Quadratic programming relaxations for metric labeling and Markov random field MAP estimation
ICML '06 Proceedings of the 23rd international conference on Machine learning
Structured Prediction, Dual Extragradient and Bregman Projections
The Journal of Machine Learning Research
Approximation algorithms for labeling hierarchical taxonomies
Proceedings of the nineteenth annual ACM-SIAM symposium on Discrete algorithms
Sdp gaps and ugc hardness for multiway cut, 0-extension, and metric labeling
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
Proceedings of the 25th international conference on Machine learning
Efficient MRF deformation model for non-rigid image matching
Computer Vision and Image Understanding
ESA '08 Proceedings of the 16th annual European symposium on Algorithms
Packing multiway cuts in capacitated graphs
SODA '09 Proceedings of the twentieth Annual ACM-SIAM Symposium on Discrete Algorithms
Graphical Models, Exponential Families, and Variational Inference
Foundations and Trends® in Machine Learning
The Design of Competitive Online Algorithms via a Primal: Dual Approach
Foundations and Trends® in Theoretical Computer Science
Message-passing for Graph-structured Linear Programs: Proximal Methods and Rounding Schemes
The Journal of Machine Learning Research
MAP estimation of semi-metric MRFs via hierarchical graph cuts
UAI '09 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence
Energy minimization under constraints on label counts
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Improved Moves for Truncated Convex Models
The Journal of Machine Learning Research
Metric labeling and semi-metric embedding for protein annotation prediction
RECOMB'11 Proceedings of the 15th Annual international conference on Research in computational molecular biology
Efficient algorithms for segmenting globally optimal and smooth multi-surfaces
IPMI'11 Proceedings of the 22nd international conference on Information processing in medical imaging
Proceedings of the 3rd Innovations in Theoretical Computer Science Conference
Algorithm for single allocation problem on hub-and-spoke networks in 2-dimensional plane
ISAAC'11 Proceedings of the 22nd international conference on Algorithms and Computation
Shape-Based Object Detection via Boundary Structure Segmentation
International Journal of Computer Vision
Nonmetric priors for continuous multilabel optimization
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Simplex partitioning via exponential clocks and the multiway cut problem
Proceedings of the forty-fifth annual ACM symposium on Theory of computing
Proceedings of the 2nd International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications
Hi-index | 0.00 |
We consider approximation algorithms for the metric labeling problem. This problem was introduced in a paper by Kleinberg and Tardos [J. ACM, 49 (2002), pp. 616--630] and captures many classification problems that arise in computer vision and related fields. They gave an O(log k log log k) approximation for the general case, where k is the number of labels, and a 2-approximation for the uniform metric case. (In fact, the bound for general metrics can be improved to O(log k) by the work of Fakcheroenphol, Rao, and Talwar [Proceedings of the 35th Annual ACM Symposium on Theory of Computing, 2003, pp. 448--455].) Subsequently, Gupta and Tardos [Proceedings of the 32nd Annual ACM Symposium on the Theory of Computing, 2000, pp. 652--658] gave a 4-approximation for the truncated linear metric, a metric motivated by practical applications to image restoration and visual correspondence. In this paper we introduce an integer programming formulation and show that the integrality gap of its linear relaxation either matches or improves the ratios known for several cases of the metric labeling problem studied until now, providing a unified approach to solving them. In particular, we show that the integrality gap of our linear programming (LP) formulation is bounded by O(log k) for a general k-point metric and 2 for the uniform metric, thus matching the known ratios. We also develop an algorithm based on our LP formulation that achieves a ratio of $2+\sqrt{2}\simeq 3.414$ for the truncated linear metric improving the earlier known ratio of 4. Our algorithm uses the fact that the integrality gap of the LP formulation is 1 on a linear metric.