Deep neural networks achieve high prediction accuracy when the train and test distributions coincide. In practice though, various types of corruptions occur which deviate from this setup and cause severe performance degradations. Few methods have been proposed to address generalization in the presence of unforeseen domain shifts. In particular, digital noise corruptions arise commonly in practice during the image acquisition stage and present a significant challenge for current methods. In this paper, we propose a diverse Gaussian noise consistency regularization method for improving robustness of image classifiers under a variety of corruptions while still maintaining high clean accuracy. We derive bounds to motivate and understand the behavior of our Gaussian noise consistency regularization using a local loss landscape analysis. Our approach improves robustness against unforeseen noise corruptions by 4.2-18.4% over adversarial training and other strong diverse data augmentation baselines across several benchmarks. Furthermore, it improves robustness and uncertainty calibration by 3.7% and 5.5%, respectively, against all common corruptions (weather, digital, blur, noise) when combined with state-of-the-art diverse data augmentations.

翻译：深度神经网络在训练与测试分布一致时能够取得高预测精度。然而实际应用中，各类偏离该设定分布的图像退化现象会导致性能严重下降。针对未知领域偏移下的泛化问题，现有方法较少涉及。特别地，数字噪声退化在图像采集阶段普遍存在，对现有方法构成重大挑战。本文提出一种多样化高斯噪声一致性正则化方法，旨在提升图像分类器在多种退化场景下的鲁棒性，同时保持较高的干净数据准确率。通过局部损失景观分析推导界限，以揭示和解释高斯噪声一致性正则化的行为机制。在多个基准测试中，本方法较对抗训练及其他强多样化数据增强基线，对未知噪声退化鲁棒性提升4.2-18.4%。当与最先进的多样化数据增强相结合时，针对所有常见退化类型（天气、数字、模糊、噪声），鲁棒性与不确定性校准分别提升3.7%和5.5%。