-
ImageNet22K
The ImageNet22K dataset contains 14 million images representing 21,841 categories organized in a hierarchy derived from WordNet and including top level concepts such as sport,... -
DenseNet-40
The dataset used in the paper is DenseNet-40, which is a variant of the DenseNet architecture. -
Multi-scale order-less pooling (MOP) dataset
The dataset is used for multi-scale order-less pooling (MOP) experiments. -
CIFAR-10C, CIFAR-100C, and ImageNetC
The dataset used in this paper is CIFAR-10C, CIFAR-100C, and ImageNetC. -
Reduced MNIST
Reduced MNIST dataset of 6000 images -
Dogs dataset
The Dogs dataset contains 10,400 training and 2,600 test images of dogs. -
ImageNet, COCO, and Unpaired real dataset
The dataset used in the paper is a large set of real images extracted from various object categories of the ImageNet, COCO, and Unpaired real dataset. -
Mixup: Beyond empirical risk minimization
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used CIFAR-10, CIFAR-100, ImageNet, CUB-200-2011, and Stanford Dogs datasets. -
SelectAugment
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used CIFAR-10, CIFAR-100, ImageNet, CUB-200-2011, and Stanford Dogs datasets. -
iNaturalist-18/19
The dataset used in the paper is iNaturalist-18/19, a dataset for object detection and image classification. -
iNaturalist 2018 and iNaturalist 2019
The dataset used in the paper is iNaturalist 2018 and iNaturalist 2019, two datasets for object detection and image classification. -
FGVC Aircraft
The FGVC Aircraft dataset is a dataset of images of aircraft, where each image is classified into one of 100 categories. -
Pinterest dataset
The Pinterest dataset. -
Twitter and Pinterest dataset
The dataset used for the experiments on Twitter and Pinterest. -
AlexNet dataset
The AlexNet dataset is used to test the proposed systematic weight pruning framework. -
LeNet-5 dataset
The LeNet-5 dataset is used to test the proposed systematic weight pruning framework. -
CIFAR-10, CIFAR-100, SVHN
The dataset used in the paper is CIFAR-10 and CIFAR-100, which are two popular image classification datasets. SVHN is also used. -
CIFAR-10-C
CIFAR-10-C is a dataset of 60,000 32x32 color images in 10 classes, with 6,000 images per class, and 10% of the images are corrupted. -
Places2 Dataset
The Places2 dataset is a dataset of images of places.