Corpus ID: 17306137

PixelVAE: A Latent Variable Model for Natural Images

@article{Gulrajani2017PixelVAEAL,
  title={PixelVAE: A Latent Variable Model for Natural Images},
  author={Ishaan Gulrajani and K. Kumar and F. Ahmed and Adrien Ali Ta{\"i}ga and Francesco Visin and D. V{\'a}zquez and Aaron C. Courville},
  journal={ArXiv},
  year={2017},
  volume={abs/1611.05013}
}
  • Ishaan Gulrajani, K. Kumar, +4 authors Aaron C. Courville
  • Published 2017
  • Computer Science
  • ArXiv
  • Natural image modeling is a landmark challenge of unsupervised learning. [...] Key Method Our model requires very few expensive autoregressive layers compared to PixelCNN and learns latent codes that are more compressed than a standard VAE while still capturing most non-trivial structure. Finally, we extend our model to a hierarchy of latent variables at different scales. Our model achieves state-of-the-art performance on binarized MNIST, competitive performance on 64 × 64 ImageNet, and high-quality samples on…Expand Abstract
    215 Citations

    Figures, Tables, and Topics from this paper.

    Paper Mentions

    PixelVAE++: Improved PixelVAE with Discrete Prior
    • 7
    • Highly Influenced
    • PDF
    Latent Variable PixelCNNs for Natural Image Modeling
    • 3
    • PDF
    Hierarchical Autoregressive Image Models with Auxiliary Decoders
    • 15
    • PDF
    Variational Lossy Autoencoder
    • 365
    • PDF
    Learning Latent Subspaces in Variational Autoencoders
    • 41
    • PDF
    Auxiliary Guided Autoregressive Variational Autoencoders
    • 16
    • PDF
    Training VAEs Under Structured Residuals
    • 3
    • PDF
    Learning Deep Generative Models With Discrete Latent Variables
    • 2
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 32 REFERENCES
    Pixel Recurrent Neural Networks
    • 1,271
    • PDF
    Variational Lossy Autoencoder
    • 365
    • PDF
    Towards Conceptual Compression
    • 168
    • PDF
    Discrete Variational Autoencoders
    • 99
    • PDF
    Ladder Variational Autoencoders
    • 418
    • PDF
    MADE: Masked Autoencoder for Distribution Estimation
    • 335
    • PDF
    Importance Weighted Autoencoders
    • 658
    • PDF
    LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
    • 570
    • PDF
    Adversarial Feature Learning
    • 949
    • PDF