Our goal is to generate fonts with specific impressions, by training a generative adversarial network with a font dataset with impression labels. The main difficulty is that font impression is ambiguous and the absence of an impression label does not always mean that the font does not have the impression. This paper proposes a font generation model that is robust against missing impression labels. The key ideas of the proposed method are (1)a co-occurrence-based missing label estimator and (2)an impression label space compressor. The first is to interpolate missing impression labels based on the co-occurrence of labels in the dataset and use them for training the model as completed label conditions. The second is an encoder-decoder module to compress the high-dimensional impression space into low-dimensional. We proved that the proposed model generates high-quality font images using multi-label data with missing labels through qualitative and quantitative evaluations.
翻译:我们的目标是通过培训带有带有印有标签的字体数据集的基因对抗网络,生成带有具体印象的字体。主要困难在于字体印象模糊,没有印象标签并不一定意味着字体没有印象。本文提出了一种对丢失的印象标签具有强力的字体生成模型。拟议方法的主要想法是(1) 一种基于共同出现的缺失标签估计器和(2) 印象标签的空间压缩机。首先,根据数据集中标签的共发情况,对缺失的印象标签进行内插,并将它们作为完整的标签条件来培训模型。第二个是将高维面印象空间压缩到低维度的编码解码器模块。我们证明,拟议的模型通过定性和定量评估,利用缺少标签的多标签数据生成高质量的字体图像。