通过局部维度估计分析 GAN 的潜在空间
Analyzing the Latent Space of GAN through Local Dimension Estimation
AI总结：
本文提出预训练 GAN 中间层的局部维度估计算法，并以纯几何指标 Distortion 无监督评估潜在空间解耦程度。
摘要：
基于风格的 GAN（StyleGAN）在高保真图像合成中取得的令人瞩目的成功，推动了理解其潜在空间语义属性的研究。本文中，我们通过将潜在空间作为流形进行几何分析来处理这一问题。具体而言，我们提出了一种用于预训练 GAN 模型中任意中间层的局部维度估计算法。估计得到的局部维度被解释为该潜在变量可能产生的语义变化数量。此外，这种内禀维度估计能够实现对潜在空间解耦的无监督评估。我们提出的名为 Distortion 的指标，用于衡量所学潜在空间上内禀切空间的不一致性。Distortion 是纯几何的，不需要任何额外的属性信息。尽管如此，Distortion 仍与全局基兼容性以及有监督解耦得分表现出高度相关性。我们的工作是在没有属性标签的情况下，从 GAN 的各种潜在空间中选择最具解耦性的潜在空间的第一步。
英文摘要：
The impressive success of style-based GANs (StyleGANs) in high-fidelity image synthesis has motivated research to understand the semantic properties of their latent spaces. In this paper, we approach this problem through a geometric analysis of latent spaces as a manifold. In particular, we propose a local dimension estimation algorithm for arbitrary intermediate layers in a pre-trained GAN model. The estimated local dimension is interpreted as the number of possible semantic variations from this latent variable. Moreover, this intrinsic dimension estimation enables unsupervised evaluation of disentanglement for a latent space. Our proposed metric, called Distortion, measures an inconsistency of intrinsic tangent space on the learned latent space. Distortion is purely geometric and does not require any additional attribute information. Nevertheless, Distortion shows a high correlation with the global-basis-compatibility and supervised disentanglement score. Our work is the first step towards selecting the most disentangled latent space among various latent spaces in a GAN without attribute labels.
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。
