Submodularization for Quadratic Pseudo-Boolean Optimization
This addresses a key bottleneck in computer vision for researchers and practitioners by providing a more efficient optimization method for non-submodular problems.
The paper tackles the optimization of binary non-submodular energies in computer vision by proposing a local submodular approximation framework, achieving state-of-the-art results that outperform standard techniques like LBP, QPBO, and TRWS.
Many computer vision problems require optimization of binary non-submodular energies. We propose a general optimization framework based on local submodular approximations (LSA). Unlike standard LP relaxation methods that linearize the whole energy globally, our approach iteratively approximates the energies locally. On the other hand, unlike standard local optimization methods (e.g. gradient descent or projection techniques) we use non-linear submodular approximations and optimize them without leaving the domain of integer solutions. We discuss two specific LSA algorithms based on "trust region" and "auxiliary function" principles, LSA-TR and LSA-AUX. These methods obtain state-of-the-art results on a wide range of applications outperforming many standard techniques such as LBP, QPBO, and TRWS. While our paper is focused on pairwise energies, our ideas extend to higher-order problems. The code is available online (http://vision.csd.uwo.ca/code/).