permutation invariant MNIST

Permutation invariant MNIST is a dataset that contains images of handwritten digits where the order of the pixels is irrelevant, and it is used to evaluate the performance of generative models and their ability to generalize in tasks like classification.

Papers using permutation invariant MNIST (1)

Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation2020 · 7 cites