MNIST-C

The MNIST-C dataset is a comprehensive suite of different corruptions applied to the MNIST dataset, for benchmarking out-of-distribution robustness in computer vision.

Data and Resources

Cite this as

Zelin He, Ying Sun, Jingyuan Liu, Runze Li (2025). Dataset: MNIST-C. https://doi.org/10.57702/oo6wjeam

DOI retrieved: January 3, 2025

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.2404.01153
Citation
  • https://doi.org/10.48550/arXiv.2212.09000
Author Zelin He
More Authors
Ying Sun
Jingyuan Liu
Runze Li
Homepage https://arxiv.org/abs/2106.06291