文献类型：会议论文

英文题名：Improving Few-shot Image Generation by Structural Discrimination and Textural Modulation

作者：Yang, Mengping[1];Wang, Zhe[1];Feng, Wenyi[1];Zhang, Qian[2];Xiao, Ting[2]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Key Lab Smart Mfg Energy Chem Proc, Shanghai, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai, Peoples R China

会议论文集：31st ACM International Conference on Multimedia (MM)

会议日期：OCT 29-NOV 03, 2023

会议地点：Ottawa, CANADA

语种：英文

外文关键词：Few-shot Learning; Image Generation; Textural Modulation; Structural Discrimination

摘要：Few-shot image generation, which aims to produce plausible and diverse images for one category given a fewimages from this category, has drawn extensive attention. Existing approaches either globally interpolate different images or fuse local representations with pre-defined coefficients. However, such an intuitive combination of images/features only exploits the most relevant information for generation, leading to poor diversity and coarse-grained semantic fusion. To remedy this, this paper proposes a novel textural modulation (TexMod) mechanism to inject external semantic signals into internal local representations. Parameterized by the feedback from the discriminator, our TexMod enables more fined-grained semantic injection while maintaining the synthesis fidelity. Moreover, a global structural discriminator (StructD) is developed to explicitly guide the model to generate images with reasonable layout and outline. Furthermore, the frequency awareness of the model is reinforced by encouraging the model to distinguish frequency signals. Together with these techniques, we build a novel and effective model for few-shot image generation. The effectiveness of our model is identified by extensive experiments on three popular datasets and various settings. Besides achieving state-of-the-art synthesis performance on these datasets, our proposed techniques could be seamlessly integrated into existing models for a further performance boost. Our code and models are available at here.