492 datasets found

The dataset used in the paper is CIFAR-10, CIFAR-100, and Tiny-Imagenet.

The dataset used in the paper is a subset of the Caltech Silhouettes database, consisting of 11 images with 42 to 59 pixels in each class.

The Oxford 102 Category Flower dataset consists of 8,189 images with 102 categories of flowers which commonly occurs in the United Kingdom, and each category has 40 to 258 images.

The dataset used in the paper is a classification dataset, specifically CIFAR-100 and CUB200.

The RESISC-45 dataset is a benchmark for remote sensing image classification.

The CIFAR-10 and Tiny ImageNet datasets are used to evaluate the robustness of the proposed defense method.

The dataset used in the paper is the ImageNet-2k dataset, a large dataset for image classification.

The COIL100 dataset is a benchmark dataset for object recognition and image classification.

The VOC2007 dataset is a benchmark dataset for object recognition and image classification.

The MNIST-1D dataset is a 1-dimensional version of the classic MNIST handwritten digits dataset.

Foods dataset

The dataset used in the paper is a hierarchical concept representation task, where the goal is to predict is-a relationships between concepts.

The dataset used for the Drawing out of Distribution (DooD) model, which consists of stroke-based images of handwritten Japanese characters.

The EMNIST-letters dataset is a collection of handwritten letter images, each labeled with its corresponding letter.

The EMNIST-digits dataset is a collection of handwritten digit images, each labeled with its corresponding digit value.

MRI images of pancreas for IPMN classification

CIFAR-10-C and CIFAR-100-C are robustness benchmarks consisting of 19 corruptions types with five levels of severities.

Pascal VOC 2007 and 2012 datasets for object detection

The Open Image Dataset (OID) is a large-scale image dataset that contains a diverse set of images.

The Office-10 dataset is a more classic benchmark dataset from [17].