Analyzing the Latent Space of GAN through Local Dimension Estimation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeDisentanglementImage GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control
Many real-world sequential decision-making problems can be formulated as optimal control with high-dimensional observations and unknown dynamics. A promising approach is to embed the high-dimensional observations into a …
Decision MakingOpen-Ended Question AnsweringRepresentation LearningSequential Decision MakingKnowledge-Embedded Latent Projection for Robust Representation Learning
Latent space models are widely used for analyzing high-dimensional discrete data matrices, such as patient-feature matrices in electronic health records (EHRs), by capturing complex dependence structures through low-dime…
Representation LearningHALO: Hybrid Auto-encoded Locomotion with Learned Latent Dynamics, Poincaré Maps, and Regions of Attraction
Reduced-order models are powerful for analyzing and controlling high-dimensional dynamical systems. Yet constructing these models for complex hybrid systems such as legged robots remains challenging. Classical approaches…
Discovering Stylistic Variations in Distributional Vector Space Models via Lexical Paraphrases
Detecting and analyzing stylistic variation in language is relevant to diverse Natural Language Processing applications. In this work, we investigate whether salient dimensions of style variations are embedded in standar…
Semantic Textual SimilarityWord EmbeddingsThinner Latent Spaces: Detecting dimension and imposing invariance through autoencoder gradient constraints
Conformal Autoencoders are a neural network architecture that imposes orthogonality conditions between the gradients of latent variables towards achieving disentangled representations of data. In this letter we show that…