Neighborhood-consensus message passing as a framework for generalized iterated conditional expectations

摘要

In this paper we propose a novel inference method for maximum a posteriori estimation with Markov random field prior. The central idea is to integrate a kind of joint "voting" of neighboring labels into a message passing scheme similar to loopy belief propagation (LBP). While the LBP operates with many pairwise interactions, we formulate "messages" sent from a neighborhood as a whole. Hence the name neighborhood-consensus message passing (NCMP). The practical algorithm is much simpler than LBP and combines the flexibility of iterated conditional modes (ICM) with some ideas of more general message passing. The proposed method is also a generalization of the iterated conditional expectations algorithm (ICE): we revisit ICE and redefine it in a message passing framework in a more general form. We also develop a simplified version of NCMP, called weighted iterated conditional modes (W1CM), that is suitable for large neighborhoods. We verify the potentials of our methods on four different benchmarks, showing the improvement in quality and/or speed over related inference techniques.