Positive Style Accumulation: A Style Screening and Continuous Utilization Framework for Federated DG-ReID

TL;DR

This paper introduces a novel framework for federated person re-identification that screens and continuously utilizes beneficial styles to improve model generalization across domains.

Contribution

The paper proposes the SSCU framework with GGDSM, style memory recognition loss, and CST strategy to effectively select and leverage positive styles for federated DG-ReID.

Findings

Outperforms existing methods in source and target domains.

Effectively screens and accumulates positive styles for better generalization.

Enhances model robustness through continuous style utilization.

Abstract

The Federated Domain Generalization for Person re-identification (FedDG-ReID) aims to learn a global server model that can be effectively generalized to source and target domains through distributed source domain data. Existing methods mainly improve the diversity of samples through style transformation, which to some extent enhances the generalization performance of the model. However, we discover that not all styles contribute to the generalization performance. Therefore, we define styles that are beneficial or harmful to the model's generalization performance as positive or negative styles. Based on this, new issues arise: How to effectively screen and continuously utilize the positive styles. To solve these problems, we propose a Style Screening and Continuous Utilization (SSCU) framework. Firstly, we design a Generalization Gain-guided Dynamic Style Memory (GGDSM) for each client model to screen and accumulate generated positive styles. Meanwhile, we propose a style memory recognition loss to fully leverage the positive styles memorized by Memory. Furthermore, we propose a Collaborative Style Training (CST) strategy to make full use of positive styles. Unlike traditional learning strategies, our approach leverages both newly generated styles and the accumulated positive styles stored in memory to train client models on two distinct branches. This training strategy is designed to effectively promote the rapid acquisition of new styles by the client models, and guarantees the continuous and thorough utilization of positive styles, which is highly beneficial for the model's generalization performance. Extensive experimental results demonstrate that our method outperforms existing methods in both the source domain and the target domain.