead, observing correlations between the two...

The HAR dataset is a collection of physiological signals from human subjects.

The Stanford40 and HII datasets are used for image recognition. The Stanford40 dataset contains 40 action categories, while the HII dataset contains 10 action images.

The UCF101 and HMDB51 datasets are used for video recognition. The UCF101 dataset contains 101 action categories, while the HMDB51 dataset contains 51 classes.

A dataset of histopathological images for classification

A large DNN, containing 3 stacked modules. The segmentation module is an U-Net, trained beforehand to receive X-rays and output segmentation masks.

A large-scale food image segmentation dataset called FoodSeg103 (and its extension FoodSeg154) for fine-grained food image segmentation research.