It is a difficult task to classify images with multiple labels only using a small number of labeled samples and to be worse, with unbalanced distribution. In this paper we propose a brand-new data augmentation method using generative adversarial networks, which is able to complement and complete the data manifold from the true sense, assist the classifier to better find margins or hyper-planes of neighboring classes, and finally lead to better performance in image classification task. Specifically, we design a pipeline containing a CNN model as classifier and a cycle-consistent adversarial networks(CycleGAN) to generate supplementary data from given classes. In order to avoid gradient vanishing, we apply a least-squared loss to adversarial loss. We also propose several evaluation methods to validate GAN's contribution in data augmentation. Qualitative observations indicate that data manifolds show a significant improvement in distribution integrity and margin clarity between classes. Quantitative comparative experiments with the baseline show a 5%~10% increase after this data augmentation technique.

本论文提出了一种将生成对抗网络（GAN）用于数据增强的方法，以解决标签分布不均衡导致的图像分类困难，特别是在情感分类中，实验结果表明，使用GAN进行数据增强，可以使分类准确率提高5％〜10％。

使用生成对抗网络的情感分类数据增强