Guaranteed Parameter Estimation for Discrete Energy Minimization

@article{Li2017GuaranteedPE,
  title={Guaranteed Parameter Estimation for Discrete Energy Minimization},
  author={Mengtian Li and Daniel Huber},
  journal={2017 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2017},
  pages={473-482}
}
  • Mengtian Li, Daniel Huber
  • Published 2017
  • Computer Science
  • 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • Structural learning, a method to estimate the parameters for discrete energy minimization, has been proven to be effective in solving computer vision problems, especially in 3D scene parsing. As the complexity of the models increases, structural learning algorithms turn to approximate inference to retain tractability. Unfortunately, such methods often fail because the approximation can be arbitrarily poor. In this work, we propose a method to overcome this limitation through exploiting the… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Solving Association Problems with Convex Co-embedding
    2

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES
    Complexity of Discrete Energy Minimization Problems
    14
    Efficient Exact Inference for 3D Indoor Scene Understanding
    107
    Optimizing Binary MRFs via Extended Roof Duality
    477
    Learning CRFs Using Graph Cuts
    309
    Convergent Tree-Reweighted Message Passing for Energy Minimization
    1250
    A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
    146
    Contextual classification with functional Max-Margin Markov Networks
    108
    Discriminative learning of Markov random fields for segmentation of 3D scan data
    412
    Face detection, pose estimation, and landmark localization in the wild
    1909