Log In Sign Up

MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models

by   Siddharth Tourani, et al.

Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications. This work introduces a new MAP-solver, based on the popular Dual Block-Coordinate Ascent principle. Surprisingly, by making a small change to the low-performing solver, the Max Product Linear Programming (MPLP) algorithm, we derive the new solver MPLP++ that significantly outperforms all existing solvers by a large margin, including the state-of-the-art solver Tree-Reweighted Sequential (TRWS) message-passing algorithm. Additionally, our solver is highly parallel, in contrast to TRWS, which gives a further boost in performance with the proposed GPU and multi-thread CPU implementations. We verify the superiority of our algorithm on dense problems from publicly available benchmarks, as well, as a new benchmark for 6D Object Pose estimation. We also provide an ablation study with respect to graph density.


page 1

page 2

page 3

page 4


Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization

We consider the maximum-a-posteriori inference problem in discrete graph...

Maximum Persistency via Iterative Relaxed Inference with Graphical Models

We consider the NP-hard problem of MAP-inference for undirected discrete...

A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching

We study the quadratic assignment problem, in computer vision also known...

Efficient semidefinite-programming-based inference for binary and multi-class MRFs

Probabilistic inference in pairwise Markov Random Fields (MRFs), i.e. co...

Dual coordinate solvers for large-scale structural SVMs

This manuscript describes a method for training linear SVMs (including b...

Efficient Linear Programming for Dense CRFs

The fully connected conditional random field (CRF) with Gaussian pairwis...

Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

We present an efficient approximate message passing solver for the lifte...