论文标题
混合样本数据增强的统一分析：损失函数的观点
A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective
论文作者
论文摘要
我们提出了对混合样品数据增强（MSDA）的第一个统一的理论分析，例如混合和cutmix。我们的理论结果表明，无论选择混合策略如何，MSDA都表现为基础训练损失的像素级正规化和第一层参数的正则化。同样，与香草训练策略相比，我们的理论结果支持MSDA培训策略可以改善对抗性的鲁棒性和泛化。利用理论结果，我们对MSDA的不同设计选择的工作方式提供了高级了解。例如，我们表明，最流行的MSDA方法，混合和cutmix的行为不同，例如，CutMix通过像素距离正规化输入梯度，而混合量则使输入梯度正常于像素距离。我们的理论结果还表明，最佳的MSDA策略取决于任务，数据集或模型参数。从这些观察结果中，我们提出了普遍的MSDA，这是混合版的混合和Cutmix（HMIX）和Gaussian Mixup（GMIX），简单的混合和CutMix。我们的实施可以利用混合和cutmix的优势，而我们的实施非常有效，并且计算成本几乎可以忽略为混合和cutmix。我们的实证研究表明，我们的HMIX和GMIX优于CIFAR-100和Imagenet分类任务中先前最先进的MSDA方法。源代码可从https://github.com/naver-ai/hmix-gmix获得
We propose the first unified theoretical analysis of mixed sample data augmentation (MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level regularization of the underlying training loss and a regularization of the first layer parameters. Similarly, our theoretical results support that the MSDA training strategy can improve adversarial robustness and generalization compared to the vanilla training strategy. Using the theoretical results, we provide a high-level understanding of how different design choices of MSDA work differently. For example, we show that the most popular MSDA methods, Mixup and CutMix, behave differently, e.g., CutMix regularizes the input gradients by pixel distances, while Mixup regularizes the input gradients regardless of pixel distances. Our theoretical results also show that the optimal MSDA strategy depends on tasks, datasets, or model parameters. From these observations, we propose generalized MSDAs, a Hybrid version of Mixup and CutMix (HMix) and Gaussian Mixup (GMix), simple extensions of Mixup and CutMix. Our implementation can leverage the advantages of Mixup and CutMix, while our implementation is very efficient, and the computation cost is almost neglectable as Mixup and CutMix. Our empirical study shows that our HMix and GMix outperform the previous state-of-the-art MSDA methods in CIFAR-100 and ImageNet classification tasks. Source code is available at https://github.com/naver-ai/hmix-gmix
