Abstract
Lifelong person re-identification (LReID) aims to incrementally accumulate knowledge across a sequence of tasks under domain shifts. Recently, replay-based methods have demonstrated strong effectiveness in LReID by rehearsing past samples stored in an auxiliary memory. However, storing historical exemplars raises concerns over data privacy. To avoid this, exemplar-free approaches attempt to match the distribution of past data without storing raw samples. Despite being privacy-friendly, these methods often suffer from performance degradation due to the forgetting of specific past knowledge representations. To this end, we propose to condense information from sequential data into the pixel space in the replay memory, enabling Privacy-Preserving Replay (Pr^2R). More specifically, by distilling the training characteristics of multiple real images into a single image, the condensed samples undergo pixel-level changes. This not only protects the privacy of the original data but also makes the replay samples more representative for sequential tasks. During the style replay phase, we align the current domain to the previous one while simultaneously adapting the replay samples to match the style of the current domain. This dual-alignment strategy effectively mitigates both class-incremental challenges and forgetting caused by domain shifts. Extensive experiments on multiple benchmarks show that the proposed method significantly improves replay effectiveness while preserving data privacy. Specifically, Pr^2R achieves 4% and 6% higher accuracy on sequential tasks compared to the current state-of-the-art and other replay-based methods, respectively.
Abstract (translated)
终身人员重识别（LReID）的目标是在领域变化的序列任务中逐步积累知识。最近，基于重放的方法通过在辅助记忆中存储过去的样本进行回放，在LReID中展示了很强的有效性。然而，存储历史示例引发了数据隐私方面的担忧。为了避免这种情况，无示例方法尝试匹配过去数据的分布而不存储原始样本。尽管这些方法对隐私友好，但由于忘记了特定的过去知识表示，它们通常会因性能下降而受到困扰。 为此，我们提出了一种将顺序数据的信息浓缩到重放记忆中的像素空间的方法，从而实现隐私保护型重放（Pr^2R）。具体而言，通过将多个真实图像的训练特征提炼成单个图像，浓缩后的样本在像素级别发生变化。这不仅保护了原始数据的隐私，还使重播样本更具有代表性以应对序列任务。在风格重放阶段，我们将当前领域与先前领域对齐的同时适应性地调整重放样本，使其符合当前领域的样式。这种双对齐策略有效地缓解了增量分类问题以及由领域变化引起的遗忘现象。 多项基准测试的广泛实验表明，所提出的方法显著提高了重放的有效性，同时保持数据隐私。具体而言，在序列任务上，Pr^2R相比目前最先进的方法和其它基于重播的方法分别取得了4%和6%更高的准确率。
URL
https://arxiv.org/abs/2508.01587
