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 robustness approaches. In this paper, we propose a diverse Gaussian noise consistency regularization method for improving robustness of image classifiers under a variety of noise corruptions while still maintaining high clean accuracy. We derive bounds to motivate our Gaussian noise consistency regularization using a local loss landscape analysis. We show that this simple approach improves robustness against various unforeseen noise corruptions over standard and adversarial training and other strong baselines. Furthermore, when combined with diverse data augmentation techniques we empirically show this type of consistency regularization further improves robustness and uncertainty calibration for common corruptions upon the state-of-the-art for several image classification benchmarks.
翻译:深神经网络在列车和测试分布同时达到高预测准确度。但在实践中,出现了各种类型的腐败,这些腐败偏离了这一设置,并导致严重性能退化。在出现意外的域变换的情况下,很少提出处理一般化的方法。特别是,数字噪音腐败在获取图像阶段通常发生,对目前的稳健性方法构成重大挑战。在本文件中,我们提出了多种高斯噪音一致性规范化方法,在各种噪音腐败的情况下提高图像分类者的稳健性,同时保持高斯级的高度清洁性。我们通过对当地失传情况的分析,获得激励高斯级声音一致性规范化的界限。我们表明,这一简单方法在标准、对抗性培训和其他强基线方面,提高了应对各种意外噪音腐败的稳健性。此外,如果结合各种数据增强技术,我们实验性地展示了这种一致性规范化方法,将进一步提高本行业在几个图像分类基准上常见腐败的稳健性和不确定性校准度。