Research Article
A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification
Table 5
Comparison with state-of-the-art algorithms on CIFAR-100.
| Algorithms | CIFAR-100 (%) |
| Probout [42] | 61.86 | NIN + dropout [43] | 64.32 | Maxout + dropout [44] | 61.43 | Stochastic pooling [45] | 57.49 | Probabilistic weighted pooling [46] | 62.87 | Our method | 70.22 |
|
|