论文标题
歧视生成对抗网络中的不切实际插值
Discriminating Against Unrealistic Interpolations in Generative Adversarial Networks
论文作者
论文摘要
深生成模型的潜在空间中的插值是合成生成样品的语义意义混合物的标准工具之一。由于发电机函数是非线性的，因此潜在空间中常用的线性插值不会产生样品空间中最短的路径，从而导致非平滑插值。因此，最近的工作为潜在空间配备了合适的度量标准，以在生成的样品的流形上强制执行最短路径。但是，这些通常是易于摆脱真实样品的多种形式的敏感，从而导致平稳但不切实际的产生，这需要一种额外的方法来评估沿路径的样本质量。生成对抗网络（GAN），通过构造，使用其歧视者网络来测量样本质量。在本文中，我们确定可以有效地使用鉴别器来避免沿最短路径的样本质量低区域。通过重复判别器网络来修改潜在空间上的度量，我们提出了一种轻巧的解决方案，以改善预训练的gan中的插值。
Interpolations in the latent space of deep generative models is one of the standard tools to synthesize semantically meaningful mixtures of generated samples. As the generator function is non-linear, commonly used linear interpolations in the latent space do not yield the shortest paths in the sample space, resulting in non-smooth interpolations. Recent work has therefore equipped the latent space with a suitable metric to enforce shortest paths on the manifold of generated samples. These are often, however, susceptible of veering away from the manifold of real samples, resulting in smooth but unrealistic generation that requires an additional method to assess the sample quality along paths. Generative Adversarial Networks (GANs), by construction, measure the sample quality using its discriminator network. In this paper, we establish that the discriminator can be used effectively to avoid regions of low sample quality along shortest paths. By reusing the discriminator network to modify the metric on the latent space, we propose a lightweight solution for improved interpolations in pre-trained GANs.
