Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image with patches from another to generate the mixed image. Similarly, the corresponding labels are linearly combined by a fixed ratio $\lambda$ by l. The objects in two images may be overlapped during the mixing process, so some semantic information is corrupted in the mixed samples. In this case, the mixed image does not match the mixed label information. Besides, such a label may mislead the deep learning model training, which results in poor performance. To solve this problem, we proposed a novel approach named SUMix to learn the mixing ratio as well as the uncertainty for the mixed samples during the training process. First, we design a learnable similarity function to compute an accurate mix ratio. Second, an approach is investigated as a regularized term to model the uncertainty of the mixed samples. We conduct experiments on five image benchmarks, and extensive experimental results imply that our method is capable of improving the performance of classifiers with different cutting-based mixup approaches. The source code is available at https://github.com/JinXins/SUMix.

翻译：混合数据增强方法已被广泛应用于深度学习的各项任务中，旨在提升深度神经网络的泛化能力。现有方法如CutMix、SaliencyMix等，通常随机将一幅图像中的某个区域替换为另一幅图像的对应区域以生成混合图像，同时通过固定比例λ对相应标签进行线性组合。然而，在混合过程中两幅图像的目标可能发生重叠，导致混合样本中的语义信息遭到破坏。此时，混合图像与混合标签信息并不匹配。此外，此类标签可能误导深度学习模型的训练，进而导致性能下降。为解决该问题，本文提出一种名为SUMix的新方法，能够在训练过程中学习混合样本的混合比例及其不确定性。首先，我们设计了一种可学习的相似度函数以计算精确的混合比例；其次，提出一种作为正则化项的方法来建模混合样本的不确定性。我们在五个图像基准数据集上进行了实验，大量实验结果表明，本方法能够有效提升基于不同裁剪混合方法的分类器性能。源代码公开于https://github.com/JinXins/SUMix。