论文标题
分类数据分类的歧视性特征生成
Discriminative feature generation for classification of imbalanced data
论文作者
论文摘要
数据不平衡问题是神经网络分类性能的常见瓶颈。在本文中，我们为少数类别数据集提出了一种新颖的监督判别特征生成（DFG）方法。 DFG基于由四个独立网络组成的生成对抗网络的修改结构：生成器，鉴别器，功能提取器和分类器。为了通过采用注意机制来增强少数群体数据的选定判别特征，训练了类失去平衡的目标任务的生成器，并且使用大型源数据中的预训练功能正规化了功能提取器和分类器。实验结果表明，DFG发生器增强了标签保留和多样的特征的增强，并且在目标任务上，分类结果得到了显着改善。特征生成模型可以通过歧视性特征生成和监督注意力方法为数据增强方法的开发做出很大贡献。
The data imbalance problem is a frequent bottleneck in the classification performance of neural networks. In this paper, we propose a novel supervised discriminative feature generation (DFG) method for a minority class dataset. DFG is based on the modified structure of a generative adversarial network consisting of four independent networks: generator, discriminator, feature extractor, and classifier. To augment the selected discriminative features of the minority class data by adopting an attention mechanism, the generator for the class-imbalanced target task is trained, and the feature extractor and classifier are regularized using the pre-trained features from a large source data. The experimental results show that the DFG generator enhances the augmentation of the label-preserved and diverse features, and the classification results are significantly improved on the target task. The feature generation model can contribute greatly to the development of data augmentation methods through discriminative feature generation and supervised attention methods.
