Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-12 · 47 (12) · 10932-10948
DOI: 10.1109/tpami.2025.3597023 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-12. Verfasst von Jiahuan Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation, National Key R&D Program of China.
Abstract (Originalsprache)
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.
Förderung
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
- National Key R&D Program of China
Zitieren
APA
Zhou, J., Xu, K., Zhuo, F., Zou, X., & Peng, Y. (2025). Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(12), 10932-10948. https://doi.org/10.1109/tpami.2025.3597023
Vancouver
Zhou J, Xu K, Zhuo F, Zou X, Peng Y. Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(12):10932-10948. doi:10.1109/tpami.2025.3597023
BibTeX
@article{Zhou2025,
author = {Zhou, Jiahuan and Xu, Kunlun and Zhuo, Fan and Zou, Xu and Peng, Yuxin},
title = {Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {12},
pages = {10932--10948},
doi = {10.1109/tpami.2025.3597023}
}
EUVIMED