Table 4 Outcomes of baseline approach and augmenting approach.
Method | Baseline models | Augmenting | ||||||
|---|---|---|---|---|---|---|---|---|
Accuracy | F1 | Sensitivity | Specificity | Accuracy | F1 | Sensitivity | Specificity | |
DeepLab v3+ | 0.97 | 0.95 | 0.93 | 0.97 | 0.97 | 0.95 | 0.93 | 0.97 |
Unet | 0.97 | 0.93 | 0.94 | 0.97 | 0.97 | 0.93 | 0.94 | 0.97 |
DilatedFastFNN | 0.97 | 0.94 | 0.9 | 0.9 | 0.97 | 0.94 | 0.9 | 0.9 |
DANet | 0.96 | 0.9 | 0.9 | 0.97 | 0.96 | 0.92 | 0.92 | 0.97 |
Custom vanilla architecture | 0.97 | 0.94 | 0.94 | 0.97 | 0.97 | 0.94 | 0.94 | 0.97 |
