FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918375586791424 |
|---|---|
| author | Xu, Xin Ma, Binchang Yu, Zhixi Liu, Wei |
| author_facet | Xu, Xin Ma, Binchang Yu, Zhixi Liu, Wei |
| contents | The application of federated domain generalization in person re-identification (FedDG-ReID) aims to enhance the model's generalization ability in unseen domains while protecting client data privacy. However, existing mainstream methods typically rely on global feature representations and simple averaging operations for model aggregation, leading to two limitations in domain generalization: (1) Using only global features makes it difficult to capture subtle, domain-invariant local details (such as accessories or textures); (2) Uniform parameter averaging treats all clients as equivalent, ignoring their differences in robust feature extraction capabilities, thereby diluting the contributions of high quality clients. To address these issues, we propose a novel federated learning framework, Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration (FedARKS), comprising two mechanisms: RK (Robust Knowledge) and KS (Knowledge Selection). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06122 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification Xu, Xin Ma, Binchang Yu, Zhixi Liu, Wei Computer Vision and Pattern Recognition The application of federated domain generalization in person re-identification (FedDG-ReID) aims to enhance the model's generalization ability in unseen domains while protecting client data privacy. However, existing mainstream methods typically rely on global feature representations and simple averaging operations for model aggregation, leading to two limitations in domain generalization: (1) Using only global features makes it difficult to capture subtle, domain-invariant local details (such as accessories or textures); (2) Uniform parameter averaging treats all clients as equivalent, ignoring their differences in robust feature extraction capabilities, thereby diluting the contributions of high quality clients. To address these issues, we propose a novel federated learning framework, Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration (FedARKS), comprising two mechanisms: RK (Robust Knowledge) and KS (Knowledge Selection). |
| title | FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.06122 |