-
MNIST and USPS
The MNIST and USPS datasets are used for binary classification tasks. -
CUB 200-2011
The CUB 200-2011 dataset contains 200 classes of bird species in 11,788 images with approximately 30 examples per class in the training set. -
CIFAR-10 and STL-10
The dataset used in the paper is CIFAR-10 and STL-10, which are commonly used datasets for image classification tasks. -
CIFAR-100 and ImageNet
The dataset used in the paper is CIFAR-100 and ImageNet. -
Fashion-Mnist
A binary imbalanced classification dataset with 28 × 28 grayscale images of 10 classes corresponding to fashion products. -
ImageNet-Dogs
The dataset used in the paper for image classification, object detection, and face verification tasks. -
ImageNet-10
ImageNet-10 is a dataset of 10,000 224x224 color images in 10 classes, with 1,000 images per class. -
CIFAR10 and CIFAR100 datasets
The CIFAR10 and CIFAR100 datasets are used to evaluate the proposed randomized defense method. -
CIFAR10 and ImageNet Datasets
CIFAR10 and ImageNet datasets are used as the original task for the pre-trained models. -
Dynamic Batch Norm Statistics Update for Natural Robustness
CIFAR10-C and ImageNet-C datasets are used to evaluate the proposed framework for improving the natural robustness of trained DNNs against corrupted inputs. -
Synthetic Data
The dataset used in the paper is a synthetic dataset for off-policy contextual bandits, with contexts x ∈ X, a finite set of actions A, and bounded real rewards r ∈ A → [0, 1]. -
ImageNet 2012 Large-Scale Visual Recognition Challenge
The dataset used in the paper is the ImageNet 2012 Large-Scale Visual Recognition Challenge dataset. -
OpenImages dataset
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the OpenImages dataset to train their models. -
ImageNet and CACD datasets
The dataset used in the paper is the ImageNet dataset for image classification and the CACD dataset for face identification. -
Jasmine and Basmati, and Arborio and Karacadag datasets
Two datasets for binary image classification: Jasmine and Basmati, and Arborio and Karacadag.