72 datasets found

The MNIST and FashionMNIST datasets are used to test the performance of the proposed generative autoencoders.

Reduced MNIST dataset of 6000 images

One domain consists of the original MNIST digits, while the other is generated by applying multiple transformations including rotation, downscaling, and Gaussian blurring.

The MNIST, USPS, and SVHN datasets are digit datasets used for domain adaptation tasks.

The dataset used for MNIST and Fashion MNIST binary classification tasks

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.

The MNIST dataset is used for image classification, and the Lending Club Loan dataset is used for tabular data.

The dataset used in this paper is MNIST, USPS, and CIFAR10. The dataset is used for privacy-preserving CNN training.

Three public datasets were employed throughout the experiments: MNIST, Fashion-MNIST, and Kuzushiji-MNIST.

FashionMNIST and MNIST datasets are used for continual unsupervised learning with variational autoencoders and generative replay.

The dataset contains 30 multi-instance classification datasets generated from the MNIST, FashionMNIST, and KuzushijiMNIST datasets.

The MNIST, Fashion-MNIST, CIFAR-10, and CelebA datasets are used for image data.

We use the preprocessed binarized MNIST dataset from [49] which has a split of 50k/10k/10k.

The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions.

The MNIST and USPS datasets are used for binary classification tasks.

The MNIST Digit Swap Task dataset consists of 64 × 64 images of handwritten digits, where 0s are placed on the left and 1s are placed on the right, or vice versa.

The MNIST handwritten digit database is a dataset of 60,000 8x8 grayscale images of handwritten digits.

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

A dataset of stochastic moving MNIST, consisting of sequences of 15 frames of size 64x64.

The dataset used in this paper is a synthetic dataset with a nonlinear response, where the response is learned by means of a neural network trained to count numbers in synthetic...