Corpus ID: 216144688

Understanding when spatial transformer networks do not support invariance, and what to do about it

@article{Finnveden2020UnderstandingWS,
  title={Understanding when spatial transformer networks do not support invariance, and what to do about it},
  author={Lukas Finnveden and Ylva Jansson and Tony Lindeberg},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.11678}
}
  • Lukas Finnveden, Ylva Jansson, Tony Lindeberg
  • Published 2020
  • Computer Science
  • ArXiv
  • Spatial transformer networks (STNs) were designed to enable convolutional neural networks (CNNs) to learn invariance to image transformations. STNs were originally proposed to transform CNN feature ... 

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES
    Motion tracking of human mouth by generalized deformable models
    13
    FDG PET/CT in carcinoma of unknown primary
    84
    Dokl
    • 1958
    Mutual Fund Styles
    421
    A non - competitive mechanism responsible for restricting niches
    • 1977
    Doxorubicin inactivates myocardial cytochrome c oxidase in rats: cardioprotection by Mito-Q.
    132
    NuSea Collaboration], arXiv:hep-ex/0302019
    • 2019
    Antagonistic Parents in Family Courts
    17