Discrete Dynamics in Nature and Society / 2020 / Article / Tab 5

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.

AlgorithmsCIFAR-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 method70.22

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.