论文标题
ABCA：光谱规范作为自动稳定器的自适应结合控制
ABCAS: Adaptive Bound Control of spectral norm as Automatic Stabilizer
论文作者
论文摘要
光谱归一化是稳定生成对抗网络训练的最佳方法之一。光谱归一化限制了歧视器的梯度之间的分布和伪造数据之间的分布之间。但是，即使有了这种归一化，GAN的培训有时也会失败。在本文中，我们揭示有时需要更严重的限制，具体取决于训练数据集，然后我们提出了一种新型的稳定剂，该稳定剂提供了一种自适应归一化方法，称为ABCAS。我们的方法通过检查真实数据和虚假数据的分布距离来决定歧视者的Lipschitz不断自适应地。我们的方法提高了生成对抗网络训练的稳定性，并获得了更好的Fréchet成立距离得分。我们还研究了三个数据集的合适光谱规范。我们将结果显示为消融研究。
Spectral Normalization is one of the best methods for stabilizing the training of Generative Adversarial Network. Spectral Normalization limits the gradient of discriminator between the distribution between real data and fake data. However, even with this normalization, GAN's training sometimes fails. In this paper, we reveal that more severe restriction is sometimes needed depending on the training dataset, then we propose a novel stabilizer which offers an adaptive normalization method, called ABCAS. Our method decides discriminator's Lipschitz constant adaptively, by checking the distance of distributions of real and fake data. Our method improves the stability of the training of Generative Adversarial Network and achieved better Fréchet Inception Distance score of generated images. We also investigated suitable spectral norm for three datasets. We show the result as an ablation study.
