Distribution-aware Knowledge Unification and Association for Non-exemplar Lifelong Person Re-identification

2025-08-05

AI Summary

Lifelong person re-identification (LReID) faces the fundamental challenge of balancing catastrophic forgetting of previously learned knowledge with effective adaptation to new domains. To address this, we propose a sample-free continual learning framework—the first to jointly model domain-specific distributions and a cross-domain unified representation. Our approach introduces four core mechanisms: distribution-aware modeling, adaptive knowledge consolidation (AKC), unified knowledge association (UKA), and distribution-based knowledge transfer (DKT), enabling distribution-aware knowledge integration and cross-domain semantic alignment. Extensive experiments on multiple benchmarks demonstrate consistent improvements: average mAP and Rank-1 accuracy increase by 7.6% and 5.3%, respectively, outperforming state-of-the-art methods. The proposed framework significantly enhances anti-forgetting capability and cross-domain generalization performance without requiring storage of historical training samples.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Computer Vision: Representation Learning for Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Lifelong person re-identification (LReID) encounters a key challenge: balancing the preservation of old knowledge with adaptation to new information. Existing LReID methods typically employ knowledge distillation to enforce representation alignment. However, these approaches ignore two crucial aspects: specific distribution awareness and cross-domain unified knowledge learning, both of which are essential for addressing this challenge. To overcome these limitations, we propose a novel distribution-aware knowledge unification and association (DKUA) framework where domain-style modeling is performed for each instance to propagate domain-specific representations, enhancing anti-forgetting and generalization capacity. Specifically, we design a distribution-aware model to transfer instance-level representations of the current domain into the domain-specific representations with the different domain styles, preserving learned knowledge without storing old samples. Next, we propose adaptive knowledge consolidation (AKC) to dynamically generate the unified representation as a cross-domain representation center. To further mitigate forgetting, we develop a unified knowledge association (UKA) mechanism, which explores the unified representation as a bridge to explicitly model inter-domain associations, reducing inter-domain gaps. Finally, distribution-based knowledge transfer (DKT) is proposed to prevent the current domain distribution from deviating from the cross-domain distribution center, improving adaptation capacity. Experimental results show our DKUA outperforms the existing methods by 7.6%/5.3% average mAP/R@1 improvement on anti-forgetting and generalization capacity, respectively. Our code will be publicly released.

Problem

• Balancing old knowledge preservation with new information adaptation in lifelong person re-identification
• Addressing lack of distribution awareness and cross-domain unified knowledge learning
• Mitigating forgetting and improving generalization in non-exemplar lifelong re-identification

Innovation

• Domain-style modeling for instance-specific representations
• Adaptive knowledge consolidation for unified representation
• Unified knowledge association to reduce inter-domain gaps