Table 3 The ablation experiments on the CIFAR-10 dataset.
From: D2S-DiffGAN: a novel image classification model under limited labeled samples
Size of training set | Model 1 | Model 2 | Model 3 | Model 4 | Model 5 |
|---|---|---|---|---|---|
10% | 74.98% | 75.66% | 81.88% | 83.31% | 85.06% |
15% | 77.25% | 78.36% | 83.12% | 86.77% | 88.13% |
20% | 80.57% | 82.17% | 86.54% | 87.44% | 90.55% |
25% | 83.33% | 84.83% | 87.34% | 89.52% | 91.12% |
30% | 85.76% | 87.69% | 89.45% | 90.79% | 91.94% |
