CIFAR100, ImageNet100, and ImageNet

The dataset used in the paper is CIFAR100, ImageNet100, and ImageNet. CIFAR100 consists of 100 object classes and 60,000 images. ImageNet100 has 100 object classes and 60,000 color images of size 84×84. ImageNet is a 1,000-class dataset from ILSVRC2012, providing 1.2 million images for training and 50,000 images for validation.

BibTex: