DGAOT: Dynamic Graph Attention With Optimal Transport Based Re-Ranking for Mobile Robot Visual Place Recognition

A two-stage pipeline is widely used in Visual Place Recognition (VPR) for mobile robotics to improve robustness under challenging conditions. It typically consists of two steps:descriptor generationandre-ranking. In descriptor generation, a backbone network generates descriptors for the query and database images. Then, re-ranking performs three steps: 1) top-kcandidate descriptors are selected from the database; 2) these candidates are aggregated into a global descriptor; 3) are-orderedlist of candidates is returned according to similarity scores against the global descriptor. However, current re-ranking methods suffer from two critical limitations: 1) False Positive Aggregation: Under texture variations, positive and negative database samples may produce similar descriptors. As a result, some negative samples may be selected into re-ranking, contaminating the aggregation and hence incorrect top-ksimilarity scores. 2) Limited Similarity Correction: Most re-ordering is typically non-differentiable so thatnomatching error can be back-propagated to train the re-ranking stage to learn calibrated similarity scores during network training. To address these issues, we propose a novel re-ranking framework called Dynamic Graph Attention Optimal Transport (DGAOT), comprising two key re-ranking modules built upon optimal transport theory. First, a Dynamic Graph Aggregation (DGA) module is designed to convert the pairwise affinities of the top-kquery–candidate graph into an OT-constrained joint coupling, down-weight the falsely selected candidates and aggregate the descriptors under consistent distributional patterns, improving the robustness to texture variations. Second, Differentiable Reordering Layer (DRL) - a differentiable score calibration layer is designed to perform differentiable score re-allocation via Sinkhorn iterations. Finally, a new Coarse-to-fine Average Precision (CFAP) loss is proposed to supervise DGA and DRL, enabling end-to-end re-ranking. Extensive experiments show that DGAOT achieves high retrieval performance, by about 5.3% relative and 3.35% absolute improvement in R@1 on average.