Object Re-Identification Based on Federated Incremental Subgradient Proximal Optimization
Object Re-identification (Object ReID) is one of the key tasks in the field of computer vision. However, traditional centralized ReID methods face challenges related to privacy protection and data storage. Federated learning, as a distributed machine learning framework, can utilize dispersed data fo...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of the Computer Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10742512/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550782737940480 |
|---|---|
| author | Li Kang Chuanghong Zhao Jianjun Huang |
| author_facet | Li Kang Chuanghong Zhao Jianjun Huang |
| author_sort | Li Kang |
| collection | DOAJ |
| description | Object Re-identification (Object ReID) is one of the key tasks in the field of computer vision. However, traditional centralized ReID methods face challenges related to privacy protection and data storage. Federated learning, as a distributed machine learning framework, can utilize dispersed data for model training without sharing raw data, thereby reducing communication costs and ensuring data privacy. However, the real statistical heterogeneity in federated object re-identification leads to domain shift issues, resulting in decreased performance and generalization ability of the ReID model. Therefore, to address the privacy constraints and real statistical heterogeneity in object re-identification, this article focuses on studying the object re-identification method based on the Federated Incremental Subgradient Proximal(FedISP) framework. FedISP effectively alleviates weight divergence and low communication efficiency issues through incremental sub-gradient proximal methods and ring topology, ensuring stable model convergence and efficient communication. Considering the complexity of ReID scenarios, this article adopts a ViT-based task model to cope with feature skew across clients. Additionally, it defines camera federated scenarios and dataset federated scenarios for problem modeling and analysis. Furthermore, due to the heterogeneous classifiers that clients may have, the approach intergrates personalized layers. In the experiments, instance datasets of two federated scenarios were constructed for model training. The final test results show that FedISP can effectively address the privacy protection and statistical heterogeneity issues faced by ReID. |
| format | Article |
| id | doaj-art-91427932fec64f6eaa04f9d7239822dc |
| institution | Kabale University |
| issn | 2644-1268 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Computer Society |
| spelling | doaj-art-91427932fec64f6eaa04f9d7239822dc2025-01-10T00:03:35ZengIEEEIEEE Open Journal of the Computer Society2644-12682025-01-016607110.1109/OJCS.2024.348987510742512Object Re-Identification Based on Federated Incremental Subgradient Proximal OptimizationLi Kang0https://orcid.org/0000-0003-4094-3348Chuanghong Zhao1https://orcid.org/0009-0004-8852-7006Jianjun Huang2https://orcid.org/0000-0001-7040-3591College of Electronics and Information Engineering, Shenzhen University, Shenzhen, ChinaCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen, ChinaCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen, ChinaObject Re-identification (Object ReID) is one of the key tasks in the field of computer vision. However, traditional centralized ReID methods face challenges related to privacy protection and data storage. Federated learning, as a distributed machine learning framework, can utilize dispersed data for model training without sharing raw data, thereby reducing communication costs and ensuring data privacy. However, the real statistical heterogeneity in federated object re-identification leads to domain shift issues, resulting in decreased performance and generalization ability of the ReID model. Therefore, to address the privacy constraints and real statistical heterogeneity in object re-identification, this article focuses on studying the object re-identification method based on the Federated Incremental Subgradient Proximal(FedISP) framework. FedISP effectively alleviates weight divergence and low communication efficiency issues through incremental sub-gradient proximal methods and ring topology, ensuring stable model convergence and efficient communication. Considering the complexity of ReID scenarios, this article adopts a ViT-based task model to cope with feature skew across clients. Additionally, it defines camera federated scenarios and dataset federated scenarios for problem modeling and analysis. Furthermore, due to the heterogeneous classifiers that clients may have, the approach intergrates personalized layers. In the experiments, instance datasets of two federated scenarios were constructed for model training. The final test results show that FedISP can effectively address the privacy protection and statistical heterogeneity issues faced by ReID.https://ieeexplore.ieee.org/document/10742512/Federated learningnon-IID dataincremental methodsobject re-identification |
| spellingShingle | Li Kang Chuanghong Zhao Jianjun Huang Object Re-Identification Based on Federated Incremental Subgradient Proximal Optimization IEEE Open Journal of the Computer Society Federated learning non-IID data incremental methods object re-identification |
| title | Object Re-Identification Based on Federated Incremental Subgradient Proximal Optimization |
| title_full | Object Re-Identification Based on Federated Incremental Subgradient Proximal Optimization |
| title_fullStr | Object Re-Identification Based on Federated Incremental Subgradient Proximal Optimization |
| title_full_unstemmed | Object Re-Identification Based on Federated Incremental Subgradient Proximal Optimization |
| title_short | Object Re-Identification Based on Federated Incremental Subgradient Proximal Optimization |
| title_sort | object re identification based on federated incremental subgradient proximal optimization |
| topic | Federated learning non-IID data incremental methods object re-identification |
| url | https://ieeexplore.ieee.org/document/10742512/ |
| work_keys_str_mv | AT likang objectreidentificationbasedonfederatedincrementalsubgradientproximaloptimization AT chuanghongzhao objectreidentificationbasedonfederatedincrementalsubgradientproximaloptimization AT jianjunhuang objectreidentificationbasedonfederatedincrementalsubgradientproximaloptimization |