120 datasets found

iSAID dataset is a large-scale high-resolution remote sensing dataset for aerial instance segmentation, containing many small objects with complex backgrounds.

The CIFAR-100 dataset consists of 100 classes of 32 × 32 RGB images with 60,000 training and 10,000 testing examples.

The ImageNet-20 and ImageNet-100 datasets are used for zero-shot image classification tasks.

Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating...

The Caltech-UCSD Birds-200-2011 Dataset consists of 11,169 bird images from 200 categories and each category has 60 images averagely.

A synthetic toy dataset of square images of n = 4 pixels, where each pixel takes values between 0 and 255 in grayscale.

The VOC2012 dataset is a multi-label image recognition dataset. It contains 11,540 train-val images and 10,991 test images.

The Fashion MNIST dataset is a large dataset of fashion images, each image is a 28x28 grayscale image, and there are 60,000 training images, 10,000 validation images, and 10,000...

The dataset used in the paper is a large set of real images extracted from various object categories of the ImageNet, COCO, and Unpaired real dataset.

The Pinterest dataset.

The dataset used for the experiments on Twitter and Pinterest.

The DeepFace dataset is a large-scale face recognition dataset containing over 2 million images of faces.

The WikiArt dataset is a large-scale dataset of artworks, containing over 1 million images of paintings.

The VGGFace2 dataset is a large-scale face recognition dataset containing over 2 million images of faces.

The dataset used for image classification tasks, including ImageNet-1K, Food-101, Birds, and Dogs.

The Places dataset is a large-scale dataset for scene recognition, containing 1 million images from 365 categories.

The dataset used in this paper is the FashionMNIST dataset, which consists of 60,000 images of clothing items from 10 different classes.

Sub-ImageNet dataset consists of 60,000 training and 10,000 testing samples.

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.

MNIST dataset consists of 60,000 training and 10,000 testing samples, while SVHN consists of 73,257 training and 26,032 testing digital images.