Efficient and Flexible Sublabel-Accurate Energy Minimization

Zhakshylyk Nurlanov, Daniel Cremers, Florian Bernard

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We address the problem of minimizing a class of energy functions consisting of data and smoothness terms that commonly occur in machine learning, computer vision, and pattern recognition. While discrete optimization methods are able to give theoretical optimality guarantees, they can only handle a finite number of labels and therefore suffer from label discretization bias. Existing continuous optimization methods can find sublabel-accurate solutions, but they are not efficient for large label spaces. In this work, we propose an efficient sublabel-accurate method that utilizes the best properties of both continuous and discrete models. We separate the problem into two sequential steps: (i) global discrete optimization for selecting the label range, and (ii) efficient continuous sublabel-accurate local refinement of a convex approximation of the energy function in the chosen range. Doing so allows us to achieve a boost in time and memory efficiency while practically keeping the accuracy at the same level as continuous convex relaxation methods, and in addition, providing theoretical optimality guarantees at the level of discrete methods. Finally, we show the flexibility of the proposed approach to general pairwise smoothness terms, so that it is applicable to a wide range of regularizations. Experiments on the illustrating example of the image denoising problem demonstrate the properties of the proposed method. The code reproducing experiments is available on https://github.com/nurlanov-zh/sublabel-accurate-alpha-expansion.

Original languageEnglish
Title of host publication2022 26th International Conference on Pattern Recognition, ICPR 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages175-181
Number of pages7
ISBN (Electronic)9781665490627
DOIs
StatePublished - 2022
Event26th International Conference on Pattern Recognition, ICPR 2022 - Montreal, Canada
Duration: 21 Aug 202225 Aug 2022

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2022-August
ISSN (Print)1051-4651

Conference

Conference26th International Conference on Pattern Recognition, ICPR 2022
Country/TerritoryCanada
CityMontreal
Period21/08/2225/08/22

Fingerprint

Dive into the research topics of 'Efficient and Flexible Sublabel-Accurate Energy Minimization'. Together they form a unique fingerprint.

Cite this