Table 3
Binary cross entropy.
| Model | BCE Score |
|---|---|
| UNet[10−2] | 0.0085 |
| UNet[10−3] | 0.0084 |
| UNet[10−4] | 0.0088 |
| UNet[10−5] | 0.0161 |
| UNet++[10−3] | 0.0081 |
| UNet++[l0−4] | 0.0088 |
| UNet++[10−5] | 0.0122 |
Notes. Binary cross entropy (BCE) evaluation on the test set for the schemes reported in Fig. 14. The lowest (highest) achieved BCE is given in blue (red). BCE values in test are inline with performances in training and validation steps with UNet++[10−3] and UNet[10−5] resulting in the best and less performing schemes, respectively.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.