Frank R. Schmidt

This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier. The considered task is posed as a joint optimization problem in the continuous classifier parameters and the discrete label vari- ables. In contrast to prior approaches such as convex relaxations, we propose an advantageous decoupling of the objective function into discrete and continuous subproblems and a novel, efficient optimization method related to ADMM. This approach preserves integrality of the discrete label variables and guarantees global convergence to a critical point. We demonstrate the advantages of our approach in several experiments including video object segmentation on the DAVIS data set and interactive image segmentation.

This paper is also stored on arXiv.

@InProceedings\{LLSDSAC18,
  author       = "Laude, Emanuel and Lange, Jan-Hendrik and Sch{\"u}pfer, Jonas and Domokos, Csaba and Leal-Taix\'e, Laura and Schmidt, Frank R. and Andres, Bj{\"o}rn and Cremers, Daniel",
  title        = "Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs",
  booktitle    = "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
  month        = "Jun",
  year         = "2018",
  url          = "http://frank-r-schmidt.de/Publications/2018/LLSDSAC18"
}