Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. To facilitate GAN training, current methods propose to use data-specific augmentation techniques. Despite the effectiveness, it is difficult for these methods to scale to practical applications. In this work, we present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks. We first produce augmented samples using the convex combinations of the real samples. Then, we optimize the augmented samples by minimizing the norms of the data scores, i.e., the gradients of the log-density functions. This procedure enforces the augmented samples close to the data manifold. To estimate the scores, we train a deep estimation network with multi-scale score matching. For different image synthesis tasks, we train the score estimation network using different data. We do not require the tuning of the hyperparameters or modifications to the network architecture. The ScoreMix method effectively increases the diversity of data and reduces the overfitting problem. Moreover, it can be easily incorporated into existing GAN models with minor modifications. Experimental results on numerous tasks demonstrate that GAN models equipped with the ScoreMix method achieve significant improvements.

翻译：提供有限的培训数据时,通常会过度使用生成数据。为了便利GAN培训,目前的方法建议使用特定数据增强技术。尽管效果有效,但这些方法很难推广到实际应用。在这项工作中,我们为各种图像合成任务展示了“评分Mix”,这是一个新颖和可缩放的数据增强方法。我们首先使用真实样本的相形形形形形色色组合来制作增强的样本。然后,我们通过尽可能减少数据分数的规范,即日志密度函数的梯度,优化扩大的样本。这个程序使扩大的样本靠近数据方形。为了估算得分,我们用多级得分匹配来培训一个深度估算网络。对于不同的图像合成任务,我们用不同的数据来培训得分估计网络。我们不需要对超参数进行调或对网络结构进行修改。而“评分Mix”方法有效地增加了数据的多样性,减少了过度的问题。此外,它很容易被纳入现有的GAN模型中,并稍作修改。为了估算得分,我们培训一个有多重得分的深度的深度估计网络。对于不同任务,我们用不同的图像合成模型进行实验性结果显示,我们用得分估计网络进行了。