Graph-FCN for Image Semantic Segmentation

@article{Lu2019GraphFCNFI,
  title={Graph-FCN for Image Semantic Segmentation},
  author={Y. Lu and Y. Chen and D. Zhao and Jianxin Chen},
  journal={ArXiv},
  year={2019},
  volume={abs/2001.00335}
}
  • Y. Lu, Y. Chen, +1 author Jianxin Chen
  • Published 2019
  • Computer Science
  • ArXiv
  • Semantic segmentation with deep learning has achieved great progress in classifying the pixels in the image. However, the local location information is usually ignored in the high-level feature extraction by the deep learning, which is important for image semantic segmentation. To avoid this problem, we propose a graph model initialized by a fully convolutional network (FCN) named Graph-FCN for image semantic segmentation. Firstly, the image grid data is extended to graph structure data by a… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    BiFNet: Bidirectional Fusion Network for Road Segmentation
    LGNN: A Context-aware Line Segment Detector
    ContourRend: A Segmentation Method for Improving Contours by Rendering

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 19 REFERENCES
    Rethinking Atrous Convolution for Semantic Image Segmentation
    1629
    Conditional Random Fields as Recurrent Neural Networks
    1816
    Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
    338
    A visual attention based convolutional neural network for image classification
    16
    Deep Reinforcement Learning With Visual Attention for Vehicle Classification
    66
    Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
    2038
    Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
    2075