660 datasets found

ImageNet-Subset is a subset of the ImageNet dataset, containing 100 classes with 500 training images, 50 validation images, and 50 test images per class.

The Stanford Online Products (SOP) dataset contains 120,053 product images covering 22,634 categories. The training set is composed of 59,551 images of the first 11,318...

ImageNet classification dataset, COCO dataset

The EyePACS dataset is a collection of retinal fundus images of individuals potentially suffering from diabetic retinopathy (DR), an eye disease associated with diabetes that is...

COVID-19 chest X-ray dataset is the largest open access benchmark dataset in terms of the number of COVID-19 positive patient cases.

The dataset used in the paper for attention-oriented data analysis and attention-based adversarial defense.

The proposed MG-ViT model is used for few-shot learning on the Agri-ImageNet and ACFR apple detection tasks.

The dataset is used for biomedical data and contains 30 input features computed from digitalized images of needle aspirates, with binary labels malignant/benign. The dataset is...

The dataset is used for biomedical data and contains 30 input features computed from digitalized images of needle aspirates, with binary labels malignant/benign.

Three-dimensional cine-MRI dataset for cardiac segmentation and classification

The dataset used in the paper is the MobileNetV2 dataset, which is a pre-trained deep neural network model.

The ImageNet400 dataset contains 400 images.

Augmented MNIST dataset with 1000 classes

The Grassy-MNIST dataset is a semi-synthetic dataset of hand-written digits from the MNIST dataset superimposed on images of grass from the ImageNet dataset.

WebVision-1000 is a large-scale web dataset for image classification, containing 2.4M noisy-labeled training images crawled from Flickr and Google.

Webly supervised learning (WSL) aims at training an optimal deep neural network Mθ from a dataset D = {(x1, y∗N )} collected from the Internet.

Generative adversarial nets (GANs) are a class of deep learning models that consist of two neural networks: a generator and a discriminator.

The Office-Home dataset is a visual domain adaptation task, where the goal is to adapt a model trained in a source domain to a target domain with different distributions.

ILSVRC 2012-2017 image classification and localization dataset used for cover image generation

AlexNet, VGG-16, and ResNet-18 datasets used for training and testing the Zero Activation Predictor (ZAP) model.