FedDAD: Federated Domain Adaptation for Object Detection

Peggy Joy Lu*, Chia Yung Jui, Jen Hui Chuang

*此作品的通信作者

研究成果: Article同行評審

1 引文 斯高帕斯(Scopus)

摘要

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 collaboratively train a model while protecting user privacy. However, models trained with FL may fail to be generalized for new target domain due to domain shift when the data between source and target domains are statistically different. In this work, we formulate a real-world object detection problem as a source-free multi-domain adaptation problem in FL architecture. Moreover, we propose an adaptive FL algorithm, called FedDAD (Federated Domain Adaptive Detector), which aggregates models with dynamic attention targeting the unsupervised domain on server, and utilize instance-level alignment to alleviate the effects of scene variation on clients. Experimental results show that FedDAD improves the average precision (AP) by up to 10.05% and 19.15% compared to the popular FedAvg for specific object classes in the KAIST and MI3 datasets, respectively.

原文English
頁(從 - 到)51320-51330
頁數11
期刊IEEE Access
11
DOIs
出版狀態Published - 2023

指紋

深入研究「FedDAD: Federated Domain Adaptation for Object Detection」主題。共同形成了獨特的指紋。

引用此