Corpus ID: 57825775

Variation Network: Learning High-level Attributes for Controlled Input Manipulation

@article{Hadjeres2019VariationNL,
  title={Variation Network: Learning High-level Attributes for Controlled Input Manipulation},
  author={Ga{\"e}tan Hadjeres},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.03634}
}
  • Gaëtan Hadjeres
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • This paper presents the Variation Network (VarNet), a generative model providing means to manipulate the high-level attributes of a given input. The originality of our approach is that VarNet is not only capable of handling pre-defined attributes but can also learn the relevant attributes of the dataset by itself. These two settings can be easily combined which makes VarNet applicable for a wide variety of tasks. Further, VarNet has a sound probabilistic interpretation which grants us with a… CONTINUE READING
    2 Citations

    Figures and Topics from this paper.

    Neural Drum Machine : An Interactive System for Real-time Synthesis of Drum Sounds
    • 5
    • PDF

    References

    SHOWING 1-10 OF 35 REFERENCES
    beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
    • 1,444
    The Variational Fair Autoencoder
    • 269
    • PDF
    Deep Learning for Classical Japanese Literature
    • 152
    • PDF
    Controllable Invariance through Adversarial Feature Learning
    • 100
    • PDF
    Diagnosing and Enhancing VAE Models
    • 112
    • PDF
    Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
    • 69
    • PDF
    Variational Lossy Autoencoder
    • 363
    • PDF
    Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
    • 9
    • PDF