Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels. This technique is known to improve the generalization performance in many learning paradigms and applications. In this work, we first analyze Mixup and show that it implicitly regularizes infinitely many directional derivatives of all orders. Based on this new insight, we propose an improved version of Mixup, theoretically justified to deliver better generalization performance than the vanilla Mixup. To demonstrate the effectiveness of the proposed method, we conduct experiments across various domains such as images, tabular data, speech, and graphs. Our results show that the proposed method improves Mixup across multiple datasets using a variety of architectures, for instance, exhibiting an improvement over Mixup by 0.8% in ImageNet top-1 accuracy.

翻译：Mixup是一种训练深度神经网络时常用的数据增强技术，通过线性插值输入及其标签来生成额外样本。该技术已被证明能提升多种学习范式及应用中的泛化性能。本文首先分析Mixup，发现其隐式正则化了无穷多任意阶方向导数。基于这一新见解，我们提出改进版Mixup，并从理论上证明其泛化性能优于原始Mixup。为验证所提方法的有效性，我们在图像、表格数据、语音和图数据等多个领域开展实验。结果表明，该方法在使用多种架构的多个数据集上均提升了Mixup性能，例如在ImageNet top-1准确率上比Mixup提高了0.8%。