Table 1.
Top-1 accuracy (%) on the CIFAR10 and CIFAR100 datasets. I represents independent training and MD represents our method. m1 and m2 are the abbreviations of Model1 and Model2.
| CIFAR10 Results | |||||
| Model1 | Model2 | I (m1) | I (m2) | MD (m1) | MD (m2) |
| VGG | ResNet | 93.36 | 93.84 | 94.27 | 95.6 |
| DenseNet | ResNet | 95.35 | 93.84 | 95.72 | 95.48 |
| AlexNet | VGG | 77.58 | 93.36 | 80.23 | 93.81 |
| ResNet | ResNet | 93.84 | 93.84 | 95.72 | 95.75 |
| DenseNet | DenseNet | 95.35 | 95.35 | 95.62 | 95.76 |
| VGG | VGG | 93.36 | 93.36 | 94.10 | 94.33 |
| CIFAR100 Results | |||||
| Model1 | Model2 | I (m1) | I (m2) | MD (m1) | MD (m2) |
| VGG | ResNet | 72.57 | 74.02 | 74.85 | 77.75 |
| DenseNet | ResNet | 77.57 | 74.02 | 78.57 | 79.09 |
| AlexNet | VGG | 43.85 | 72.57 | 49.79 | 74.08 |
| ResNet | ResNet | 74.02 | 74.02 | 77.81 | 77.47 |
| DenseNet | DenseNet | 77.57 | 77.57 | 78.55 | 78.85 |
| VGG | VGG | 72.57 | 72.57 | 75.43 | 75.45 |