论文标题
使用Mobius转换的数据增强
Data augmentation with Mobius transformations
论文作者
论文摘要
数据增强导致了深层模型的性能和概括的实质性改善，并且仍然是一种不断发展的模型架构和不同数据的方法，尤其是非常稀缺的可用培训数据。在本文中，我们提出了一种新颖的方法，该方法将Mobius转换应用于在训练过程中增强输入图像。 Mobius转换是概括图像翻译以在像素空间中复杂反转的过程中运行的射射形结构图。结果，Mobius转换可以在样本级别上运行并保留数据标签。我们表明，在训练过程中包含Mobius转换，可以改善对先前样本级数据增强技术（例如切口和标准的作物和翼型转换）的概括，最值得注意的是在低数据方案中。
Data augmentation has led to substantial improvements in the performance and generalization of deep models, and remain a highly adaptable method to evolving model architectures and varying amounts of data---in particular, extremely scarce amounts of available training data. In this paper, we present a novel method of applying Mobius transformations to augment input images during training. Mobius transformations are bijective conformal maps that generalize image translation to operate over complex inversion in pixel space. As a result, Mobius transformations can operate on the sample level and preserve data labels. We show that the inclusion of Mobius transformations during training enables improved generalization over prior sample-level data augmentation techniques such as cutout and standard crop-and-flip transformations, most notably in low data regimes.
