Corpus ID: 49657329

Glow: Generative Flow with Invertible 1x1 Convolutions

@article{Kingma2018GlowGF,
  title={Glow: Generative Flow with Invertible 1x1 Convolutions},
  author={Diederik P. Kingma and P. Dhariwal},
  journal={ArXiv},
  year={2018},
  volume={abs/1807.03039}
}
  • Diederik P. Kingma, P. Dhariwal
  • Published 2018
  • Mathematics, Computer Science
  • ArXiv
  • Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis. In this paper we propose Glow, a simple type of generative flow using an invertible 1x1 convolution. Using our method we demonstrate a significant improvement in log-likelihood on standard benchmarks. Perhaps most strikingly, we demonstrate that a generative model… CONTINUE READING

    Paper Mentions

    MaCow: Masked Convolutional Generative Flow
    15
    Generative Flow via Invertible nxn Convolution
    Regularized Autoencoders via Relaxed Injective Probability Flow
    9
    Emerging Convolutions for Generative Normalizing Flows
    41
    VFlow: More Expressive Generative Flows with Variational Data Augmentation
    4
    Generative Latent Flow
    6
    Invertible Residual Networks
    132
    Transflow Learning: Repurposing Flow Models Without Retraining
    2
    Decoupling Global and Local Representations from/for Image Generation

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES
    Density estimation using Real NVP
    866
    Auto-Encoding Variational Bayes
    8622
    Improved Variational Inference with Inverse Autoregressive Flow
    728
    Generative Adversarial Nets
    16734
    NICE: Non-linear Independent Components Estimation
    585
    Identity Mappings in Deep Residual Networks
    3675
    Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models
    80
    LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
    515
    Image Transformer
    143
    Progressive Growing of GANs for Improved Quality, Stability, and Variation
    1952