DeepAI AI Chat
Log In Sign Up

Generalized Fast Approximate Energy Minimization via Graph Cuts: Alpha-Expansion Beta-Shrink Moves

by   Mark Schmidt, et al.

We present alpha-expansion beta-shrink moves, a simple generalization of the widely-used alpha-beta swap and alpha-expansion algorithms for approximate energy minimization. We show that in a certain sense, these moves dominate both alpha-beta-swap and alpha-expansion moves, but unlike previous generalizations the new moves require no additional assumptions and are still solvable in polynomial-time. We show promising experimental results with the new moves, which we believe could be used in any context where alpha-expansions are currently employed.


page 4

page 8


On ordered beta distribution and the generalized incomplete beta function

Motivated by applications in Bayesian analysis we introduce a multidimen...

Markov Random Field Model-Based Salt and Pepper Noise Removal

Problem of impulse noise reduction is a very well studied problem in ima...

Generalized Range Moves

We consider move-making algorithms for energy minimization of multi-labe...

Continuous 3D Label Stereo Matching using Local Expansion Moves

We present an accurate stereo matching method using local expansion move...

Exploring the tiers of rooted phylogenetic network space using tail moves

Popular methods for exploring the space of rooted phylogenetic trees use...

Chess2vec: Learning Vector Representations for Chess

We conduct the first study of its kind to generate and evaluate vector r...