论文标题
我的公正辅助分类器gan
Unbiased Auxiliary Classifier GANs with MINE
论文作者
论文摘要
辅助分类器gan（AC-GAN）是广泛使用的有条件生成模型，能够产生高质量的图像。先前的工作指出，AC-GAN学会了有偏分的分布。为了解决这个问题，双辅助分类器GAN（TAC-GAN）向Min-Max游戏介绍了双胞胎分类器。但是，据报道，使用双辅助分类器可能会导致训练不稳定。为此，我们提出了一个公正的辅助gan（UAC-GAN），该辅助剂（UAC-GAN）利用相互信息神经估计器（MIRE）来估计生成的数据分布和标签之间的相互信息。为了进一步提高性能，我们还提出了一种基于投影的新型统计网络架构。在三个数据集上进行的实验结果，包括高斯（MOG），MNIST和CIFAR10数据集的混合物，表明我们的UAC-GAN的性能比AC-GAN和TAC-GAN更好。代码可以在项目网站上找到。
Auxiliary Classifier GANs (AC-GANs) are widely used conditional generative models and are capable of generating high-quality images. Previous work has pointed out that AC-GAN learns a biased distribution. To remedy this, Twin Auxiliary Classifier GAN (TAC-GAN) introduces a twin classifier to the min-max game. However, it has been reported that using a twin auxiliary classifier may cause instability in training. To this end, we propose an Unbiased Auxiliary GANs (UAC-GAN) that utilizes the Mutual Information Neural Estimator (MINE) to estimate the mutual information between the generated data distribution and labels. To further improve the performance, we also propose a novel projection-based statistics network architecture for MINE. Experimental results on three datasets, including Mixture of Gaussian (MoG), MNIST and CIFAR10 datasets, show that our UAC-GAN performs better than AC-GAN and TAC-GAN. Code can be found on the project website.
