Corpus ID: 173990500

DualDis: Dual-Branch Disentangling with Adversarial Learning

@article{Robert2019DualDisDD,
  title={DualDis: Dual-Branch Disentangling with Adversarial Learning},
  author={Thomas Robert and Nicolas Thome and Matthieu Cord},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.00804}
}
  • Thomas Robert, Nicolas Thome, Matthieu Cord
  • Published 2019
  • Computer Science
  • ArXiv
  • In computer vision, disentangling techniques aim at improving latent representations of images by modeling factors of variation. [...] Key Method To effectively separate the information, we propose to use a combination of regular and adversarial classifiers to guide the two branches in specializing for class and attribute information respectively. We also investigate the possibility of using semi-supervised learning for an effective disentangling even using few labels.Expand Abstract

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES

    Multi-task Adversarial Network for Disentangled Feature Learning

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    A Style-Based Generator Architecture for Generative Adversarial Networks

    VIEW 1 EXCERPT

    Dual Swap Disentangling

    VIEW 1 EXCERPT