In recent years,artificial intelligence has fueled the development of numerous applications[1,2].Person re-identification(re-ID)is a typical artificial intelligence system designed to automatically retrieve images of ...In recent years,artificial intelligence has fueled the development of numerous applications[1,2].Person re-identification(re-ID)is a typical artificial intelligence system designed to automatically retrieve images of specific individuals from galleries captured by different cameras[3].While supervised(in-domain)person re-ID methods have achieved considerable success in recent years[4],they remain susceptible to domain shifts.This means a model trained on one domain may fail to identify the person in another distinct domain.Collecting annotating data for every possible domain variation(e.g.,resolutions,lighting,and cameras)is impractical.展开更多
Federated learning is a promising learning paradigm that allows collaborative training of models across multiple data owners without sharing their raw datasets.To enhance privacy in federated learning,multi-party comp...Federated learning is a promising learning paradigm that allows collaborative training of models across multiple data owners without sharing their raw datasets.To enhance privacy in federated learning,multi-party computation can be leveraged for secure communication and computation during model training.This survey provides a comprehensive review on how to integrate mainstream multi-party computation techniques into diverse federated learning setups for guaranteed privacy,as well as the corresponding optimization techniques to improve model accuracy and training efficiency.We also pinpoint future directions to deploy federated learning to a wider range of applications.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.62276013,62141605)。
文摘In recent years,artificial intelligence has fueled the development of numerous applications[1,2].Person re-identification(re-ID)is a typical artificial intelligence system designed to automatically retrieve images of specific individuals from galleries captured by different cameras[3].While supervised(in-domain)person re-ID methods have achieved considerable success in recent years[4],they remain susceptible to domain shifts.This means a model trained on one domain may fail to identify the person in another distinct domain.Collecting annotating data for every possible domain variation(e.g.,resolutions,lighting,and cameras)is impractical.
基金partially supported by the National Natural Science Foundation of China(NSFC)(Grant Nos.U21A20516,62076017,and 62141605)the Funding of Advanced Innovation Center for Future Blockchain and Privacy Computing(No.ZF226G2201)+1 种基金the Beihang University Basic Research Funding(No.YWF-22-L-531)the Funding(No.22-TQ23-14-ZD-01-001)and WeBank Scholars Program.
文摘Federated learning is a promising learning paradigm that allows collaborative training of models across multiple data owners without sharing their raw datasets.To enhance privacy in federated learning,multi-party computation can be leveraged for secure communication and computation during model training.This survey provides a comprehensive review on how to integrate mainstream multi-party computation techniques into diverse federated learning setups for guaranteed privacy,as well as the corresponding optimization techniques to improve model accuracy and training efficiency.We also pinpoint future directions to deploy federated learning to a wider range of applications.
