生成对抗网络中不真实插值的判别
Discriminating Against Unrealistic Interpolations in Generative Adversarial Networks
摘要：
深度生成模型的潜在空间中的插值是合成生成样本的语义上有意义的混合的标准工具之一。由于生成函数是非线性的，通常使用的潜在空间中的线性插值不会产生样本空间中的最短路径，从而导致非光滑插值。因此，最近的工作配备了一个合适的度量的潜在空间，以执行最短路径的流形上生成的样本。然而，这些通常容易偏离真实样本的流形，导致平滑但不切实际的生成，需要额外的方法来评估样本质量。生成对抗网络（GANs）通过构建，使用其网络来衡量样本质量。在本文中，我们建立了，可以有效地使用，以避免沿最短路径的低样本质量的区域。通过重用神经网络来修改潜在空间上的度量，我们提出了一种轻量级的解决方案，用于改进预训练GANs中的插值。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
