Compassionately Conservative Balanced Cuts for Image Segmentation

@article{Cahill2018CompassionatelyCB,
  title={Compassionately Conservative Balanced Cuts for Image Segmentation},
  author={Nathan D. Cahill and Tyler L. Hayes and Renee T. Meinhold and John F. Hamilton},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={1683-1691}
}
  • Nathan D. Cahill, Tyler L. Hayes, +1 author John F. Hamilton
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • The Normalized Cut (NCut) objective function, widely used in data clustering and image segmentation, quantifies the cost of graph partitioning in a way that biases clusters or segments that are balanced towards having lower values than unbalanced partitionings. However, this bias is so strong that it avoids any singleton partitions, even when vertices are very weakly connected to the rest of the graph. Motivated by the Bühler-Hein family of balanced cut costs, we propose the family of… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES

    Normalized cuts and image segmentation

    • Jianbo Shi, Jagannath Malik
    • Computer Science
    • Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    • 1997
    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Piecewise Flat Embedding for Image Segmentation

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    New spectral methods for ratio cut partitioning and clustering

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

    VIEW 1 EXCERPT

    Multiscale Combinatorial Grouping

    VIEW 1 EXCERPT