InfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive Regularizers

Preprint English OPEN
Lin, Zinan; Thekumparampil, Kiran Koshy; Fanti, Giulia; Oh, Sewoong;
  • Subject: Statistics - Machine Learning | Computer Science - Machine Learning

Training disentangled representations with generative adversarial networks (GANs) remains challenging, with leading implementations failing to achieve comparable performance to Variational Autoencoder (VAE)-based methods. After $\beta$-VAE and FactorVAE discovered that ... View more