论文标题
细颗粒的卡通脸生成的知识转移很少
Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation
论文作者
论文摘要
在本文中，我们有兴趣为各组生成细粒度的卡通面。我们假设其中一个组由足够的培训数据组成，而其他组仅包含很少的样本。尽管这些群体的卡通面积具有相似的风格，但各组中的外观仍然可能具有一些特定的特征，这使它们彼此不同。这项任务的一个主要挑战是如何在群体之间转移知识并仅使用几个样本学习群体特定特征。为了解决这个问题，我们提出了一个两阶段的培训过程。首先，对基本组的基本翻译模型（由足够的数据组成）进行了训练。然后，给定其他组的新样本，我们通过为每个新组创建特定组的分支来扩展基本模型。直接更新组特定的分支以捕获每个组的特定外观，而剩余的组共享参数则间接更新以维护中间特征空间的分布。通过这种方式，我们的方法能够为各个群体生成高质量的卡通面孔。
In this paper, we are interested in generating fine-grained cartoon faces for various groups. We assume that one of these groups consists of sufficient training data while the others only contain few samples. Although the cartoon faces of these groups share similar style, the appearances in various groups could still have some specific characteristics, which makes them differ from each other. A major challenge of this task is how to transfer knowledge among groups and learn group-specific characteristics with only few samples. In order to solve this problem, we propose a two-stage training process. First, a basic translation model for the basic group (which consists of sufficient data) is trained. Then, given new samples of other groups, we extend the basic model by creating group-specific branches for each new group. Group-specific branches are updated directly to capture specific appearances for each group while the remaining group-shared parameters are updated indirectly to maintain the distribution of intermediate feature space. In this manner, our approach is capable to generate high-quality cartoon faces for various groups.
