Learning Discriminative Style Representations for Unsupervised and Few-Shot Artistic Portrait Drawing Generation

Abstract

In this paper, we propose an unsupervised artistic portrait drawing generation method for few-shot datasets based on contrastive learning of style features. Firstly, we construct a discriminative style encoder with contrastive learning, improving the ability of the encoder to separate style features. Secondly, based on the dynamic codebook and momentum network, we used historical average features instead of batch instance features to prevent the problem of style bias in few-shot datasets. Finally, a conditional projection discriminator with filter response normalization is utilized to improve the discriminative ability of the discriminator and the stability of the generative adversarial network, which motivates the generator to synthesize more realistic image details. Quantitative and qualitative analysis show that the method proposed in this paper significantly improves the quality of artistic portrait drawing generation, and outperforms existing benchmarks in terms of visual effect and metrics evaluation. Our code and results are avilable at https://github.com/AiArt-HDU/Co-GAN.