论文标题
深层有条件生成网络的信息补偿
Information Compensation for Deep Conditional Generative Networks
论文作者
论文摘要
近年来，无监督/弱监督的条件生成对抗网络（GAN）在建模和生成数据的任务上取得了许多成功。但是，他们的弱点之一在于他们分离或分离的能力差，是表征在其潜在空间中代表的不同因素。为了解决这个问题，我们提出了一种由新的信息补偿连接（IC-Connection）提供动力的无监督条件gan的新结构。拟议的IC连接使GAN能够补偿在反卷积操作期间产生的信息损失。此外，为了量化离散和连续变量的分离程度，我们设计了一种新的评估程序。我们的经验结果表明，与有条件的生成环境中的最先进的gan相比，我们的方法可实现更好的分离。
In recent years, unsupervised/weakly-supervised conditional generative adversarial networks (GANs) have achieved many successes on the task of modeling and generating data. However, one of their weaknesses lies in their poor ability to separate, or disentangle, the different factors that characterize the representation encoded in their latent space. To address this issue, we propose a novel structure for unsupervised conditional GANs powered by a novel Information Compensation Connection (IC-Connection). The proposed IC-Connection enables GANs to compensate for information loss incurred during deconvolution operations. In addition, to quantify the degree of disentanglement on both discrete and continuous latent variables, we design a novel evaluation procedure. Our empirical results suggest that our method achieves better disentanglement compared to the state-of-the-art GANs in a conditional generation setting.
