31 datasets found

The CIFAR10 and CIFAR100 datasets are used to evaluate the proposed randomized defense method.

CIFAR10 and ImageNet datasets are used as the original task for the pre-trained models.

The dataset used in this paper is CIFAR10/100, ImageNet, and CUB-200.

The MNIST and CIFAR10 datasets are used to evaluate the proposed Adversarial Training with Transferable Adversarial Examples (ATTA) method.

Out-of-distribution (OOD) detection is a crucial task for ensuring the reliability and safety of deep learning. The dataset used in this paper is CIFAR10, CIFAR100, and ImageNet.

The dataset used in the paper is CIFAR10 and CelebA 64x64.

The CIFAR10 and MNIST datasets are used for image classification tasks.

The dataset used in this paper is a spiking neural network dataset.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors conducted experiments on various vision tasks, including image classification,...

The MNIST and CIFAR10 datasets are used to evaluate the Cycle-Consistent Adversarial GAN (CycleAdvGAN) for image classification.

Network calibration aims to accurately estimate the level of confidences, which is particularly important for employing deep neural networks in real-world systems.