Robust Knowledge Adaptation for Federated Unsupervised Person ReID

TL;DR

This paper proposes a federated unsupervised learning method for person re-identification that preserves privacy, reduces annotation effort, and achieves state-of-the-art results across multiple datasets.

Contribution

It introduces FedUCC, a three-stage federated learning framework that captures generic, specialized, and patch knowledge for unsupervised person ReID.

Findings

Achieves state-of-the-art performance on 8 benchmark datasets.

Effectively shares mutual knowledge while maintaining local domain-specific knowledge.

Reduces reliance on laborious data annotations.

Abstract

Person Re-identification (ReID) has been extensively studied in recent years due to the increasing demand in public security. However, collecting and dealing with sensitive personal data raises privacy concerns. Therefore, federated learning has been explored for Person ReID, which aims to share minimal sensitive data between different parties (clients). However, existing federated learning based person ReID methods generally rely on laborious and time-consuming data annotations and it is difficult to guarantee cross-domain consistency. Thus, in this work, a federated unsupervised cluster-contrastive (FedUCC) learning method is proposed for Person ReID. FedUCC introduces a three-stage modelling strategy following a coarse-to-fine manner. In detail, generic knowledge, specialized knowledge and patch knowledge are discovered using a deep neural network. This enables the sharing of mutual knowledge among clients while retaining local domain-specific knowledge based on the kinds of network layers and their parameters. Comprehensive experiments on 8 public benchmark datasets demonstrate the state-of-the-art performance of our proposed method.