Fast Trust Region for Segmentation

L. Gorelick, Frank R. Schmidt, Y. Boykov
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2013
Abstract: Trust region is a well-known general approach to optimization which offers many advantages over standard gradient descent techniques. In particular, it allows more accurate nonlinear approximation models. In each iteration this approach computes a global optimum of a suitable approximation model within a fixed radius around the current solution, a.k.a. trust region. In general, this approach can be used only when some efficient constrained optimization algorithm is available for the selected non-linear (more accurate) approximation model.
In this paper we propose a Fast Trust Region (FTR) approach for optimization of segmentation energies with non-linear regional terms, which are known to be challenging for existing algorithms. These energies include, but are not limited to, KL divergence and Bhattacharyya distance between the observed and the target appearance distributions, volume constraint on segment size, and shape prior constraint in a form of L2-distance from target shape moments. Our method is 1-2 orders of magnitude times faster than the existing state-of-the-art methods while converging to comparable or better solutions.

Other associated files : GSB-cvpr13.pdf [2.2MB]  

Images and movies


BibTex reference

  author       = "L. Gorelick and F. R. Schmidt and Y. Boykov",
  title        = "Fast Trust Region for Segmentation",
  booktitle    = "IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)",
  month        = "Jun",
  year         = "2013",
  address      = "Portland, Oregon",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2013/Sch13"

Other publications in the database