Submodular decomposition framework for inference in associative Markov networks with global constraints

@article{Osokin2011SubmodularDF,
  title={Submodular decomposition framework for inference in associative Markov networks with global constraints},
  author={A. Osokin and D. Vetrov and V. Kolmogorov},
  journal={CVPR 2011},
  year={2011},
  pages={1889-1896}
}
  • A. Osokin, D. Vetrov, V. Kolmogorov
  • Published 2011
  • Computer Science, Mathematics
  • CVPR 2011
  • In this paper we address the problem of finding the most probable state of discrete Markov random field (MRF) with associative pairwise terms. Although of practical importance, this problem is known to be NP-hard in general. We propose a new type of MRF decomposition, submod-ular decomposition (SMD). Unlike existing decomposition approaches SMD decomposes the initial problem into sub-problems corresponding to a specific class label while preserving the graph structure of each subproblem. Such… CONTINUE READING
    17 Citations

    Figures and Topics from this paper.

    Submodular Relaxation for Inference in Markov Random Fields
    • A. Osokin, D. Vetrov
    • Mathematics, Computer Science
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2015
    • 6
    • PDF
    Submodular Relaxation for MRFs with High-Order Potentials
    • 4
    (Hyper)-Graphs Inference through Convex Relaxations and Move Making Algorithms: Contributions and Applications in Artificial Vision
    • 7
    • PDF
    How Hard Is the LP Relaxation of the Potts Min-Sum Labeling Problem?
    • 5
    • PDF
    Higher-order segmentation via multicuts
    • 39
    • PDF
    A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
    • 149
    • PDF
    Discriminative Non-Parametric Learning of Arithmetic Circuits
    • 1
    • PDF

    References

    SHOWING 1-10 OF 50 REFERENCES
    Global optimization for first order Markov Random Fields with submodular priors
    • 32
    • PDF
    Beyond trees: MRF inference via outer-planar decomposition
    • 42
    • PDF
    1 Introduction to Dual Decomposition for Inference
    • 178
    • PDF
    Learning associative Markov networks
    • 200
    • PDF
    MAP estimation via agreement on trees: message-passing and linear programming
    • 707
    • PDF
    Efficient Exact Inference in Planar Ising Models
    • 77
    • PDF
    Approximate Labeling via Graph Cuts Based on Linear Programming
    • 269
    • PDF
    Measuring uncertainty in graph cut solutions
    • 92
    • PDF
    MRF Energy Minimization and Beyond via Dual Decomposition
    • 315
    • PDF
    A Linear Programming Approach to Max-Sum Problem: A Review
    • T. Werner
    • Mathematics, Computer Science
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2007
    • 390
    • PDF