Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization
원문 초록
Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains are kept isolated, which poses challenges in bridging the domain gap. To address this issue, we propose a Multi-source Collaborative Gradient Discrepancy Minimization (MCGDM) method for federated domain generalization. Specifically, we propose intra-domain gradient matching between the original images and augmented images to avoid overfitting the domain-specific information within isolated domains. Additionally, we propose inter-domain gradient matching with the collaboration of other domains, which can further reduce the domain shift across decentralized domains. Combining intra-domain and inter-domain gradient matching, our method enables the learned model to generalize well on unseen domains. Furthermore, our method can be extended to the federated domain adaptation task by fine-tuning the target model on the pseudo-labeled target domain. The extensive experiments on federated domain generalization and adaptation indicate that our method outperforms the state-of-the-art methods significantly.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
seg_3D_by_PC2D: Multi-View Projection for Domain Generalization and Adaptation in 3D Semantic Segmentation
A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation viaSynergistic Pseudo-Labeling and Generative Learning
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
RoCA: Robust Cross-Domain End-to-End Autonomous Driving
Generalizable Multispectral Land Cover Classification via Frequency-Aware Mixture of Low-Rank Token Experts
On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.