基于可变损失和流形正则化的生成对抗网络

针对生成对抗网络中鉴别器在少量标记样本上的分类精度较差以及对流形局部扰动的鲁棒性不足的问题，提出一种基于可变损失和流形正则化的生成对抗网络算法。当标记样本较少时，该算法在鉴别器中利用可变损失代替原有对抗损失以解决训练前期分类性能较差的鉴别器对半监督分类任务的不利影响。此外，在鉴别器可变损失的基础上加入流形正则项，通过惩罚鉴别器在流形上分类决策的变化提高鉴别器对局部扰动的鲁棒性。以生成样本的质量和半监督的分类精度作为算法的评价标准，并在数据集SVHN和CIFAR-10上完成了数值实验。与其他半监督算法的对比结果表明，该算法在使用少量带标记数据的情况下能得到质量更高的生成样本和精度更高的分类结果。

GAN based on variable loss and manifold regularization

Aiming at the problem of the discriminator''s poor classification accuracy on a small number of labeled samples and insufficient robustness to the local perturbation of manifolds in the generative adversarial network, this paper proposed a gene-rative adversarial network based on variable loss and manifold regularization. The algorithm used a variable loss instead of the original discriminator to solve the adverse effect of the poorly trained classifier on the semi-supervised classification task. In addition, on the basis of variable loss of discriminator, it added manifold regular terms to improve the robustness of discriminator to local disturbance by punishing the variation of classification decision of discriminator on manifold. Using the quality of the generated samples and the semi-supervised classification accuracy as the evaluation criteria of the algorithm, this paper performed numerical experiments on the dataset SVHN and CIFAR-10. Compared with other semi-supervised algorithms, the results show that the proposed algorithm can obtain higher quality generated samples and higher precision classification results with a small amount of labeled data.