Robust Knowledge Adaptation for Federated Unsupervised Person ReID
This addresses privacy concerns in person re-identification for public security applications by enabling federated learning without annotations, though it is incremental as it builds on existing federated and unsupervised approaches.
The paper tackles the problem of privacy-preserving person re-identification by proposing a federated unsupervised learning method, FedUCC, which achieves state-of-the-art performance on 8 public benchmark datasets without requiring data annotations.
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.