660 datasets found

The dataset used in this paper is the ResNet-20 and ResNet-32 datasets, which are variants of the ResNet-50 model.

The dataset used in this paper is the Imagenette and Imagewoof datasets.

The dataset used in the paper is ResNet-20, ResNet-32, ResNet-56, and ResNet-110 for image classification.

The dataset used in the paper is CIFAR-10 and CIFAR-100 for image classification, and CelebA for image-to-image translation.

FloodNet is a high-resolution image dataset acquired by a small UAV platform, DJI Mavic Pro quadcopters, after Hurricane Harvey.

The WideResNet-28-10 and WideResNet-34-2 datasets are used to evaluate the performance of the proposed two-level group convolution.

The dataset used in the paper is the ResNet-50 dataset, a convolutional neural network model.

The Traffic Signs dataset contains 39252 training images in 43 classes.

The dataset used in the paper is CIFAR10-DVS, a dataset of 10,000 event streams of 128x128 images.

The dataset used in the paper is the CIFAR-10 and SVHN datasets. CIFAR-10 is a dataset of 32x32 color images in 10 classes, while SVHN is a dataset of 32x32 color images of...

The MiniImagenet dataset is a benchmark for few-shot learning, consisting of 60,000 images from 21 classes, each with 300 images.

The dataset used in the paper is subImageNet, a subset of ImageNet.

The COIL-DEL dataset contains 3900 graphs which are converted from images by the Harris corner detection algorithm and Delaunay triangulation.

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 BlockMNIST dataset is a variation of the MNIST dataset with additional objects in the background.

The dataset used in the paper is a collection of images from various sources, including MNIST, EMNIST, CIFAR10, X-ray pneumonia, and Diabetic Retinopathy detection.

The dataset used in the paper is the AlexNet dataset, which contains 60,000 32x32 color images in 10 classes, with 6,000 images per class.

The dataset used for evaluation of the proposed method. It contains images of humans and faces, with pre-annotated bounding boxes for persons and faces.

The Caltech-UCSD-Birds-200-2011 dataset contains images of 200 bird species.