一作ACL 2026Poster· Natural Language Processing
CO - EVO : Co-evolving Semantic Anchoring and Style Diversification for Federated DG - R e ID
Fengchunzhang · Qiang Ma · Liuyu Xiang · Jinshan Lai · Tingxuan Huang · Jianwei Hu
摘要
Federated domain generalization for person re-identification (FedDG-ReID) aims to collaboratively train a pedestrian retrieval model across multiple decentralized source domains such that it can generalize to unseen target environments without compromising raw data privacy. However, this task is...