As recent generative models can generate photo-realistic images, people seek to understand the mechanism behind the generation process. Interpretable generation process is beneficial to various image editing applications. In this work, we propose a framework to discover interpretable directions in the latent space given arbitrary pre-trained generative adversarial networks. We propose to learn the transformation from prior one-hot vectors representing different attributes to the latent space used by pre-trained models. Furthermore, we apply a centroid loss function to improve consistency and smoothness while traversing through different directions. We demonstrate the efficacy of the proposed framework on a wide range of datasets. The discovered direction vectors are shown to be visually corresponding to various distinct attributes and thus enable attribute editing.

翻译：由于最近的基因化模型可以产生光现实图像,人们寻求理解生成过程背后的机制。可解释生成过程有利于各种图像编辑应用。在这项工作中,我们提出了一个框架,以发现潜在空间的可解释方向,因为存在任意的未经训练的基因化对抗网络。我们建议从以前代表预训练模型所用潜在空间不同属性的一热矢量中学习这种转变。此外,我们运用一个机器人流失功能来提高一致性和顺畅性,同时通过不同方向穿行。我们展示了拟议框架在各种数据集上的效力。发现的方向矢量显示与各种不同属性相匹配,从而能够进行属性编辑。