Dynamic Magic：释放受限知识以实现终身行人重识别
Dynamic Magic: Unleashing Restricted Knowledge for Lifelong Person Re-Identification
把大预训练模型与动态扩展的模块化适配器结合，用域感知调度和相似度引导的自动选择器在推理时路由输入，为视觉里「持续学习新域又不遗忘旧域」提供了一套可复用的参数隔离+共享适配器协作框架。
原文依据 a novel dynamical expansion framework for LReID, which unleashes restricted knowledge during continuous learning by large pre-trained models
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论终身行人重识别的目标是在适应新域的同时保留旧知识。现有方法无论是基于蒸馏还是基于回放，都试图在固定的模型架构内整合多样化的知识。然而，这类架构的适应能力有限，往往会覆盖此前获得的知识，从而导致灾难性遗忘。为克服这一局限，我们提出通用增量适应（Versatile Incremental Adaptation, VIA），这是一种面向终身行人重识别的新型动态扩展框架，借助大预训练模型在持续学习过程中释放受限的知识。具体而言，VIA 中嵌入了未见域行人适配器（Unseen-domain person Adapter, UnA），它采用增量式模块化学习来捕获特定领域的知识，从而减少跨域干扰，并释放此前受静态参数共享所限制的任务专属容量。同时，考虑到终身行人重识别中不同域之间存在大量共享知识，我们设计了域感知调度（Domain-aware Dispatch）模块，通过多个共享适配器之间的自适应协作实现跨域协同与知识复用。此外，我们设计了整体域控制器（Holistic Domain Controller），依据知识相似度动态调节对新域的学习容量，从而有效释放预训练模型的泛化潜力。进一步地，我们提出轻量级的相似度引导自动选择器（Similarity-Guided Auto-Selector），在推理阶段自动将输入分配给相关的适配器。大量实验验证了 VIA 的有效性，其在已见域和未见域上均超越了最优方法。
英文原文摘要 1631 字符
Lifelong Person Re-Identification aims to adapt to new domains while preserving old knowledge. Existing methods, whether distillation-based or rehearsal-based, attempt to consolidate diverse knowledge within a fixed model architecture. However, the limited adaptability of such architectures often leads to catastrophic forgetting by overwriting previously acquired knowledge. To overcome this limitation, we propose Versatile Incremental Adaptation (VIA), a novel dynamical expansion framework for LReID, which unleashes restricted knowledge during continuous learning by large pre-trained models. Specifically, Unseen-domain person Adapter (UnA) is embedded in VIA, which employs incremental modular learning to capture the domain's specific knowledge, thereby reducing cross-domain interference and releasing task-specific capacity that is previously limited by static parameter sharing. Meanwhile, considering the substantial amount of sharing knowledge across domains in LReID, we design the Domain-aware Dispatch module to enable inter-domain collaboration and knowledge reuse through adaptive cooperation among multiple shared adapters. Besides, a Holistic Domain Controller is designed to dynamically regulate the learning capacity for new domains based on knowledge similarity, thereby effectively unleashing the generalization potential of pre-trained models. Furthermore, a lightweight Similarity-Guided Auto-Selector is proposed to assign inputs to relevant adapters during inference automatically. Extensive experiments validate VIA's effectiveness, surpassing state-of-the-art methods in both seen and unseen domains.