不存样本也能防遗忘，用风格化分布重演提升持续识人能力
DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification
- 通过自适应风格核学习，将旧数据分布转换为当前风格进行无样本重演
- 在两个评估维度上分别提升3.6%-6.8%和4.5%-6.5%的性能表现
- 适合长期运行、需保护隐私的行人再识别系统应用
终身行人再识别（LReID）因训练阶段间存在显著领域差异，易受灾难性遗忘影响。现有方法多依赖数据重放或知识蒸馏缓解此问题，但前者侵犯数据隐私，后者受限于未蒸馏知识的累积遗忘。为此，我们提出一种新范式：通过建模并重演旧领域分布来增强新数据学习中的知识固化，具备强抗遗忘能力且无需存储任何样本。具体提出无样本LReID方法DASK，包含分布重演学习（DRL）机制，可将任意分布数据在每步学习中转换为当前数据风格；为增强风格迁移能力，引入自适应核预测网络（AKPNet），实现实例级分布调整；同时设计分布重演驱动的训练模块（DRRT），基于新数据通过旧AKPNet模型重演旧分布，在联合知识固化框架下实现高效新旧知识融合。实验表明，DASK在抗遗忘与泛化能力上均优于现有方法3.6%-6.8%和4.5%-6.5%。代码已开源。
原文摘要 · Abstract (English)
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 Rehearsing-driven LReID Training (DRRT) module, which rehearses old distribution based on the new data via the old AKPNet 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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。