论文标题
gan中潜在语义的封闭形式分解
Closed-Form Factorization of Latent Semantics in GANs
论文作者
论文摘要
已经显示，一组丰富的可解释维度可以在训练用于合成图像的生成对抗网络（GAN）的潜在空间中出现。为了确定图像编辑的潜在维度，以前的方法通常会注释一个合成样本的集合，并在潜在空间中训练线性分类器。但是，他们需要对目标属性以及相应的手动注释进行明确的定义，从而限制了其实践中的应用程序。在这项工作中，我们研究了甘斯学到的内部表示，以无监督的方式揭示了潜在的变化因子。特别是，我们仔细研究了gan的发电机理，并进一步提出了一种通过直接分解预训练的重量来进行潜在语义发现的封闭形式分解算法。通过闪电实现，我们的方法不仅能够找到与最先进的监督方法相当的语义有意义的维度，而且还可以在多个在广泛数据集中训练的GAN模型中产生更广泛的概念。
A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In order to identify such latent dimensions for image editing, previous methods typically annotate a collection of synthesized samples and train linear classifiers in the latent space. However, they require a clear definition of the target attribute as well as the corresponding manual annotations, limiting their applications in practice. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. In particular, we take a closer look into the generation mechanism of GANs and further propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights. With a lightning-fast implementation, our approach is capable of not only finding semantically meaningful dimensions comparably to the state-of-the-art supervised methods, but also resulting in far more versatile concepts across multiple GAN models trained on a wide range of datasets.
