Discrete Dynamics in Nature and Society / 2020 / Article / Tab 1

Research Article

A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification

Table 1

Classification accuracy of various data augmentation methods on CIAFR-10 under the proposed full stage data augmentation framework.

MethodsCIFAR-10 (%)

Translation91.41
Horizontal flip90.27
Rotation88.78
Scale transformation90.70
Noise disturbance87.54

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.