English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we study the problem of federated domain generalization(FedDG) for person re-identification (re-ID), which aims to learn a generalizedmodel with multiple decentralized labeled source domains. An empirical method(FedAvg) trains local models individually and averages them to obtain theglobal model for further local fine-tuning or deploying in unseen targetdomains. One drawback of FedAvg is neglecting the data distributions of otherclients during local training, making the local model overfit local data andproducing a poorly-generalized global model. To solve this problem, we proposea novel method, called "Domain and Feature Hallucinating (DFH)", to producediverse features for learning generalized local and global models.Specifically, after each model aggregation process, we share the Domain-levelFeature Statistics (DFS) among different clients without violating dataprivacy. During local training, the DFS are used to synthesize novel domainstatistics with the proposed domain hallucinating, which is achieved byre-weighting DFS with random weights. Then, we propose feature hallucinating todiversify local features by scaling and shifting them to the distribution ofthe obtained novel domain. The synthesized novel features retain the originalpair-wise similarities, enabling us to utilize them to optimize the model in asupervised manner. Extensive experiments verify that the proposed DFH caneffectively improve the generalization ability of the global model. Our methodachieves the state-of-the-art performance for FedDG on four large-scale re-IDbenchmarks.

Federated and Generalized Person Re-identification through Domain and Feature Hallucinating