Continuous Multiclass Labeling Approaches and Algorithms

@article{Lellmann2011ContinuousML,
  title={Continuous Multiclass Labeling Approaches and Algorithms},
  author={Jan Lellmann and Christoph Schn{\"o}rr},
  journal={SIAM J. Imaging Sci.},
  year={2011},
  volume={4},
  pages={1049-1096}
}
  • Jan Lellmann, Christoph Schnörr
  • Published 2011
  • Computer Science, Mathematics
  • SIAM J. Imaging Sci.
  • We study convex relaxations of the image labeling problem on a continuous domain with regularizers based on metric interaction potentials. The generic framework ensures existence of minimizers and covers a wide range of relaxations of the original combinatorial problem. We focus on two specific relaxations that differ in flexibility and simplicity—one can be used to tightly relax any metric interaction potential, while the other covers only Euclidean metrics but requires less computational… CONTINUE READING

    Figures and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 121 CITATIONS

    What Is Optimized in Convex Relaxations for Multilabel Problems: Connecting Discrete and Continuously Inspired MAP Inference

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Discrete and Continuous Models for Partitioning Problems

    VIEW 3 EXCERPTS
    CITES BACKGROUND

    Sublabel–Accurate Relaxation of Nonconvex Energies

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Fast Partitioning of Vector-Valued Images

    A Direct Approach Toward Global Minimization for Multiphase Labeling and Segmentation Problems

    VIEW 1 EXCERPT
    CITES METHODS

    Multi-Label Segmentation via Residual-Driven Adaptive Regularization

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2010
    2020

    CITATION STATISTICS

    • 3 Highly Influenced Citations

    • Averaged 7 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 94 REFERENCES

    A convex relaxation approach for computing minimal partitions

    VIEW 1 EXCERPT

    Convex optimization for multi-class image labeling with a novel family of total variation based regularizers

    VIEW 1 EXCERPT

    Optimality Bounds for a Variational Relaxation of the Image Partitioning Problem

    VIEW 2 EXCERPTS

    Approximate Labeling via Graph Cuts Based on Linear Programming

    VIEW 2 EXCERPTS

    An Unconstrained Multiphase Thresholding Approach for Image Segmentation

    VIEW 2 EXCERPTS