DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
复制标题
DOI：
10.48550/arxiv.2211.14694
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Tiantian Fang;Ruoyu Sun;A. Schwing
中科院分区：
文献类型：
--
作者：
Tiantian Fang;Ruoyu Sun;A. Schwing
生成对抗网络（GAN）在学习从给定数据集指定的分布中采样方面非常成功，特别是如果给定数据集与其维度相比相当大。然而，由于数据有限，传统的GAN一直在努力，输出正则化，数据增强，使用预训练模型和修剪等策略已被证明可以带来改进。值得注意的是，这些策略的适用性1）通常限于特定的设置，例如，预训练GAN的可用性;或者2）增加训练时间，例如，当使用修剪。相比之下，我们提出了一个判别器梯度间隙正则化GAN（DigGAN）公式，它可以添加到任何现有的GAN。DigGAN增强了现有的GAN，鼓励缩小神经元预测的梯度范数与r.t. t之间的差距。真实的图像和w.r.t.\生成的样本。我们观察到这个公式，以避免GAN损失景观中的不良吸引子，并且我们发现DigGAN在有限的数据可用时显着改善GAN训练的结果。代码可在\url{https：//github.com/AilsaF/DigGAN}获得。
Generative adversarial nets (GANs) have been remarkably successful at learning to sample from distributions specified by a given dataset, particularly if the given dataset is reasonably large compared to its dimensionality. However, given limited data, classical GANs have struggled, and strategies like output-regularization, data-augmentation, use of pre-trained models and pruning have been shown to lead to improvements. Notably, the applicability of these strategies is 1) often constrained to particular settings, e.g., availability of a pretrained GAN; or 2) increases training time, e.g., when using pruning. In contrast, we propose a Discriminator gradIent Gap regularized GAN (DigGAN) formulation which can be added to any existing GAN. DigGAN augments existing GANs by encouraging to narrow the gap between the norm of the gradient of a discriminator's prediction w.r.t.\ real images and w.r.t.\ the generated samples. We observe this formulation to avoid bad attractors within the GAN loss landscape, and we find DigGAN to significantly improve the results of GAN training when limited data is available. Code is available at \url{https://github.com/AilsaF/DigGAN}.