Corpus ID: 211066206

Data augmentation with Möbius transformations

@article{Zhou2020DataAW,
  title={Data augmentation with M{\"o}bius transformations},
  author={Sharon Zhou and Jiequan Zhang and Hang Jiang and Torbjorn Lundh and Andrew Y. Ng},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.02917}
}
  • Sharon Zhou, Jiequan Zhang, +2 authors Andrew Y. Ng
  • Published 2020
  • Computer Science
  • ArXiv
  • Data augmentation has led to substantial improvements in the performance and generalization of deep models, and remain a highly adaptable method to evolving model architectures and varying amounts of data---in particular, extremely scarce amounts of available training data. In this paper, we present a novel method of applying Mobius transformations to augment input images during training. Mobius transformations are bijective conformal maps that generalize image translation to operate over… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES

    Improved Mixed-Example Data Augmentation

    VIEW 1 EXCERPT

    AutoAugment: Learning Augmentation Strategies From Data

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Fast AutoAugment

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Unsupervised Data Augmentation

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL