Corpus ID: 220056269

InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs

  title={InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs},
  author={Z. Lin and Kiran Koshy Thekumparampil and Giulia Fanti and Sewoong Oh},
  • Z. Lin, Kiran Koshy Thekumparampil, +1 author Sewoong Oh
  • Published in ICML 2020
  • Computer Science, Mathematics
  • Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. Recent advances have been dominated by Variational AutoEncoder (VAE)-based methods, while training disentangled generative adversarial networks (GANs) remains challenging. In this work, we show that the dominant challenges facing disentangled GANs can be mitigated through the use… CONTINUE READING
    10 Citations

    Figures, Tables, and Topics from this paper

    Learning Disentangled Representations with Latent Variation Predictability
    • 1
    • PDF
    Challenging β-VAE with β<1 for Disentanglement Via Dynamic Learning
    Disentangled Generative Causal Representation Learning
    • PDF
    Globally Injective ReLU Networks
    • PDF


    High-Fidelity Synthesis with Disentangled Representation
    • 14
    • PDF
    Learning Disentangled Representations with Semi-Supervised Deep Generative Models
    • 198
    • PDF
    Hyperprior Induced Unsupervised Disentanglement of Latent Representations
    • 16
    • PDF
    beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
    • 1,585
    • Highly Influential
    A Heuristic for Unsupervised Model Selection for Variational Disentangled Representation Learning
    • 13
    • Highly Influential
    • PDF
    Weakly Supervised Disentanglement by Pairwise Similarities
    • 18
    • PDF
    Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
    • 348
    • PDF
    Learning Deep Disentangled Embeddings with the F-Statistic Loss
    • 71
    • PDF