-
Describable Textures Dataset (DTD)
The dataset used in the paper is Describable Textures Dataset (DTD), which is a texture classification dataset. -
Image Perturbation Dataset
The dataset used in the paper is a collection of images with perturbations, where participants are asked to identify when an image becomes just noticeably different from the... -
MIT Places
MIT Places dataset, a dataset of images of places. -
iNaturalist 2018 dataset
The dataset used in the paper is the iNaturalist 2018 dataset, which is a real-world large-scale imbalanced dataset. -
TNCD: Thyroid Nodule Classification Dataset
Thyroid Nodule Classification Dataset (TNCD) is a benchmark for thyroid nodule diagnosis, containing 3493 ultrasound images taken from 2421 patients. -
CIFAR-10 and GIST1M datasets
The dataset used in this paper is CIFAR-10 and GIST1M. -
E-MNIST dataset
The E-MNIST dataset is a large dataset of handwritten digits, each image is 28x28 pixels and consists of 47 classes (0-9 and letters). -
K-MNIST dataset
The K-MNIST dataset is a large dataset of handwritten digits, each image is 28x28 pixels and consists of 10 classes (0-9). -
MNIST and MIMIC-CXR-JPG datasets
The MNIST dataset is a large dataset of handwritten digits, and the MIMIC-CXR-JPG dataset is a large dataset of chest x-ray images. -
CIFAR-10 and Caltech-256
The dataset used in the paper is CIFAR-10 and Caltech-256. -
CIFAR10-LT
CIFAR10-LT: a long-tailed version of the CIFAR-10 dataset, where the training images are randomly removed class-wise to follow a pre-defined imbalance ratio. -
MNIST-Scale-Local-2 dataset
The MNIST-Scale-Local-2 dataset is created to test the performance of the proposed method on local scale variations. -
MNIST-Scale and FMNIST-Scale datasets
The MNIST-Scale and FMNIST-Scale datasets are used to evaluate the performance of the proposed scale-steerable CNN framework. -
MNIST and SVHN datasets for incomplete image processing
We investigate the problem of training neural networks from incomplete images without replacing missing values. -
edges2shoes
A dataset of 10 simple object classes (pineapple, soccer, basketball, etc.) with white backgrounds. -
Deep Neural Networks for Pattern Recognition
The dataset used for training and testing the conditional generative adversarial networks for pattern recognition. -
CIFAR10 and ResNet32
The dataset used in the paper is CIFAR10 and ResNet32.
