Table 4 Communication overhead and total training time.
From: Enhanced brain tumour segmentation using a hybrid dual encoder–decoder model in federated learning
Model | Avg. upload per client (MB) | Server aggregation time (s) | Total training time (h) |
|---|---|---|---|
U-Net | 30 | 12 | 5.8 |
UNet + + | 34 | 14 | 6.0 |
ResUNet | 38 | 15 | 6.6 |
Proposed Model | 55 | 20 | 5.1 |
