FedDAD: Federated Domain Adaptation for Object Detection
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3279132
Abstract: Training an object detection model often requires numerous annotated images on a centralized host, which may violate user privacy and data confidentiality. Federated learning (FL) resolves this issue by allowing multiple clients, e.g., cameras, to… read more here.
Keywords: domain adaptation; feddad federated; detection; federated domain ... See more keywords
FedDGKA: Federated Domain Generalization using Knowledge Alignment
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Access"
DOI: 10.1109/access.2025.3635473
Abstract: Domain Generalization (DG) presents a significant challenge where models trained on multiple source domains must effectively generalize to unseen target domains. Federated Domain Generalization (FDG) synergistically combines Federated Learning (FL) and Domain Generalization methodologies, enabling… read more here.
Keywords: knowledge; feddgka; federated domain; generalization ... See more keywords
Universal Federated Domain Adaptation through One-vs-All Self-Supervision for Internet of Things
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2025.3623225
Abstract: In practical Internet of Things (IoT) applications, deep neural networks (DNNs) often encounter challenges arising from covariate shifts (differences in feature distributions) and category shifts (discrepancies in label spaces), which significantly degrade their generalization performance.… read more here.
Keywords: one self; universal federated; internet things; domain adaptation ... See more keywords
Communicational and Computational Efficient Federated Domain Adaptation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Parallel and Distributed Systems"
DOI: 10.1109/tpds.2022.3167457
Abstract: The emerging paradigm of Federated Learning enables mobile users to collaboratively train a model without disclosing their privacy-sensitive data. Nevertheless, data collected from different mobile users may not be independent and identically distributed. Thus directly… read more here.
Keywords: domain adaptation; adaptation; federated domain; communicational computational ... See more keywords