Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification
- 7 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 10932-10948
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (62376011, 62525201, 62132001, 62432001)
- Beijing Natural Science Foundation (L247006)
- National Key R&D Program of China (2024YFA1410000)
This publication has 76 references indexed in Scilit:
- PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification2022
- Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic SegmentationInternational Journal of Computer Vision, 2021
- Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification2020
- DeeSIL: Deep-Shallow Incremental Learning2019
- Performance Measures and a Data Set for Multi-target, Multi-camera Tracking2016
- Human Reidentification with Transferred Metric Learning2013
- Person Re-identification by Descriptive and Discriminative Classification2011
- Time-Delayed Correlation Analysis for Multi-Camera Activity UnderstandingInternational Journal of Computer Vision, 2010
- Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features2008
- On the Cauchy-Schwarz InequalityJournal of Mathematical Analysis and Applications, 1999