A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting

Abstract

This paper addresses the problem of matching $N$ weighted graphs referring to an identical object or category. More specifically, matching the common node correspondences among graphs. This multi-graph matching problem involves two ingredients affecting the overall accuracy: i) the local pairwise matching affinity score among graphs; ii) the global matching consistency that measures the uniqueness of the pairwise matching results by different chaining orders. Previous studies typically either enforce the matching consistency constraints in the beginning of iterative optimization, which may propagate matching error both over iterations and across graph pairs; or separate affinity optimizing and consistency regularization in two steps. This paper is motivated by the observation that matching consistency can serve as a regularizer in the affinity objective function when the function is biased due to noises or inappropriate modeling. We propose multi-graph matching methods to incorporate the two aspects by boosting the affinity score, meanwhile gradually infusing the consistency as a regularizer. Furthermore, we propose a node-wise consistency/affinity-driven mechanism to elicit the common inlier nodes out of the irrelevant outliers. Extensive results on both synthetic and public image datasets demonstrate the competency of the proposed algorithms.

Cited by in corpus (20)

• Exploiting Global Camera Network Constraints for Unsupervised Video Person Re-identification
• Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope
• Synchronisation of Partial Multi-Matchings via Non-negative Factorisations
• Visual analytics for networked-guarantee loans risk management
• Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching
• Applying graph matching techniques to enhance reuse of plant design information
• Multi-Image Matching via Fast Alternating Minimization
• AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
• Robust Multi-object Matching via Iterative Reweighting of the Graph Connection Laplacian
• Multi-Image Semantic Matching by Mining Consistent Features
• Initialization and Coordinate Optimization for Multi-way Matching
• MIXER: Multiattribute, Multiway Fusion of Uncertain Pairwise Affinities
• Smooth Deformation Field-based Mismatch Removal in Real-time
• Distributable Consistent Multi-Object Matching
• Deep Momentum Uncertainty Hashing
• Graph-Based Parallel Large Scale Structure from Motion
• MIXER: A Principled Framework for Multimodal, Multiway Data Association
• Higher-order Projected Power Iterations for Scalable Multi-Matching
• Consistent Multiple Graph Matching with Multi-layer Random Walks Synchronization
• Isometric Multi-Shape Matching