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...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 07. Aug.
1. Verfasser: Zhou, Jiahuan (VerfasserIn)
Weitere Verfasser: Xu, Kunlun, Zhuo, Fan, Zou, Xu, Peng, Yuxin
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM390801674
003 DE-627
005 20250808232354.0
007 cr uuu---uuuuu
008 250808s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3597023  |2 doi 
028 5 2 |a pubmed25n1524.xml 
035 |a (DE-627)NLM390801674 
035 |a (NLM)40773395 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zhou, Jiahuan  |e verfasserin  |4 aut 
245 1 0 |a Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 07.08.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a 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 
650 4 |a Journal Article 
700 1 |a Xu, Kunlun  |e verfasserin  |4 aut 
700 1 |a Zhuo, Fan  |e verfasserin  |4 aut 
700 1 |a Zou, Xu  |e verfasserin  |4 aut 
700 1 |a Peng, Yuxin  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2025) vom: 07. Aug.  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:07  |g month:08 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3597023  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2025  |b 07  |c 08