2021/09/15 by Nanqing Dong, Dong, Nanqing, ID Voiculescu +2 · 3 citations
Computer Science · Engineering · Medicine · #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Microwave Imaging and Scattering Analysis #Tumors and Oncological Cases #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2109.07504
openalex publication_date 2021/09/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
A label-efficient paradigm in computer vision is based on self-supervised contrastive pre-training on unlabeled data followed by fine-tuning with a small number of labels. Making practical use of a federated computing environment in the clinical domain and learning on medical images poses specific challenges. In this work, we propose FedMoCo, a robust federated contrastive learning (FCL) framework, which makes efficient use of decentralized unlabeled medical data. FedMoCo has two novel modules: metadata transfer, an inter-node statistical data augmentation module, and self-adaptive aggregation, an aggregation module based on representational similarity analysis. To the best of our knowledge, this is the first FCL work on medical images. Our experiments show that FedMoCo can consistently outperform FedAvg, a seminal federated learning framework, in extracting meaningful representations for downstream tasks. We further show that FedMoCo can substantially reduce the amount of labeled data required in a downstream task, such as COVID-19 detection, to achieve a reasonable performance.