论文标题
多样本$ζ$ -mixup：$ p $ series Interpolant的更丰富，更现实的合成样本
Multi-Sample $ζ$-mixup: Richer, More Realistic Synthetic Samples from a $p$-Series Interpolant
论文作者
论文摘要
现代的深度学习培训程序依赖于模型正规化技术，例如数据增强方法，该技术生成培训样本，以增加数据的多样性和标签信息的丰富性。一种流行的方法Mixup使用凸组合的原始样品组合来生成新样品。但是，正如我们在实验中显示的那样，混合物可能会产生不良的合成样品，其中数据被从歧管中采样并可能包含不正确的标签。我们提出了$ζ$ -MIXUP，这是一种具有证明且明显理想的属性的混合概括的概括，可以使用$ n $原始样本的信息，从而允许$ n \ geq 2 $样品的凸组组合，从而通过使用$ p $ series internpolant internpolant。我们表明，与混合相比，$ζ$ -Mixup更好地保留了原始数据集的内在维度，这是用于培训可概括模型的理想属性。此外，我们表明，我们对$ζ$ -MIXUP的实现比混合速度快，并且对受控合成和24个现实世界的自然和医疗图像分类数据集进行了广泛的评估，这表明$ζ$ -Mixup优于混合和传统数据增强技术。
Modern deep learning training procedures rely on model regularization techniques such as data augmentation methods, which generate training samples that increase the diversity of data and richness of label information. A popular recent method, mixup, uses convex combinations of pairs of original samples to generate new samples. However, as we show in our experiments, mixup can produce undesirable synthetic samples, where the data is sampled off the manifold and can contain incorrect labels. We propose $ζ$-mixup, a generalization of mixup with provably and demonstrably desirable properties that allows convex combinations of $N \geq 2$ samples, leading to more realistic and diverse outputs that incorporate information from $N$ original samples by using a $p$-series interpolant. We show that, compared to mixup, $ζ$-mixup better preserves the intrinsic dimensionality of the original datasets, which is a desirable property for training generalizable models. Furthermore, we show that our implementation of $ζ$-mixup is faster than mixup, and extensive evaluation on controlled synthetic and 24 real-world natural and medical image classification datasets shows that $ζ$-mixup outperforms mixup and traditional data augmentation techniques.
