FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts

2026-03-13

AI Summary

This work addresses the challenge of insufficient feature discriminability in federated domain generalization for person re-identification, which arises from heterogeneous data distributions across clients and background distractions. To mitigate this, we propose a Body-aware Prompting Mechanism (BAPM) that leverages learnable global and local body-aware visual prompts to guide the attention of Vision Transformers toward the primary human regions. Coupled with a Prompt-based Fine-Tuning Strategy (PFTS), our approach updates only lightweight prompt parameters, significantly reducing communication overhead while substantially improving cross-domain generalization performance. The method seamlessly integrates into existing Vision Transformer frameworks and achieves state-of-the-art results on multiple federated ReID benchmarks with minimal aggregation rounds.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Prompt Engineering / Prompting

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

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.

Problem

• Federated Learning
• Domain Generalization
• Person Re-Identification
• Vision Transformer
• Distribution Shift

Innovation

• Federated Learning
• Person Re-Identification
• Visual Prompting
• Domain Generalization
• Vision Transformer