Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

This repository contains the datasets and some code for the paper Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (ICLR 2019) by Dan Hendrycks and Thomas Dietterich.

Requires Python 3+ and PyTorch 0.3+.

ImageNet-C Leaderboard

ImageNet-C Robustness with a ResNet-50 Backbone

Method	Reference	mCE
Stylized ImageNet Data Augmentation	Geirhos et al. (ICLR 2019)	69.3%
ResNet-50 Baseline		76.7%

Other backbones can obtain better results. For example, a vanilla ResNeXt-101 has an mCE of 62.2%.

Submit a pull request if you beat the state-of-the-art on ImageNet-C.

ImageNet-C

Download Tiny ImageNet-C here. (Mirror.)

Download ImageNet-C here. (Mirror.)

Tiny ImageNet-C has 200 classes with images of size 64x64, while ImageNet-C has all 1000 classes where each image is the standard size. For even quicker experimentation, there is CIFAR-10-C, but improvements on CIFAR-10-C may be much less indicative of ImageNet-C improvements. Evaluation using the JPEGs above is strongly prefered to computing the corruptions in memory, so that evaluation is deterministic and consistent.

ImageNet-P

_{^{ImageNet-P sequences are MP4s not GIFs. The spatter perturbation sequence is a validation sequence.}}

Download Tiny ImageNet-P here. (Mirror.)

Download ImageNet-P here.

Citation

If you find this useful in your research, please consider citing:

@article{hendrycks2019robustness,
  title={Benchmarking Neural Network Robustness to Common Corruptions and Perturbations},
  author={Dan Hendrycks and Thomas Dietterich},
  journal={Proceedings of the International Conference on Learning Representations},
  year={2019}
}

Part of the code was contributed by Tom Brown.

Icons-50 (From an Older Draft)

Download Icons-50 here or here.

lucasosouza / robustness