论文标题
光谱生成对抗网络的混合物，用于不平衡的高光谱图像分类
Mixture of Spectral Generative Adversarial Networks for Imbalanced Hyperspectral Image Classification
论文作者
论文摘要
我们提出了一个三人频谱生成的对抗网络（GAN）体系结构，以负担能够在不平衡条件下管理少数类别的GAN。已经开发出一种依赖类的混合物发电机频谱GAN（MGSGAN）来强制产生的样品，保留在数据的实际分布的域内。即使多数族裔与少数族裔的不平衡比率很高，MGSGAN也能够产生少数群体。基于较低功能的分类器与顺序歧视器一起采用，以形成三人游戏的GAN游戏。发电机网络执行数据增强以提高分类器的性能。该方法已通过两个高光谱图像数据集进行了验证，并将其与与实际数据分布相对应的两个类不平衡设置下的最新方法进行了比较。
We propose a three-player spectral generative adversarial network (GAN) architecture to afford GAN with the ability to manage minority classes under imbalance conditions. A class-dependent mixture generator spectral GAN (MGSGAN) has been developed to force generated samples remain within the domain of the actual distribution of the data. MGSGAN is able to generate minority classes even when the imbalance ratio of majority to minority classes is high. A classifier based on lower features is adopted with a sequential discriminator to form a three-player GAN game. The generator networks perform data augmentation to improve the classifier's performance. The proposed method has been validated through two hyperspectral images datasets and compared with state-of-the-art methods under two class-imbalance settings corresponding to real data distributions.
