Learning Disentangled Representations with Latent Variation Predictability

Abstract

Latent traversal is a popular approach to visualize the disentangled latent representations. Given a bunch of variations in a single unit of the latent representation, it is expected that there is a change in a single factor of variation of the data while others are fixed. However, this impressive experimental observation is rarely explicitly encoded in the objective function of learning disentangled representations. This paper defines the variation predictability of latent disentangled representations. Given image pairs generated by latent codes varying in a single dimension, this varied dimension could be closely correlated with these image pairs if the representation is well disentangled. Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs. We further develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations. The proposed variation predictability is a general constraint that is applicable to the VAE and GAN frameworks for boosting disentanglement of latent representations. Experiments show that the proposed variation predictability correlates well with existing ground-truth-required metrics and the proposed algorithm is effective for disentanglement learning.

arXiv comment14 pages, ECCV20

References in corpus (15)

• Auto-Encoding Variational Bayes
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Self-Attention Generative Adversarial Networks
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Estimating divergence functionals and the likelihood ratio by convex risk minimization
• On Convergence and Stability of GANs
• Domain Agnostic Learning with Disentangled Representations
• Flexibly Fair Representation Learning by Disentanglement
• Interpreting the Latent Space of GANs for Semantic Face Editing
• InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
• Learning Hierarchical Features from Generative Models
• PixelGAN Autoencoders
• Learning Discrete and Continuous Factors of Data via Alternating Disentanglement

Cited by in corpus (1)

• Commutative Lie Group VAE for Disentanglement Learning