paper-with-me

Papers

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

2020-04-16 · ECCV 2018 9 · Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy

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.

📄 PDF Abstract BibTeX arXiv:2004.08227

Code (0)

등록된 구현이 없습니다.

Tasks

6D Pose Estimation using RGBCPUGPUPose Estimation

Similar Papers 제목 키워드 기반

A Forest Mixture Bound for Block-Free Parallel Inference

2018-05-17 · Neal Lawton, Aram Galstyan, Greg Ver Steeg

Coordinate ascent variational inference is an important algorithm for inference in probabilistic models, but it is slow because it updates only a single variable at a time. Block coordinate methods perform inference fast…

Variational Inference

On Coordinate Minimization of Convex Piecewise-Affine Functions

2017-09-14 · Tomas Werner

A popular class of algorithms to optimize the dual LP relaxation of the discrete energy minimization problem (a.k.a.\ MAP inference in graphical models or valued constraint satisfaction) are convergent message-passing al…

Stochastic Parallel Block Coordinate Descent for Large-scale Saddle Point Problems

2015-11-23 · Zhanxing Zhu, Amos J. Storkey

We consider convex-concave saddle point problems with a separable structure and non-strongly convex functions. We propose an efficient stochastic block coordinate descent method using adaptive primal-dual updates, which …

feature selection

Asynchronous parallel primal-dual block coordinate update methods for affinely constrained convex programs

2017-05-18 · Yangyang Xu

Recent several years have witnessed the surge of asynchronous (async-) parallel computing methods due to the extremely big data involved in many modern applications and also the advancement of multi-core machines and com…

MPLP: Learning a Message Passing Learning Protocol

2020-07-02 · Ettore Randazzo, Eyvind Niklasson, Alexander Mordvintsev

We present a novel method for learning the weights of an artificial neural network - a Message Passing Learning Protocol (MPLP). In MPLP, we abstract every operations occurring in ANNs as independent agents. Each agent i…