论文标题
基于傅立叶的增强功能，以改善鲁棒性和不确定性校准
Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration
论文作者
论文摘要
各种数据增强策略是一种自然的方法，可以改善计算机视觉模型的鲁棒性，以防止数据分布的不可预见的变化。但是，能够量身定制此类策略以对特定类别的腐败或攻击接种模型的能力，而不会导致对其他类别的腐败造成的强大损失 - 仍然难以捉摸。在这项工作中，我们成功地针对基于傅立叶的攻击而成功地硬化了模型，同时在CIFAR-10-C和CIFAR-100-C数据集中产生了优越到agemix的精度和校准结果；对于某些高度噪声和数字型损坏，分类误差将减少超过10个百分点。我们通过将傅立叶基础扰动纳入Augmix图像启发框架中来实现这一目标。因此，我们证明了Augmix框架可以量身定制，以有效地针对特定的分布变化，同时促进整体模型鲁棒性。
Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution. However, the ability to tailor such strategies to inoculate a model against specific classes of corruptions or attacks -- without incurring substantial losses in robustness against other classes of corruptions -- remains elusive. In this work, we successfully harden a model against Fourier-based attacks, while producing superior-to-AugMix accuracy and calibration results on both the CIFAR-10-C and CIFAR-100-C datasets; classification error is reduced by over ten percentage points for some high-severity noise and digital-type corruptions. We achieve this by incorporating Fourier-basis perturbations in the AugMix image-augmentation framework. Thus we demonstrate that the AugMix framework can be tailored to effectively target particular distribution shifts, while boosting overall model robustness.
