Submodularization for Binary Pairwise Energies
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
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Submodularization for Quadratic Pseudo-Boolean Optimization
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…
Adaptive and Move Making Auxiliary Cuts for Binary Pairwise Energies
Many computer vision problems require optimization of binary non-submodular energies. In this context, iterative submodularization techniques based on trust region (LSA-TR) and auxiliary functions (LSA-AUX) have been rec…
Superdifferential Cuts for Binary Energies
We propose an efficient and general purpose energy optimization method for binary variable energies used in various low-level vision tasks. The proposed method can be used for broad classes of higher-order and pairwise n…
BinarizationImage SegmentationSemantic SegmentationFast Energy Minimization Using Learned State Filters
Pairwise discrete energies defined over graphs are ubiquitous in computer vision. Many algorithms have been proposed to minimize such energies, often concentrating on sparse graph topologies or specialized classes of pai…
ESSP: An Efficient Approach to Minimizing Dense and Nonsubmodular Energy Functions
Many recent advances in computer vision have demonstrated the impressive power of dense and nonsubmodular energy functions in solving visual labeling problems. However, minimizing such energies is challenging. None of ex…