Transformation of general binary mrf minimization to the first-order case

    Research output: Contribution to journalArticle

    66 Citations (Scopus)

    Abstract

    We introduce a transformation of general higher-order Markov random field with binary labels into a first-order one that has the same minima as the original. Moreover, we formalize a framework for approximately minimizing higher-order multilabel MRF energies that combines the new reduction with the fusion-move and QPBO algorithms. While many computer vision problems today are formulated as energy minimization problems, they have mostly been limited to using first-order energies, which consist of unary and pairwise clique potentials, with a few exceptions that consider triples. This is because of the lack of efficient algorithms to optimize energies with higher-order interactions. Our algorithm challenges this restriction that limits the representational power of the models so that higher-order energies can be used to capture the rich statistics of natural scenes. We also show that some minimization methods can be considered special cases of the present framework, as well as comparing the new method experimentally with other such techniques.

    Original languageEnglish
    Article number5444874
    Pages (from-to)1234-1249
    Number of pages16
    JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
    Volume33
    Issue number6
    DOIs
    Publication statusPublished - 2011

    Fingerprint

    Higher Order
    Binary
    First-order
    Energy
    Computer vision
    Labels
    Energy Minimization
    Unary
    Fusion reactions
    Clique
    Statistics
    Computer Vision
    Minimization Problem
    Random Field
    Exception
    Pairwise
    Fusion
    Efficient Algorithms
    Optimise
    Restriction

    Keywords

    • Energy minimization
    • graph cuts
    • higher-order MRFs
    • pseudo-Boolean function

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Vision and Pattern Recognition
    • Software
    • Computational Theory and Mathematics
    • Applied Mathematics

    Cite this

    Transformation of general binary mrf minimization to the first-order case. / Ishikawa, Hiroshi.

    In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, No. 6, 5444874, 2011, p. 1234-1249.

    Research output: Contribution to journalArticle

    @article{f4a235f3185d4650907ee4e72bba30fe,
    title = "Transformation of general binary mrf minimization to the first-order case",
    abstract = "We introduce a transformation of general higher-order Markov random field with binary labels into a first-order one that has the same minima as the original. Moreover, we formalize a framework for approximately minimizing higher-order multilabel MRF energies that combines the new reduction with the fusion-move and QPBO algorithms. While many computer vision problems today are formulated as energy minimization problems, they have mostly been limited to using first-order energies, which consist of unary and pairwise clique potentials, with a few exceptions that consider triples. This is because of the lack of efficient algorithms to optimize energies with higher-order interactions. Our algorithm challenges this restriction that limits the representational power of the models so that higher-order energies can be used to capture the rich statistics of natural scenes. We also show that some minimization methods can be considered special cases of the present framework, as well as comparing the new method experimentally with other such techniques.",
    keywords = "Energy minimization, graph cuts, higher-order MRFs, pseudo-Boolean function",
    author = "Hiroshi Ishikawa",
    year = "2011",
    doi = "10.1109/TPAMI.2010.91",
    language = "English",
    volume = "33",
    pages = "1234--1249",
    journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
    issn = "0162-8828",
    publisher = "IEEE Computer Society",
    number = "6",

    }

    TY - JOUR

    T1 - Transformation of general binary mrf minimization to the first-order case

    AU - Ishikawa, Hiroshi

    PY - 2011

    Y1 - 2011

    N2 - We introduce a transformation of general higher-order Markov random field with binary labels into a first-order one that has the same minima as the original. Moreover, we formalize a framework for approximately minimizing higher-order multilabel MRF energies that combines the new reduction with the fusion-move and QPBO algorithms. While many computer vision problems today are formulated as energy minimization problems, they have mostly been limited to using first-order energies, which consist of unary and pairwise clique potentials, with a few exceptions that consider triples. This is because of the lack of efficient algorithms to optimize energies with higher-order interactions. Our algorithm challenges this restriction that limits the representational power of the models so that higher-order energies can be used to capture the rich statistics of natural scenes. We also show that some minimization methods can be considered special cases of the present framework, as well as comparing the new method experimentally with other such techniques.

    AB - We introduce a transformation of general higher-order Markov random field with binary labels into a first-order one that has the same minima as the original. Moreover, we formalize a framework for approximately minimizing higher-order multilabel MRF energies that combines the new reduction with the fusion-move and QPBO algorithms. While many computer vision problems today are formulated as energy minimization problems, they have mostly been limited to using first-order energies, which consist of unary and pairwise clique potentials, with a few exceptions that consider triples. This is because of the lack of efficient algorithms to optimize energies with higher-order interactions. Our algorithm challenges this restriction that limits the representational power of the models so that higher-order energies can be used to capture the rich statistics of natural scenes. We also show that some minimization methods can be considered special cases of the present framework, as well as comparing the new method experimentally with other such techniques.

    KW - Energy minimization

    KW - graph cuts

    KW - higher-order MRFs

    KW - pseudo-Boolean function

    UR - http://www.scopus.com/inward/record.url?scp=79955471099&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79955471099&partnerID=8YFLogxK

    U2 - 10.1109/TPAMI.2010.91

    DO - 10.1109/TPAMI.2010.91

    M3 - Article

    VL - 33

    SP - 1234

    EP - 1249

    JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

    JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

    SN - 0162-8828

    IS - 6

    M1 - 5444874

    ER -