Abstract
The application of federated domain generalization in person re-identification (FedDG-ReID) aims to enhance the model's generalization ability in unseen domains while protecting client data privacy. However, existing mainstream methods typically rely on global feature representations and simple averaging operations for model aggregation, leading to two limitations in domain generalization: (1) Using only global features makes it difficult to capture subtle, domain-invariant local details (such as accessories or textures); (2) Uniform parameter averaging treats all clients as equivalent, ignoring their differences in robust feature extraction capabilities, thereby diluting the contributions of high quality clients. To address these issues, we propose a novel federated learning framework, Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration (FedARKS), comprising two mechanisms: RK (Robust Knowledge) and KS (Knowledge Selection).
Abstract (translated)
在人员再识别（Person Re-Identification，ReID）中应用联合领域泛化（Federated Domain Generalization, FedDG-ReID），旨在增强模型在未见过领域的泛化能力的同时保护客户端数据隐私。然而，现有的主流方法通常依赖于全局特征表示和简单的平均操作来进行模型聚合，这导致了领域泛化中的两个限制：(1) 仅使用全局特征难以捕捉细微的、跨域不变的局部细节（如配饰或纹理）；(2) 统一参数平均将所有客户端视为等同，忽视它们在鲁棒特征提取能力上的差异，从而稀释了高质量客户端的贡献。为解决这些问题，我们提出了一种新颖的联邦学习框架——通过鲁棒和判别性知识选择与集成实现的联合聚合（Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration, FedARKS），该框架包含两个机制：RK（Robust Knowledge）和KS（Knowledge Selection）。
URL
https://arxiv.org/abs/2603.06122
