DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification

Lifelong person re-identification (LReID) is an important but challenging task that suffers from catastrophic forgetting due to significant domain gaps between training steps. Existing LReID approaches typically rely on data replay and knowledge distillation to mitigate this issue. However, data replay methods compromise data privacy by storing historical exemplars, while knowledge distillation methods suffer from limited performance due to the cumulative forgetting of undistilled knowledge. To overcome these challenges, we propose a novel paradigm that models and rehearses the distribution of the old domains to enhance knowledge consolidation during the new data learning, possessing a strong anti-forgetting capacity without storing any exemplars. Specifically, we introduce an exemplar-free LReID method called Distribution Rehearsing via Adaptive Style Kernel Learning (DASK). DASK includes a Distribution Rehearser Learning (DRL) mechanism that learns to transform arbitrary distribution data into the current data style at each learning step. To enhance the style transfer capacity of DRL, an Adaptive Kernel Prediction Network (AKPNet) is explored to achieve an instance-specific distribution adjustment. Additionally, we design a Distribution Rehearsingdriven LReID Training (DRRT) module, which rehearses old distribution based on the new data via the old AKP-Net model, achieving effective new-old knowledge accumulation under a joint knowledge consolidation scheme. Experimental results show our DASK outperforms the existing methods by 3.6%-6.8% and 4.5%-6.5% on anti-forgetting and generalization capacity, respectively. Our code is available at https://github.com/zhoujiahuan1991/AAAI2025- LReID-DASK * Corresponding author Domain 𝒕-1 Domain 𝒕 (a) Knowledge of Different Domains Model 𝒕 (b) Knowledge Distillation-based Method Knowledge of Domain 𝒕-1 Knowledge of Domain 𝒕 Sample of Domain 𝒕-1 Sample of Domain 𝒕 Knowledge of Model 𝒕 Model 𝒕 (c) Replay-based Method Exemplar Buffer 𝑡-1 Model 𝒕 (d) Distribution Rehearsing (Ours) Distribution Rehearsing Module 𝑡-1 Privacy Generated Sample of Domain 𝒕-1 Style