Research on data augmentation for image classification based on convolution neural networks 论文

摘要

The performance of deep convolution neural networks will be further enhanced with the expansion of the training data set. For the image classification tasks, it is necessary to expand the insufficient training image samples through various data augmentation methods. This paper explores the impact of various data augmentation methods on image classification tasks with deep convolution Neural network, in which Alexnet is employed as the pre-training network model and a subset of CIFAR10 and ImageNet (10 categories) are selected as the original data set. The data augmentation methods used in this paper include: GAN/WGAN, Flipping, Cropping, Shifting, PCA jittering, Color jittering, Noise, Rotation, and some combinations. Experimental results show that, under the same condition of multiple increasing, the performance evaluation on small-scale data sets is more obvious, the four individual methods (Cropping, Flipping, WGAN, Rotation) perform generally better than others, and some appropriate combination methods are slightly more effective than the individuals.