Deep networks have achieved impressive results on a range of well-curated benchmark datasets. Surprisingly, their performance remains sensitive to perturbations that have little effect on human performance. In this work, we propose a novel extension of Mixup called Robustmix that regularizes networks to classify based on lower-frequency spatial features. We show that this type of regularization improves robustness on a range of benchmarks such as Imagenet-C and Stylized Imagenet. It adds little computational overhead and, furthermore, does not require a priori knowledge of a large set of image transformations. We find that this approach further complements recent advances in model architecture and data augmentation, attaining a state-of-the-art mCE of 44.8 with an EfficientNet-B8 model and RandAugment, which is a reduction of 16 mCE compared to the baseline.

翻译：深度网络在一系列精心整理的基准数据集上取得了令人瞩目的成果。令人惊讶的是，其性能仍然对几乎不影响人类表现的扰动敏感。在本工作中，我们提出了一种名为Robustmix的Mixup新型扩展方法，该方法通过正则化网络使其基于低频率空间特征进行分类。我们证明这种正则化方式在多个基准测试（如Imagenet-C和Stylized Imagenet）上提升了鲁棒性。该方法计算开销极小，且无需预先掌握大量图像变换的先验知识。我们发现本方法进一步与模型架构及数据增强领域的最新进展形成互补：当使用EfficientNet-B8模型与RandAugment时，获得了44.8的最优平均错误率（mCE），相比基线降低了16个mCE点。