Hierarchical Multi-Graphs Learning for Robust Group Re-Identification

TL;DR

This paper introduces a Hierarchical Multi-Graphs Learning framework for robust group re-identification, modeling complex intra-group relationships with multi-relational graphs and a multi-scale matching algorithm, achieving state-of-the-art results.

Contribution

The paper proposes a novel hierarchical multi-graphs approach combined with a multi-scale matching algorithm to improve group re-identification accuracy and robustness.

Findings

Achieves state-of-the-art performance on CSG and RoadGroup benchmarks.

Improves Rank-1 accuracy by 1.7% and 2.5% over existing methods.

Effectively models complex group dynamics with multi-relational graphs.

Abstract

Group Re-identification (G-ReID) faces greater complexity than individual Re-identification (ReID) due to challenges like mutual occlusion, dynamic member interactions, and evolving group structures. Prior graph-based approaches have aimed to capture these dynamics by modeling the group as a single topological structure. However, these methods struggle to generalize across diverse group compositions, as they fail to fully represent the multifaceted relationships within the group. In this study, we introduce a Hierarchical Multi-Graphs Learning (HMGL) framework to address these challenges. Our approach models the group as a collection of multi-relational graphs, leveraging both explicit features (such as occlusion, appearance, and foreground information) and implicit dependencies between members. This hierarchical representation, encoded via a Multi-Graphs Neural Network (MGNN), allows us to resolve ambiguities in member relationships, particularly in complex, densely populated scenes. To further enhance matching accuracy, we propose a Multi-Scale Matching (MSM) algorithm, which mitigates issues of member information ambiguity and sensitivity to hard samples, improving robustness in challenging scenarios. Our method achieves state-of-the-art performance on two standard benchmarks, CSG and RoadGroup, with Rank-1/mAP scores of 95.3%/94.4% and 93.9%/95.4%, respectively. These results mark notable improvements of 1.7% and 2.5% in Rank-1 accuracy over existing approaches.