Dynamic Batch Norm Statistics Update for Natural Robustness

doi:doi:10.57702/ijlrj58x

Dynamic Batch Norm Statistics Update for Natural Robustness

CIFAR10-C and ImageNet-C datasets are used to evaluate the proposed framework for improving the natural robustness of trained DNNs against corrupted inputs.

Data and Resources

Original MetadataJSON
The json representation of the dataset with its distributions based on DCAT.
Explore
- Preview
- Download

Cite this as

Shahbaz Rezaei, Mohammad Sadegh Norouzzadeh (2024). Dataset: Dynamic Batch Norm Statistics Update for Natural Robustness. https://doi.org/10.57702/ijlrj58x

DOI retrieved: December 2, 2024

Additional Info

Field	Value
Created	December 2, 2024
Last update	December 2, 2024
Defined In	https://doi.org/10.48550/arXiv.2310.20649
Author	Shahbaz Rezaei
More Authors	Mohammad Sadegh Norouzzadeh
Homepage	https://arxiv.org/abs/2103.09641