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

Data drift is a thorny challenge when deploying person re-identification(ReID) models into real-world devices, where the data distribution issignificantly different from that of the training environment and keepschanging. To tackle this issue, we propose a federated spatial-temporalincremental learning approach, named FedSTIL, which leverages both lifelonglearning and federated learning to continuously optimize models deployed onmany distributed edge clients. Unlike previous efforts, FedSTIL aims to minespatial-temporal correlations among the knowledge learnt from different edgeclients. Specifically, the edge clients first periodically extract generalrepresentations of drifted data to optimize their local models. Then, thelearnt knowledge from edge clients will be aggregated by centralized parameterserver, where the knowledge will be selectively and attentively distilled fromspatial- and temporal-dimension with carefully designed mechanisms. Finally,the distilled informative spatial-temporal knowledge will be sent back tocorrelated edge clients to further improve the recognition accuracy of eachedge client with a lifelong learning method. Extensive experiments on a mixtureof five real-world datasets demonstrate that our method outperforms others bynearly 4% in Rank-1 accuracy, while reducing communication cost by 62%. Allimplementation codes are publicly available onhttps://github.com/MSNLAB/Federated-Lifelong-Person-ReID

Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges