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}
}
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
4
Twitter Mentions

Similar Papers

References

Publications referenced by this paper.
SHOWING 1-10 OF 23 REFERENCES

Piecewise Flat Embedding for Image Segmentation

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2019
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Multiclass spectral clustering

  • Proceedings Ninth IEEE International Conference on Computer Vision
  • 2003
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

New spectral methods for ratio cut partitioning and clustering

  • IEEE Trans. on CAD of Integrated Circuits and Systems
  • 1991
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

An improved two-way partitioning algorithm with stable performance [VLSI]

  • IEEE Trans. on CAD of Integrated Circuits and Systems
  • 1990
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Compassionately conservative balanced cuts for image segmentation

N. D. Cahill, T. L. Hayes, R. T. Meinhold, J. H. Hamilton
  • In eprint arXiv:1803.09903, March 2018
  • 2018
VIEW 2 EXCERPTS