Common corruptions and perturbations for evaluating robustness

Common corruptions and perturbations are used to evaluate the robustness of neural networks.

Data and Resources

Cite this as

Hendrycks and Dietterich (2024). Dataset: Common corruptions and perturbations for evaluating robustness. https://doi.org/10.57702/ocxymtff

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Hendrycks and Dietterich
Homepage https://arxiv.org/abs/1905.12132