Corpus ID: 204509548

Context-Gated Convolution

@article{Lin2019ContextGatedC,
  title={Context-Gated Convolution},
  author={Xu-Dong Lin and L. Ma and Wenyu Liu and Shih-Fu Chang},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.05577}
}
  • Xu-Dong Lin, L. Ma, +1 author Shih-Fu Chang
  • Published 2019
  • Computer Science
  • ArXiv
  • As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in its nature. Many efforts have been recently devoted to complementing CNNs with the global modeling ability, especially by a family of works on global feature interaction. In these works, the global context information is incorporated into local features before they are fed into convolutional layers. However, research… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 63 REFERENCES
    Dokl
    • 1958
    Veech surfaces with nonperiodic directions in the trace field
    18
    A Theory of Diagnosis from First Principles
    2504
    Pavement Distress Detection Algorithm Based on Tiles in Wavelet Domain
    4
    Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
    483
    Deformable ConvNets V2: More Deformable, Better Results
    194