Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
This work provides an incremental improvement in outlier-robust graph matching, which is a problem for various computer vision and pattern recognition applications.
This paper addresses the challenge of outliers in deep graph matching by proposing RGM, a deep reinforcement learning approach with a revocable action framework. It also introduces a quadratic approximation technique to regularize affinity scores, allowing timely inlier matching without needing to pre-specify the number of inliers. Experiments on real-world datasets show improved accuracy and robustness.
Graph matching (GM) has been a building block in various areas including computer vision and pattern recognition. Despite recent impressive progress, existing deep GM methods often have obvious difficulty in handling outliers, which are ubiquitous in practice. We propose a deep reinforcement learning based approach RGM, whose sequential node matching scheme naturally fits the strategy for selective inlier matching against outliers. A revocable action framework is devised to improve the agent's flexibility against the complex constrained GM. Moreover, we propose a quadratic approximation technique to regularize the affinity score, in the presence of outliers. As such, the agent can finish inlier matching timely when the affinity score stops growing, for which otherwise an additional parameter i.e. the number of inliers is needed to avoid matching outliers. In this paper, we focus on learning the back-end solver under the most general form of GM: the Lawler's QAP, whose input is the affinity matrix. Especially, our approach can also boost existing GM methods that use such input. Experiments on multiple real-world datasets demonstrate its performance regarding both accuracy and robustness.