Visible to the public Multitask Adversarial Learning for Chinese Font Style Transfer

TitleMultitask Adversarial Learning for Chinese Font Style Transfer
Publication TypeConference Paper
Year of Publication2020
AuthorsWu, L., Chen, X., Meng, L., Meng, X.
Conference Name2020 International Joint Conference on Neural Networks (IJCNN)
Date Publishedjul
Keywordscharacter images, character recognition, character sets, Chinese character complexity, Chinese font datasets, Chinese font style transfer, cross-task interactions, Decoding, fine-grained parts, font generation, Gallium nitride, gan, general style transfer, Generators, learning (artificial intelligence), Libraries, machine learning, MTfontGAN, multiple target ones, multitask, multitask adversarial learning, natural language processing, neural nets, neural style transfer, overfitting problem, Predictive Metrics, pubcrawl, reference font, Resiliency, Scalability, style transfer, Task Analysis, Training
AbstractStyle transfer between Chinese fonts is challenging due to both the complexity of Chinese characters and the significant difference between fonts. Existing algorithms for this task typically learn a mapping between the reference and target fonts for each character. Subsequently, this mapping is used to generate the characters that do not exist in the target font. However, the characters available for training are unlikely to cover all fine-grained parts of the missing characters, leading to the overfitting problem. As a result, the generated characters of the target font may suffer problems of incomplete or even radicals and dirty dots. To address this problem, this paper presents a multi-task adversarial learning approach, termed MTfontGAN, to generate more vivid Chinese characters. MTfontGAN learns to transfer a reference font to multiple target ones simultaneously. An alignment is imposed on the encoders of different tasks to make them focus on the important parts of the characters in general style transfer. Such cross-task interactions at the feature level effectively improve the generalization capability of MTfontGAN. The performance of MTfontGAN is evaluated on three Chinese font datasets. Experimental results show that MTfontGAN outperforms the state-of-the-art algorithms in a single-task setting. More importantly, increasing the number of tasks leads to better performance in all of them.
Citation Keywu_multitask_2020