-
Colored MNIST dataset
The dataset used in the paper is a binary classification task in a 300-dimensional space. The procedure for generating the training dataset is as follows: Each label y ∈ {−1, 1}... -
ImageNet32x32
The dataset used in the paper is ImageNet32x32, a down-sampled version of ImageNet. -
Oxford Flower-102
Fine-grained image classification, which aims to recognize subordinate level categories, has emerged as a popular research area in the computer vision community. -
iNaturalist 2021-mini dataset
The iNaturalist 2021-mini dataset contains images of animals from 200 species. -
CUB dataset
The CUB dataset is a large collection of images of birds, each image is a 299x299 RGB image, and there are 11,778 training images and 5,994 testing images. -
Content-Aware Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution... -
Very Deep Convolutional Networks for Large-Scale Image Recognition
The dataset consists of 60,000 images of objects in 200 categories, with 300 images per category. -
MNIST and CIFAR-10
The MNIST dataset is a large dataset of handwritten digits, and the CIFAR-10 dataset is a dataset of images from 10 different classes. -
University of Houston
The University of Houston dataset is a hyperspectral image dataset acquired over the University of Houston campus and the neighboring urban area. -
Kennedy Space Center
A hyperspectral image dataset with 4 classes, captured over the Kennedy Space Center, FL, by the NASA AVIRIS instrument. -
Triplet-Watershed for Hyperspectral Image Classification
Hyperspectral images consist of rich spatial and spectral information, which can be used for several applications. However, noise, band correlations, and high dimensionality... -
CIFAR-10, CIFAR-100, and SVHN datasets
The dataset used in the paper is the CIFAR-10 and CIFAR-100 datasets, and the SVHN dataset. -
Masked Autoencoders Are Scalable Vision Learners
Masked autoencoders are scalable vision learners -
Masked convolution meets masked autoencoders
Masked convolution meets masked autoencoders -
Decision Support System for Detection and Classification of Skin Cancer using...
Skin Cancer detection and classification using CNN -
Classification Accuracy Score
Classification accuracy score (CAS) is a better proxy than FID and IS for performance of downstream training on generated data.
