Reweighted Random Walks for Graph Matching

Cho, Minsu; Lee, Jungmin; Lee, Kyoung Mu

doi:10.1007/978-3-642-15555-0_36

Cited by 364 publications

(511 citation statements)

References 19 publications

Supporting

Mentioning

510

Contrasting

Order By: Relevance

“…The proposed algorithm (SMCM) was compared with seven state-of-the-art methods including SM [4], SMAC [16], PM [25], IPFP [5], GAGM [15], RRWM [6], and DDMCM [7]. The authors' implementations were used for SM, SMAC 1 , PM 2 , IPFP 3 , DDMCM, and RRWM 4 .…”

Section: Methodsmentioning

confidence: 99%

“…A graph matching solution M is represented by a set of assignments or matches The graph matching score of x is evaluated by x T Wx which corresponds to the sum of all similarity values covered by the matching. Therefore, graph matching is mathematically formulated as the following IQP problem [4,7,6]:…”

Section: Problem Definitionmentioning

confidence: 99%

“…The random graph matching experiments were performed following the experimental protocol of [16,15,6]. In this experiment, the Hungarian algorithm [26] was used for the post-processing of discretization, and τ = 2 is used for SMCM.…”

Section: Synthetic Random Graph Matchingmentioning

confidence: 99%

“…Due to the NP-hard nature of graph matching in general, its optimal solution is virtually unachievable so that a myriad of algorithms are proposed to approximate it. In recent computer vision literature, the graph matching problem is widely formulated as the Integer Quadratic Program (IQP) [4,5,6,7] that explicitly considers both local appearances and generic pairwise relations. This line of graph matching researches has further extended to hyper-graph matching [8,9], learning techniques [10,11], and its progressive framework [12].…”

Section: Introductionmentioning

confidence: 99%

“…Torresani et al [17] used dual decomposition technique for graph matching optimization. Cho et al [6] introduced a random walk algorithm to explore the relaxed solution space in the consideration of the matching constraints. More recently, to overcome the limitation of pair-wise relations and embed higher-order information, hyper-graph matching techniques were proposed based on the generalization of the IQP [8,9].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Graph Matching via Sequential Monte Carlo

Suh

Cho

Lee

2012

Computer Vision – ECCV 2012

Self Cite

View full text Add to dashboard Cite

Abstract. Graph matching is a powerful tool for computer vision and machine learning. In this paper, a novel approach to graph matching is developed based on the sequential Monte Carlo framework. By constructing a sequence of intermediate target distributions, the proposed algorithm sequentially performs a sampling and importance resampling to maximize the graph matching objective. Through the sequential sampling procedure, the algorithm effectively collects potential matches under one-to-one matching constraints to avoid the adverse effect of outliers and deformation. Experimental evaluations on synthetic graphs and real images demonstrate its higher robustness to deformation and outliers.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Problem Definitionmentioning

confidence: 99%

Section: Synthetic Random Graph Matchingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Graph Matching via Sequential Monte Carlo

Suh

Cho

Lee

2012

Computer Vision – ECCV 2012

Self Cite

View full text Add to dashboard Cite

show abstract

An efficient algorithm for bounded spectral matching with affine constraint

Dou

Chandrasekaran

2019

Numerical Linear Algebra App

View full text Add to dashboard Cite

Summary Graph matching problem appears frequently in the applications of computer vision and machine learning. In this work, based on the spectral matching with affine constraint (SMAC) formulation, we present a new formulation, named bounded SMAC (BSMAC), for the graph matching problem by adding an upper‐bound constraint on the solution norm. We demonstrate the existence of a unique solution with BSMAC, whereas SMAC needs not to have any meaningful solution in general. We develop an effective numerical method to solve the BSMAC formulation as an optimization problem. Numerical experiments are presented to verify feasibility and to show the performance of the proposed numerical method.

show abstract

Underwater place recognition using forward‐looking sonar images: A topological approach

Santos

Zaffari

Ribeiro

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

Autonomous underwater vehicles are a prominent tool for underwater exploration because they can access dangerous places avoiding the risks for the human beings.However, the autonomous navigation still a challenge due to the characteristics of the environment that decrease the performance of the sensor and the robot perception.In this context, this paper proposes a loop closure detector addressed to the simultaneous localization and mapping problem at semistructured environments using acoustic images acquired by forward-looking sonars. The images are segmented by an adaptative approach based on the acoustic beams analysis. A pose-invariant topological graph is build to represent the relationship between image features. The loop closure detection is achieved using a graph comparison. The approach is evaluated in a real environment at a marina. The results reveal all loop closures of the data set are detected with a high precision and present an invariant to image rotation.

show abstract

Reweighted Random Walks for Graph Matching

Cited by 364 publications

References 19 publications

Graph Matching via Sequential Monte Carlo

Graph Matching via Sequential Monte Carlo

An efficient algorithm for bounded spectral matching with affine constraint

Underwater place recognition using forward‐looking sonar images: A topological approach

Contact Info

Product

Resources

About