-
MNIST, CIFAR10, and UDIS-D datasets
The MNIST and CIFAR10 datasets are used for image classification, while the UDIS-D dataset is used for image reconstruction. -
iNaturalist and ImageNet datasets
The dataset used for evaluating the Variable Length Embeddings (VLE) model, consisting of a mix of the iNaturalist and ImageNet datasets. -
Places dataset
The Places dataset is a large-scale dataset for scene recognition, containing 1 million images from 365 categories.
