FedBPrompt：基于身体分布感知视觉提示词的联邦域泛化行人重识别
FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts
提出可学习的视觉提示词分组机制（整体身体提示词+身体部位对齐提示词）来引导ViT注意力聚焦行人区域，并冻结骨干网络仅微调提示词以降低联邦通信开销，可直接用于ViT-based行人重识别及其他细粒度视觉任务的参数高效域泛化。
原文依据 introduces learnable visual prompts to explicitly guide Transformer attention toward pedestrian-centric regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦域泛化行人重识别（FedDG-ReID）旨在从去中心化数据中学习域不变表示。尽管视觉Transformer（ViT）被广泛采用，但其全局注意力往往难以从高相似背景或多样视角中区分行人——联邦域泛化行人重识别中的跨客户端分布偏移进一步放大了这一挑战。为此，我们提出联邦身体分布感知视觉提示词（FedBPrompt），引入可学习的视觉提示词以显式引导Transformer注意力聚焦于行人中心区域。FedBPrompt采用身体分布感知视觉提示词机制（BAPM），将提示词分为两组：整体全身提示词抑制跨客户端背景噪声，而身体部位对齐提示词捕获对姿态和视角变化鲁棒的细粒度细节。为缓解大型Transformer模型的高通信成本，我们进一步设计基于提示词的微调策略（PFTS），冻结ViT骨干网络并仅更新轻量级提示词，在保持适应性的同时显著降低通信开销。大量实验表明，BAPM有效增强了特征判别力和跨域泛化能力，而PFTS仅在少数聚合轮次内即实现显著性能提升。此外，BAPM和PFTS均可轻松集成到现有的基于ViT的FedDG-ReID框架中，使FedBPrompt成为联邦行人重识别的一种灵活且有效的解决方案。代码将开源。
英文原文摘要 1597 字符
Federated Domain Generalization for Person Re-Identification (FedDG-ReID) aims to learn domain-invariant representations from decentralized data. Although Vision Transformers (ViTs) are widely adopted, their global attention often fails to distinguish pedestrians from high similarity backgrounds or diverse viewpoints---a challenge further amplified by cross-client distribution shifts in FedDG-ReID. To address this, we propose Federated Body Distribution Aware Visual Prompt (FedBPrompt), which introduces learnable visual prompts to explicitly guide Transformer attention toward pedestrian-centric regions. FedBPrompt employs a Body Distribution Aware Visual Prompts Mechanism (BAPM) that divides prompts into two groups: Holistic Full Body Prompts suppress cross-client background noise, while Body Part Alignment Prompts capture fine-grained details robust to pose and viewpoint variations. To mitigate the high communication cost of large Transformer models, we further design a Prompt-based Fine-Tuning Strategy (PFTS) that freezes the ViT backbone and updates only lightweight prompts, significantly reducing communication overhead while maintaining adaptability. Extensive experiments demonstrate that BAPM effectively enhances feature discrimination and cross-domain generalization, while PFTS achieves notable performance gains within only a few aggregation rounds. Moreover, both BAPM and PFTS can be easily integrated into existing ViT-based FedDG-ReID frameworks, making FedBPrompt a flexible and effective solution for federated person re-identification. The code will be released.