FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification
This work addresses the problem of improving generalization ability in unseen domains for person re-identification models, which is important for privacy-preserving applications.
This paper addresses limitations in federated domain generalization for person re-identification (FedDG-ReID) by proposing FedARKS, a framework that moves beyond global feature representations and simple averaging. It aims to improve generalization in unseen domains while preserving client data privacy.
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).