We present a novel method to solve image analogy problems : it allows to
learn the relation between paired images present in training data, and then
generalize and generate images that correspond to the relation, but were never
seen in the training set. Therefore, we call the method Conditional Analogy
Generative Adversarial Network (CAGAN), as it is based on adversarial training
and employs deep convolutional neural networks. An especially interesting
application of that technique is automatic swapping of clothing on fashion
model photos. Our work has the following contributions. First, the definition
of the end-to-end trainable CAGAN architecture, which implicitly learns
segmentation masks without expensive supervised labeling data. Second,
experimental results show plausible segmentation masks and often convincing
swapped images, given the target article. Finally, we discuss the next steps
for that technique: neural network architecture improvements and more advanced
applications.

该研究提出了一种基于深度卷积神经网络和条件类比生成对抗网络的图像类比问题求解方法，可以通过训练数据中成对图像的关系来生成具有该关系的图像，并且可以在时尚模特照片上自动交换服装，目前的实验结果表明该方法可以学习到成对图像间隐性的分割掩模，生成的图片效果较好，并提出了神经网络结构的改进和更高级的应用方向。