For machine learning task, lacking sufficient samples mean the trained model
has low confidence to approach the ground truth function. Until recently, after
the generative adversarial networks (GAN) had been prop
本研究提出了一个称为 Data Augmentation Optimized for GAN (DAG) 的框架,用于在 GAN 训练中使用增强数据来改善原始分布的学习,通过理论分析表明该方法有效地利用增强数据来提高鉴别器和生成器的学习,并在自然图像和医疗图像数据集上证明了 DAG 的有效性和优越性。