Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
This work provides standardized benchmarks for assessing robustness in safety-critical applications, though it is incremental in expanding existing corruption research.
The paper introduced ImageNet-C and ImageNet-P benchmarks to evaluate image classifier robustness to common corruptions and perturbations, finding negligible improvements in robustness from AlexNet to ResNet and that some adversarial defenses enhance perturbation robustness.
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations. Unlike recent robustness research, this benchmark evaluates performance on common corruptions and perturbations not worst-case adversarial perturbations. We find that there are negligible changes in relative corruption robustness from AlexNet classifiers to ResNet classifiers. Afterward we discover ways to enhance corruption and perturbation robustness. We even find that a bypassed adversarial defense provides substantial common perturbation robustness. Together our benchmarks may aid future work toward networks that robustly generalize.