Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Kunlun, Zhuo, Fan, Li, Jiangmeng, Zou, Xu, Zhou, Jiahuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915407274704896
author Xu, Kunlun
Zhuo, Fan
Li, Jiangmeng
Zou, Xu
Zhou, Jiahuan
author_facet Xu, Kunlun
Zhuo, Fan
Li, Jiangmeng
Zou, Xu
Zhou, Jiahuan
contents Current lifelong person re-identification (LReID) methods predominantly rely on fully labeled data streams. However, in real-world scenarios where annotation resources are limited, a vast amount of unlabeled data coexists with scarce labeled samples, leading to the Semi-Supervised LReID (Semi-LReID) problem where LReID methods suffer severe performance degradation. Existing LReID methods, even when combined with semi-supervised strategies, suffer from limited long-term adaptation performance due to struggling with the noisy knowledge occurring during unlabeled data utilization. In this paper, we pioneer the investigation of Semi-LReID, introducing a novel Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation framework (SPRED). Our key innovation lies in establishing a self-reinforcing cycle between dynamic prototype-guided pseudo-label generation and new-old knowledge collaborative purification to enhance the utilization of unlabeled data. Specifically, learnable identity prototypes are introduced to dynamically capture the identity distributions and generate high-quality pseudo-labels. Then, the dual-knowledge cooperation scheme integrates current model specialization and historical model generalization, refining noisy pseudo-labels. Through this cyclic design, reliable pseudo-labels are progressively mined to improve current-stage learning and ensure positive knowledge propagation over long-term learning. Experiments on the established Semi-LReID benchmarks show that our SPRED achieves state-of-the-art performance. Our source code is available at https://github.com/zhoujiahuan1991/ICCV2025-SPRED
format Preprint
id arxiv_https___arxiv_org_abs_2507_01884
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
Xu, Kunlun
Zhuo, Fan
Li, Jiangmeng
Zou, Xu
Zhou, Jiahuan
Computer Vision and Pattern Recognition
Current lifelong person re-identification (LReID) methods predominantly rely on fully labeled data streams. However, in real-world scenarios where annotation resources are limited, a vast amount of unlabeled data coexists with scarce labeled samples, leading to the Semi-Supervised LReID (Semi-LReID) problem where LReID methods suffer severe performance degradation. Existing LReID methods, even when combined with semi-supervised strategies, suffer from limited long-term adaptation performance due to struggling with the noisy knowledge occurring during unlabeled data utilization. In this paper, we pioneer the investigation of Semi-LReID, introducing a novel Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation framework (SPRED). Our key innovation lies in establishing a self-reinforcing cycle between dynamic prototype-guided pseudo-label generation and new-old knowledge collaborative purification to enhance the utilization of unlabeled data. Specifically, learnable identity prototypes are introduced to dynamically capture the identity distributions and generate high-quality pseudo-labels. Then, the dual-knowledge cooperation scheme integrates current model specialization and historical model generalization, refining noisy pseudo-labels. Through this cyclic design, reliable pseudo-labels are progressively mined to improve current-stage learning and ensure positive knowledge propagation over long-term learning. Experiments on the established Semi-LReID benchmarks show that our SPRED achieves state-of-the-art performance. Our source code is available at https://github.com/zhoujiahuan1991/ICCV2025-SPRED
title Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.01884