Recent studies on Generative Adversarial Network (GAN) reveal that different
layers of a generative CNN hold different semantics of the synthesized images.
However, few GAN models have explicit dimensions to control the semantic
attributes represented in a specific layer. This paper proposes EigenGAN which
is able to unsupervisedly mine interpretable and controllable dimensions from
different generator layers. Specifically, EigenGAN embeds one linear subspace
with orthogonal basis into each generator layer. Via generative adversarial
training to learn a target distribution, these layer-wise subspaces
automatically discover a set of "eigen-dimensions" at each layer corresponding
to a set of semantic attributes or interpretable variations. By traversing the
coefficient of a specific eigen-dimension, the generator can produce samples
with continuous changes corresponding to a specific semantic attribute. Taking
the human face for example, EigenGAN can discover controllable dimensions for
high-level concepts such as pose and gender in the subspace of deep layers, as
well as low-level concepts such as hue and color in the subspace of shallow
layers. Moreover, in the linear case, we theoretically prove that our algorithm
derives the principal components as PCA does. Codes can be found in
this https URL

该论文提出了 EigenGAN，它可以从不同的生成器层无监督地挖掘可解释的和可控制的维度，以控制生成影像的语义属性。利用线性子空间的概念，EigenGAN 可以发现每一层的一组特征维度与某些可解释的变量对应，并通过这些维度进行语义属性的控制 —— 例如，语义上的高级概念如姿态和性别对应于深层的子空间，颜色等低级概念则对应于浅层的子空间。线性情况下，该算法得到的主要维度和 PCA 一样。