MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification

TL;DR

The paper introduces MGH, an unsupervised person re-identification method that leverages auxiliary metadata to construct hypergraphs for improved feature learning and label refinement, outperforming existing approaches.

Contribution

It proposes a novel hypergraph-based framework utilizing metadata for unsupervised person ReID, including a label refinement process and a memory-based listwise loss for better optimization.

Findings

Outperforms state-of-the-art on three benchmarks.

Effectively refines labels using hypergraph propagation.

Demonstrates the value of metadata in unsupervised ReID.

Abstract

As a challenging task, unsupervised person ReID aims to match the same identity with query images which does not require any labeled information. In general, most existing approaches focus on the visual cues only, leaving potentially valuable auxiliary metadata information (e.g., spatio-temporal context) unexplored. In the real world, such metadata is normally available alongside captured images, and thus plays an important role in separating several hard ReID matches. With this motivation in mind, we propose~\textbf{MGH}, a novel unsupervised person ReID approach that uses meta information to construct a hypergraph for feature learning and label refinement. In principle, the hypergraph is composed of camera-topology-aware hyperedges, which can model the heterogeneous data correlations across cameras. Taking advantage of label propagation on the hypergraph, the proposed approach is able to effectively refine the ReID results, such as correcting the wrong labels or smoothing the noisy labels. Given the refined results, We further present a memory-based listwise loss to directly optimize the average precision in an approximate manner. Extensive experiments on three benchmarks demonstrate the effectiveness of the proposed approach against the state-of-the-art.