Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification

Lifelong person re-identification (LReID) suffers from the catastrophic forgetting problem when learning from non-stationary data streams. Existing exemplar-based and knowledge distillation-based LReID methods encounter data privacy and limited acquisition capacity, respectively. In this paper, we i...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 07. Aug.
Auteur principal: Zhou, Jiahuan (Auteur)
Autres auteurs: Xu, Kunlun, Zhuo, Fan, Zou, Xu, Peng, Yuxin
Format: Article en ligne
Langue:English
Publié: 2025
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
Description
Résumé:Lifelong person re-identification (LReID) suffers from the catastrophic forgetting problem when learning from non-stationary data streams. Existing exemplar-based and knowledge distillation-based LReID methods encounter data privacy and limited acquisition capacity, respectively. In this paper, we introduce the prototype, which is under-investigated in LReID, to better balance knowledge retention and acquisition. Previous prototype-based works primarily focused on the classification task, where prototypes were modeled as discrete points or statistical distributions. However, they either discarded the distribution information or omitted instance-level diversity, which are crucial fine-grained clues for LReID. Furthermore, the domain shifts between data sources result in a feature gap between the new and old data, which restricts the utilization of the fine-grained information in prototypes. To address these challenges, we propose Distribution-aware Knowledge Aligning and Prototyping (DKP++), a novel framework for modeling and leveraging prototypes in LReID. First, an Instance-level Distribution Modeling network is introduced to capture the local diversity of each instance. Next, a Distribution-oriented Prototype Generation algorithm transforms the instance-level diversity into identity-level distributions which are stored as prototypes. Then, a Prototype-based Knowledge Transfer module distills the knowledge within the prototypes to the new model. To mitigate the impact of domain shifts during knowledge transfer, we introduce a privacy-friendly Distribution Aligning module that transforms new input data to fit the historical distribution, which is incorporated with feature-level alignment constraints to enhance the coherence between new and old knowledge, effectively improving historical prototype utilization. Extensive experiments demonstrate that our method achieves a superior balance between plasticity and stability, outperforming state-of-the-art LReID methods by a large margin
Description:Date Revised 07.08.2025
published: Print-Electronic
Citation Status Publisher
ISSN:1939-3539
DOI:10.1109/TPAMI.2025.3597023