Efficient and Flexible Sublabel-Accurate Energy Minimization

by   Zhakshylyk Nurlanov, et al.

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 at <https://github.com/nurlanov-zh/sublabel-accurate-alpha-expansion>.


page 1

page 6


Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems

In this work we show how sublabel-accurate multilabeling approaches can ...

Sublabel-Accurate Relaxation of Nonconvex Energies

We propose a novel spatially continuous framework for convex relaxations...

Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies

Convex relaxations of nonconvex multilabel problems have been demonstrat...

A variational finite volume scheme for Wasserstein gradient flows

We propose a variational finite volume scheme to approximate the solutio...

Learning Discrete and Continuous Factors of Data via Alternating Disentanglement

We address the problem of unsupervised disentanglement of discrete and c...

Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization

Dense image matching is a fundamental low-level problem in Computer Visi...

Methods and Models for Interpretable Linear Classification

We present an integer programming framework to build accurate and interp...

Please sign up or login with your details

Forgot password? Click here to reset