716 datasets found

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a combination of datasets from the scikit-learn library and the UCI machine...

The gisette dataset is a collection of 20,000 text documents, each containing a single sentence.

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.

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

The dataset used in this paper is not explicitly described. However, it is mentioned that the authors used datasets such as ImageNet and YouTube-8M.

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

The MNIST-scale dataset is a dataset of images of handwritten digits, where each image is scaled to a different size.

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

99 images of benign and malignant thyroid nodules for classification

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

The ImageCLEF-DA1 dataset is also a benchmark dataset for domain adaptation, which contains 12 categories shared by three public datasets, Caltech- 256 (C), ImageNet ILSVRC 2012...

The Office-31 dataset is a standard benchmark for domain adaptation from [16], comprising 4,652 images and 31 categories collected from three distinct domains: Amazon (A), Webcam...

The proposed method is evaluated on a toy example problem of sequence counting followed by MNIST classification problem.