DeepAI AI Chat
Log In Sign Up

Submodularization for Quadratic Pseudo-Boolean Optimization

by   Lena Gorelick, et al.

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 (


page 5

page 6

page 7


Efficient Minimization of Higher Order Submodular Functions using Monotonic Boolean Functions

Submodular function minimization is a key problem in a wide variety of a...

An Experimental Comparison of Trust Region and Level Sets

High-order (non-linear) functionals have become very popular in segmenta...

Discrete Energy Minimization, beyond Submodularity: Applications and Approximations

In this thesis I explore challenging discrete energy minimization proble...

Structured learning of sum-of-submodular higher order energy functions

Submodular functions can be exactly minimized in polynomial time, and th...

The Expressive Power of Binary Submodular Functions

It has previously been an open problem whether all Boolean submodular fu...

Scalable Combinatorial Bayesian Optimization with Tractable Statistical models

We study the problem of optimizing expensive blackbox functions over com...

On the Reducibility of Submodular Functions

The scalability of submodular optimization methods is critical for their...