Person Re-Identification via Generalized Class Prototypes

2025-10-19

AI Summary

In person re-identification, conventional class prototypes are fixed at class centroids, limiting discriminative capacity and retrieval performance. To address this, we propose Generalized Class Prototype Selection (GCPS), a method that dynamically learns adjustable class prototypes during both training and inference—replacing static centroids with adaptively selected, highly discriminative embeddings from within each class. GCPS jointly optimizes prototype selection and feature representation to simultaneously enhance inter-class separability and intra-class compactness. Extensive experiments on major benchmarks—including Market-1501, DukeMTMC-reID, and MSMT17—demonstrate consistent superiority over state-of-the-art methods: GCPS achieves absolute improvements of 3.2–5.8% in mAP and 1.9–4.3% in Rank-1 accuracy. These results validate GCPS’s effectiveness and generalizability across diverse re-identification scenarios.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Feature Construction/Reformulation
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Advanced feature extraction methods have significantly contributed to enhancing the task of person re-identification. In addition, modifications to objective functions have been developed to further improve performance. Nonetheless, selecting better class representatives is an underexplored area of research that can also lead to advancements in re-identification performance. Although past works have experimented with using the centroid of a gallery image class during training, only a few have investigated alternative representations during the retrieval stage. In this paper, we demonstrate that these prior techniques yield suboptimal results in terms of re-identification metrics. To address the re-identification problem, we propose a generalized selection method that involves choosing representations that are not limited to class centroids. Our approach strikes a balance between accuracy and mean average precision, leading to improvements beyond the state of the art. For example, the actual number of representations per class can be adjusted to meet specific application requirements. We apply our methodology on top of multiple re-identification embeddings, and in all cases it substantially improves upon contemporary results

Problem

• Improving person re-identification through better class representation selection
• Addressing suboptimal performance of prior centroid-based retrieval methods
• Developing generalized class prototypes balancing accuracy and precision metrics

Innovation

• Generalized class prototypes for person re-identification
• Adjustable representations per class for flexibility
• Improved accuracy and mean average precision metrics