Corpus ID: 71145771

Adversarial Mixup Resynthesizers

@article{Beckham2019AdversarialMR,
  title={Adversarial Mixup Resynthesizers},
  author={C. Beckham and S. Honari and Alex Lamb and V. Verma and F. Ghadiri and R. Devon Hjelm and C. Pal},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.02709}
}
  • C. Beckham, S. Honari, +4 authors C. Pal
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders. [...] Key Result We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.Expand Abstract
    10 Citations
    Adversarial Mixup Synthesis Training for Unsupervised Domain Adaptation
    • 2
    MIXUP INFERENCE: BETTER EXPLOITING MIXUP
    Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks
    • 19
    • PDF
    An experimental evaluation of mixup regression forests
    SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks
    • 1
    • PDF
    Combining Ensembles and Data Augmentation can Harm your Calibration
    KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning
    • 7
    • PDF
    CMTS: A Conditional Multiple Trajectory Synthesizer for Generating Safety-Critical Driving Scenarios
    • 2
    • PDF

    References

    SHOWING 1-10 OF 44 REFERENCES
    mixup: Beyond Empirical Risk Minimization
    • 1,134
    • PDF
    Adversarial Autoencoders
    • 988
    • PDF
    Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
    • 88
    • Highly Influential
    • PDF
    InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
    • 2,155
    • PDF
    Extracting and composing robust features with denoising autoencoders
    • 4,156
    • PDF
    Spectral Normalization for Generative Adversarial Networks
    • 1,521
    • PDF
    Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer
    • 70
    Learning deep representations by mutual information estimation and maximization
    • 477
    • PDF
    Generative Adversarial Nets
    • 18,854
    • Highly Influential
    • PDF