# Person Re-Identification via Generalized Class Prototypes

arXiv: https://arxiv.org/abs/2510.17043 · HTML: https://mlsanity.com/paper/2510.17043/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 19 Oct 2025.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification](https://mlsanity.com/paper/1906.08332/) (2019)
- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [Camera Style Adaptation for Person Re-identification](https://mlsanity.com/paper/1711.10295/) (2017)
- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [NFormer: Robust Person Re-identification with Neighbor Transformer](https://mlsanity.com/paper/2204.09331/) (2022)
- [Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification](https://mlsanity.com/paper/1803.09882/) (2018)
- [Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification](https://mlsanity.com/paper/1903.09776/) (2019)
- [Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification](https://mlsanity.com/paper/1803.09937/) (2018)
- [Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions](https://mlsanity.com/paper/2306.07520/) (2023)
- [Spatial-Temporal Person Re-identification](https://mlsanity.com/paper/1812.03282/) (2018)
- [On the Unreasonable Effectiveness of Centroids in Image Retrieval](https://mlsanity.com/paper/2104.13643/) (2021)
- [Combined Depth Space based Architecture Search For Person Re-identification](https://mlsanity.com/paper/2104.04163/) (2021)
- [End-to-End Comparative Attention Networks for Person Re-identification](https://mlsanity.com/paper/1606.04404/) (2016)
- [Quality Aware Network for Set to Set Recognition](https://mlsanity.com/paper/1704.03373/) (2017)
- [In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation](https://mlsanity.com/paper/1912.07863/) (2019)
- [Hetero-Center Loss for Cross-Modality Person Re-Identification](https://mlsanity.com/paper/1910.09830/) (2019)
- [Incomplete Descriptor Mining with Elastic Loss for Person Re-Identification](https://mlsanity.com/paper/2008.04010/) (2020)
- [Centroid-based deep metric learning for speaker recognition](https://mlsanity.com/paper/1902.02375/) (2019)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [Beyond Triplet Loss: Meta Prototypical N-tuple Loss for Person Re-identification](https://mlsanity.com/paper/2006.04991/) (2020)
- [Analysis of Farthest Point Sampling for Approximating Geodesics in a Graph](https://mlsanity.com/paper/1311.4665/) (2013)

## Abstract (arXiv)

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.