FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts
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_ | 1866915859416481792 |
|---|---|
| author | Xu, Xin Li, Weilong Liu, Wei Huang, Wenke Yu, Zhixi Yang, Bin Liao, Xiaoying Jiang, Kui |
| author_facet | Xu, Xin Li, Weilong Liu, Wei Huang, Wenke Yu, Zhixi Yang, Bin Liao, Xiaoying Jiang, Kui |
| contents | Federated Domain Generalization for Person Re-Identification (FedDG-ReID) learns domain-invariant representations from decentralized data. While Vision Transformer (ViT) is widely adopted, its global attention often fails to distinguish pedestrians from high similarity backgrounds or diverse viewpoints -- a challenge amplified by cross-client distribution shifts in FedDG-ReID. To address this, we propose Federated Body Distribution Aware Visual Prompt (FedBPrompt), introducing learnable visual prompts to guide Transformer attention toward pedestrian-centric regions. FedBPrompt employs a Body Distribution Aware Visual Prompts Mechanism (BAPM) comprising: Holistic Full Body Prompts to suppress cross-client background noise, and Body Part Alignment Prompts to capture fine-grained details robust to pose and viewpoint variations. To mitigate high communication costs, we design a Prompt-based Fine-Tuning Strategy (PFTS) that freezes the ViT backbone and updates only lightweight prompts, significantly reducing communication overhead while maintaining adaptability. Extensive experiments demonstrate that BAPM effectively enhances feature discrimination and cross-domain generalization, while PFTS achieves notable performance gains within only a few aggregation rounds. Moreover, both BAPM and PFTS can be easily integrated into existing ViT-based FedDG-ReID frameworks, making FedBPrompt a flexible and effective solution for federated person re-identification. The code is available at https://github.com/leavlong/FedBPrompt. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12912 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts Xu, Xin Li, Weilong Liu, Wei Huang, Wenke Yu, Zhixi Yang, Bin Liao, Xiaoying Jiang, Kui Computer Vision and Pattern Recognition Artificial Intelligence Federated Domain Generalization for Person Re-Identification (FedDG-ReID) learns domain-invariant representations from decentralized data. While Vision Transformer (ViT) is widely adopted, its global attention often fails to distinguish pedestrians from high similarity backgrounds or diverse viewpoints -- a challenge amplified by cross-client distribution shifts in FedDG-ReID. To address this, we propose Federated Body Distribution Aware Visual Prompt (FedBPrompt), introducing learnable visual prompts to guide Transformer attention toward pedestrian-centric regions. FedBPrompt employs a Body Distribution Aware Visual Prompts Mechanism (BAPM) comprising: Holistic Full Body Prompts to suppress cross-client background noise, and Body Part Alignment Prompts to capture fine-grained details robust to pose and viewpoint variations. To mitigate high communication costs, we design a Prompt-based Fine-Tuning Strategy (PFTS) that freezes the ViT backbone and updates only lightweight prompts, significantly reducing communication overhead while maintaining adaptability. Extensive experiments demonstrate that BAPM effectively enhances feature discrimination and cross-domain generalization, while PFTS achieves notable performance gains within only a few aggregation rounds. Moreover, both BAPM and PFTS can be easily integrated into existing ViT-based FedDG-ReID frameworks, making FedBPrompt a flexible and effective solution for federated person re-identification. The code is available at https://github.com/leavlong/FedBPrompt. |
| title | FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.12912 |