MetalGAN：使用cGANs和元学习的多域无标签图像合成
MetalGAN: Multi-Domain Label-Less Image Synthesis Using cGANs and Meta-Learning
摘要：
图像合成是当前计算机视觉和深度学习研究领域中最受关注的图像处理课题之一。研究者们致力于解决这一问题，主要集中在图像质量和尺寸、域和姿态变化、网络结构等方面，其中，使用单一结构生成不同域的图像是图像生成的一个重要目标。事实上，一个单一的多域网络将允许更大的灵活性和鲁棒性的图像合成任务比其他方法。本文提出了一种新的结构和训练算法，它能够产生多域输出使用一个单一的网络。数据集的一小部分是有意使用的，并且没有硬编码的标签（或类）。这是通过结合用于图像生成的条件生成对抗网络（cGAN）和用于域切换的元学习算法来实现的，我们称我们的方法为MetalGAN。该方法已被证明是适当的解决多领域的问题，并验证了面部属性转移，使用CelebA数据集。
英文摘要：
Image synthesis is currently one of the most addressed image processing topic in computer vision and deep learning fields of study. Researchers have tackled this problem focusing their efforts on its several challenging problems, e.g. image quality and size, domain and pose changing, architecture of the networks, and so on. Above all, producing images belonging to different domains by using a single architecture is a very relevant goal for image generation. In fact, a single multi-domain network would allow greater flexibility and robustness in the image synthesis task than other approaches. This paper proposes a novel architecture and a training algorithm, which are able to produce multi-domain outputs using a single network. A small portion of a dataset is intentionally used, and there are no hard-coded labels (or classes). This is achieved by combining a conditional Generative Adversarial Network (cGAN) for image generation and a Meta-Learning algorithm for domain switch, and we called our approach MetalGAN. The approach has proved to be appropriate for solving the multi-domain problem and it is validated on facial attribute transfer, using CelebA dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
