Research Article
Improving the Performance of Deep Learning Model-Based Classification by the Analysis of Local Probability
Table 5
The result of random probability on CIFAR-100 and Mini-ImageNet.
| Methods on local probability | VoVNet-57 [24] | Ours: L-PDL-joint/L-PDL-weight (%) |
| CIFAR-100, Rand (0, 1) | 63.98 | 65.37 | CIFAR-100, Rand (−1, 1) | 63.78 | 73.73 | CIFAR-100, Rand (−2, 1) | 63.42 | 76.01 | Mini-ImageNet, Rand (0, 1) | 72.65 | 73.52 | Mini-ImageNet, Rand (−1, 1) | 72.58 | 80.15 | Mini-ImageNet, Rand (−2, 1) | 72.47 | 84.28 |
|
|