Analyzing the Latent Space of GAN through Local Dimension Estimation
This work addresses the challenge of evaluating disentanglement in GANs for researchers in generative modeling, though it is incremental as it builds on existing style-based GAN analysis.
The paper tackles the problem of understanding semantic properties in GAN latent spaces by proposing a local dimension estimation algorithm to analyze them as manifolds, resulting in a geometric metric called Distortion that correlates with disentanglement scores without requiring attribute labels.
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.