Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification

Lifelong Person Re-identification (LReID) suffers from a key challenge in preserving old knowledge while adapting to new information. The existing solutions include rehearsal based and rehearsal-free methods to address this challenge. Rehearsal-based approaches rely on knowledge distillation, continuously accumulating forgetting during the distillation process. Rehearsal-free methods insufficiently learn domain-specific distributions, leading to forgetfulness over time. To solve these issues, we propose a novel Distribution-aware Forgetting Compensation (DAFC) model that explores cross-domain shared representation learning, and domain-specific distribution awareness without using old exemplars or knowledge distillation. We propose a Text-driven Prompt Aggregation (TPA) that utilizes text features to enrich prompt components and guide the prompt model to learn fine-grained instance-level representations. This can enhance discriminative identity information and establish the foundation for domain distribution awareness. Then, Distribution based Awareness and Integration (DAI) is designed to explore domain-specific distribution learning using the Domain-specific Generator (DSG) and dynamically consolidate all style-specific representations of each instance into a shared representation through the Knowledge Adaptive Adjustment (KAA) strategy, which alleviates catastrophic forgetting. Furthermore, we develop a Knowledge Consolidation Mechanism (KCM) that comprises instance-level discrimination and cross-domain consistency alignment strategies to facilitate model adaptive learning of new knowledge from the current domain and promote knowledge consolidation learning between acquired domain-specific distributions, respectively. Experimental results show that our DAFC outperforms state-of-the-art methods on two training orders, demonstrating anti-forgetting and generalization capacity. Our code is available at https://github.com/LiuShiBen/DAFC.