660 datasets found

The dataset used for testing the proposed UGAN-P model, which consists of images of underwater scenes with and without distortion.

The dataset used in the paper is a modified version of the MNIST dataset, where each image is flipped horizontally or vertically, and the labels are changed accordingly.

The dataset used in this paper is the CIFAR-5m dataset, a collection of images of objects.

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers...

data extracted from real images of forged banknotes, with the help of an industrial camera.

The dataset used in the paper is the ImageNet 2012 dataset.

MiniImageNet, TieredImageNet, and CUB are used for few-shot learning tasks.

The MNIST-parity experiment uses the MNIST dataset to test the performance of a ReLU network and various linear models on the parity of a single MNIST image and the parity of...

XIMAGENET-12 is an explainable visual benchmark dataset for model robustness evaluation. It consists of over 200K images with 15,410 manual semantic annotations. The dataset is...

Typical deep neural network (DNN) backdoor at-

The Leeds Butterfly dataset is a fine-grained classification dataset used for testing the performance of the IBTM model on image classification tasks.

The ACE dataset is a large-scale dataset for image classification and object detection.

The INAT dataset is a large-scale dataset for image classification and object detection.

The MNIST dataset is a collection of images of handwritten digits, with size n = 70,000 and D = 784.

The CifarQuick model is a medium-sized convolutional neural network trained on the Cifar-10 dataset.

The dataset consists of 1000 images of 28x28 grayscale images of handwritten digits.

The Stanford CS229 dataset consists of 60,000 images of 28x28 grayscale images of handwritten digits.

miniImageNet, tieredImageNet, Caltech-USCD birds-200-2011

The dataset used in this paper is also Red Mini-ImageNet, which is a benchmark for evaluating the robustness of image classification models to label noise. It contains 50,000...

Fashion-MNIST, KMNIST and SVHN datasets used for benchmarking GANs