论文标题
无监督发现gan中的分解流形的发现
Unsupervised Discovery of Disentangled Manifolds in GANs
论文作者
论文摘要
由于最近的生成模型可以生成照片真实的图像，因此人们试图了解发电过程背后的机制。可解释的生成过程对各种图像编辑应用有益。在这项工作中，我们提出了一个框架，以在给定任意训练的预训练的对抗网络的潜在空间中发现可解释的方向。我们建议学习从先前的一热矢量来代表不同属性到预训练模型使用的潜在空间的转换。此外，我们应用质心损失函数来提高一致性和平滑度，同时越过不同的方向。我们证明了所提出的框架在各种数据集上的功效。发现的方向向量在视觉上与各种不同的属性相对应，从而启用属性编辑。
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.
