Table 2.
Validation and testing accuracy of image manipulation data
| Text model | Validation accuracy | Test accuracy |
|---|---|---|
| VGG16 (Baseline) | 73.55% | 73.76% |
| EfficientNet (Baseline) | 61.15% | 60.87% |
| ResNet50 (Baseline) | 80.43% | 80.70% |
| Inception-ResNet-V2 | 80.49% | 80.66% |
| Xception | 82.07% | 82.32% |
| Inception-ResNet-V2 with ELA | 79.52% | 79.70% |
| ResNet50 with ELA | 79.01% | 79.58% |
| Xception with ELA | 79.58% | 80.01% |
Bold indicates models with better performance measures (here validation and Test accuracy)