Corpus ID: 209318141

Evaluating Lossy Compression Rates of Deep Generative Models

@article{Huang2020EvaluatingLC,
  title={Evaluating Lossy Compression Rates of Deep Generative Models},
  author={Sicong Huang and Alireza Makhzani and Yanshuai Cao and Roger B. Grosse},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.06653}
}
  • Sicong Huang, Alireza Makhzani, +1 author Roger B. Grosse
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • The field of deep generative modeling has succeeded in producing astonishingly realistic-seeming images and audio, but quantitative evaluation remains a challenge. Log-likelihood is an appealing metric due to its grounding in statistics and information theory, but it can be challenging to estimate for implicit generative models, and scalar-valued metrics give an incomplete picture of a model's quality. In this work, we propose to use rate distortion (RD) curves to evaluate and compare deep… CONTINUE READING
    5 Citations
    Denoising Diffusion Probabilistic Models
    • 29
    • PDF
    All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
    • 3
    • PDF
    Likelihood Ratio Exponential Families
    • 1
    • PDF
    Annealed Flow Transport Monte Carlo
    • PDF

    References

    SHOWING 1-10 OF 51 REFERENCES
    On the Quantitative Analysis of Decoder-Based Generative Models
    • 174
    • PDF
    Assessing Generative Models via Precision and Recall
    • 115
    • PDF
    Practical Lossless Compression with Latent Variables using Bits Back Coding
    • 28
    • PDF
    An empirical study on evaluation metrics of generative adversarial networks
    • 90
    • PDF
    Large Scale GAN Training for High Fidelity Natural Image Synthesis
    • 1,494
    • PDF
    Improved Techniques for Training GANs
    • 4,047
    • Highly Influential
    • PDF
    A note on the evaluation of generative models
    • 670
    • Highly Influential
    • PDF
    Are GANs Created Equal? A Large-Scale Study
    • 489
    • PDF
    Variational image compression with a scale hyperprior
    • 278
    • PDF
    GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
    • 2,352
    • Highly Influential
    • PDF