Approximate MRF inference using bounded treewidth subgraphs

Authors:
Alexander Fix;Joyce Chen;Endre Boros;Ramin Zabih
Affiliations:
Computer Science Department, Cornell University, Ithaca, New York;Computer Science Department, Cornell University, Ithaca, New York;RUTCOR, Rutgers University, New Brunswick, New Jersey;Computer Science Department, Cornell University, Ithaca, New York
Venue:
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Year:
2012

Citing 13
Cited 0

Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming

Journal of the ACM (JACM)
Learning Markov networks: maximum bounded tree-width graphs

SODA '01 Proceedings of the twelfth annual ACM-SIAM symposium on Discrete algorithms
Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pseudo-boolean optimization

Discrete Applied Mathematics
Approximating the value of two power proof systems, with applications to MAX 2SAT and MAX DICUT

ISTCS '95 Proceedings of the 3rd Israel Symposium on the Theory of Computing Systems (ISTCS'95)
What Energy Functions Can Be Minimizedvia Graph Cuts?

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Graph Cut Algorithm for Generalized Image Deconvolution

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Minimizing Nonsubmodular Functions with Graph Cuts-A Review

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Graphical Models, Exponential Families, and Variational Inference

Graphical Models, Exponential Families, and Variational Inference
Global Stereo Reconstruction under Second-Order Smoothness Priors

IEEE Transactions on Pattern Analysis and Machine Intelligence
libDAI: A Free and Open Source C++ Library for Discrete Approximate Inference in Graphical Models

The Journal of Machine Learning Research
A max-flow approach to improved lower bounds for quadratic unconstrained binary optimization (QUBO)

Discrete Optimization

Quantified Score

Hi-index	0.00

Visualization

Abstract

Graph cut algorithms [9], commonly used in computer vision, solve a first-order MRF over binary variables. The state of the art for this NP-hard problem is QPBO [1,2], which finds the values for a subset of the variables in the global minimum. While QPBO is very effective overall there are still many difficult problems where it can only label a small subset of the variables. We propose a new approach that, instead of optimizing the original graphical model, instead optimizes a tractable sub-model, defined as an energy function that uses a subset of the pairwise interactions of the original, but for which exact inference can be done efficiently. Our Bounded Treewidth Subgraph (k-BTS) algorithm greedily computes a large weight treewidth-k subgraph of the signed graph, then solves the energy minimization problem for this subgraph by dynamic programming. The edges omitted by our greedy method provide a per-instance lower bound. We demonstrate promising experimental results for binary deconvolution, a challenging problem used to benchmark QPBO [2]: our algorithm performs an order of magnitude better than QPBO or its common variants [4], both in terms of energy and accuracy, and the visual quality of our output is strikingly better as well. We also obtain a significant improvement in energy and accuracy on a stereo benchmark with 2nd order priors [5], although the improvement in visual quality is more modest. Our method's running time is comparable to QPBO.