The literature on robustness towards common corruptions shows no consensus on whether adversarial training can improve the performance in this setting. First, we show that, when used with an appropriately selected perturbation radius, $\ell_p$ adversarial training can serve as a strong baseline against common corruptions improving both accuracy and calibration. Then we explain why adversarial training performs better than data augmentation with simple Gaussian noise which has been observed to be a meaningful baseline on common corruptions. Related to this, we identify the $\sigma$-overfitting phenomenon when Gaussian augmentation overfits to a particular standard deviation used for training which has a significant detrimental effect on common corruption accuracy. We discuss how to alleviate this problem and then how to further enhance $\ell_p$ adversarial training by introducing an efficient relaxation of adversarial training with learned perceptual image patch similarity as the distance metric. Through experiments on CIFAR-10 and ImageNet-100, we show that our approach does not only improve the $\ell_p$ adversarial training baseline but also has cumulative gains with data augmentation methods such as AugMix, DeepAugment, ANT, and SIN, leading to state-of-the-art performance on common corruptions. The code of our experiments is publicly available at https://github.com/tml-epfl/adv-training-corruptions.
翻译:关于对常见腐败的稳健程度的文献表明,对于对抗性培训是否能够提高在这一背景下的绩效,我们没有共识。 首先,我们表明,如果在适当选择的扰动半径范围内使用,美元/美元/美元/美元/美元/美元/美元/美元/美元的对抗性培训可以作为防止常见腐败的有力基准,提高准确性和校准性。然后,我们解释为什么对抗性培训比数据增强要好,而简单的高斯语噪音被认为是关于常见腐败的有意义的基线。与此相关的,我们确定,当Gaussalsian扩大用于培训的特定标准偏差对常见腐败的准确性有重大不利影响时,那么,美元/美元/美元/美元/美元/美元/对抗性培训就可产生累积效果。我们讨论如何缓解这一问题,然后如何通过引入有效的放松对抗性培训,在认知性形象上与距离指标相似的相似,从而进一步提高对抗性培训。我们通过对CIFAR-10和图像网络的实验,我们发现我们的方法不仅改进了美元/美元/美元/美元/美元/对抗性培训基线,而且还在诸如Aug-Mix、EGEGA-GAGAGAR_ADAR_ADARBS_S_padtrainst palmentmentmentmentmentmentmentmentmentmentmental_SIN compalpalpalpalpalpalpalpalpalpalpalpal_