Material Detail

Improved Initialisation and Gaussian Mixture Pairwise Terms for Dense Random Fields with Mean-field Inference

Improved Initialisation and Gaussian Mixture Pairwise Terms for Dense Random Fields with Mean-field Inference

This video was recorded at British Machine Vision Conference (BMVC), Surrey 2012. Recently, Krahenbuhl and Koltun proposed an efficient inference method for densely connected pairwise random fields using the mean-field approximation for a Conditional Random Field (CRF). However, they restrict their pairwise weights to take the form of a weighted combination of Gaussian kernels where each Gaussian component is allowed to take only zero mean, and can only be rescaled by a single value for each label pair. Further, their method is sensitive to initialization. In this paper, we propose methods to alleviate these issues. First, we propose a hierarchical mean-field approach where labelling from the coarser level is propagated to the finer level for better initialisation. Further, we use SIFT-flow... Show More
Rate

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Browse...

Disciplines with similar materials as Improved Initialisation and Gaussian Mixture Pairwise Terms for Dense Random Fields with Mean-field Inference

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.