Skip to main content
. Author manuscript; available in PMC: 2024 Jul 1.
Published in final edited form as: IEEE Trans Med Imaging. 2023 Jun 30;42(7):1932–1943. doi: 10.1109/TMI.2022.3233574

TABLE IV:

Test accuracy for federated fine-tuning on COVID-FL Central (centralized) and Split (non-IID). T represents the communication rounds of federated fine-tuning.

Pre-training
 Test Accuracy (%)
 T
Method Setup Dataset Central Split
None None None 91.42 77.08 1000
Supervised Centralized ImageNet 95.35 86.89 100
BEiT [29] Centralized ImageNet 95.62 84.45 100
MAE [30] Centralized ImageNet 96.35 84.32 100
Supervised Centralized ChestX-ray14 92.78 82.26 100
BEiT [29] Centralized ChestX-ray14 96.07 90.28 100
MAE [30] Centralized ChestX-ray14 96.35 91.04 100
Fed-BEiT Distributed COVID-FL 95.75 87.09 100
Fed-MAE Distributed COVID-FL 95.77 91.47 100