A neural artistic style transformation (NST) model can modify the appearance
of a simple image by adding the style of a famous image. Even though the
transformed images do not look precisely like artworks by the same artist of
the respective style images, the generated images are appealing. Generally, a
trained NST model specialises in a style, and a single image represents that
style. However, generating an image under a new style is a tedious process,
which includes full model training. In this paper, we present two methods that
step toward the style image independent neural style transfer model. In other
words, the trained model could generate semantically accurate generated image
under any content, style image input pair. Our novel contribution is a
unidirectional-GAN model that ensures the Cyclic consistency by the model
architecture.Furthermore, this leads to much smaller model size and an
efficient training and validation phase.

本文提出了一种新的神经样式转换模型，它是基于无需相关风格图像，可用于任何内容和风格的输入形成语义准确的生成图像，规避了全模型训练的烦恼，并通过单向 GAN 模型的确保循环一致性的结构，实现了更高效的训练和验证阶段以及更小的模型尺寸。

有条件的对抗神经艺术风格转移

Neural Artistic Style Transfer with Conditional Adversaria

Convolutional neural networks (CNNs) have been successfully applied to solve
the problem of correspondence estimation between semantically related images.
Due to non-availability of large training datasets, existing methods resort to
self-supervised or unsupervised training paradigm. In this paper we propose a
semi-supervised learning framework that imposes cyclic consistency constraint
on unlabeled image pairs. Together with the supervised loss the proposed model
achieves state-of-the-art on a benchmark semantic matching dataset.

本文提出了一种半监督学习框架，为无标签图像对增加循环一致性限制，在监督丢失和无监督训练中实现了最先进的语义匹配性能。

半监督语义匹配

Semi-Supervised Semantic Matching

CycleGAN (Zhu et al. 2017) is one recent successful approach to learn a
transformation between two image distributions. In a series of experiments, we
demonstrate an intriguing property of the model: CycleGAN learns to "hide"
information about a source image into the images it generates in a nearly
imperceptible, high-frequency signal. This trick ensures that the generator can
recover the original sample and thus satisfy the cyclic consistency
requirement, while the generated image remains realistic. We connect this
phenomenon with adversarial attacks by viewing CycleGAN's training procedure as
training a generator of adversarial examples and demonstrate that the cyclic
consistency loss causes CycleGAN to be especially vulnerable to adversarial
attacks.

CycleGAN 可以学习到将两个图像分布之间的转化，并且会将源图像信息隐藏在其生成的图像中，从而保证了循环一致性，然而其通过循环一致性来保证生成的图像真实性导致了其容易受到对抗攻击的影响。