Generative Adversarial Networks (GANs) have achieved remarkable achievements in image synthesis. These successes of GANs rely on large scale datasets, requiring too much cost. With limited training data, how to stable the training process of GANs and generate realistic images have attracted more attention. The challenges of Data-Efficient GANs (DE-GANs) mainly arise from three aspects: (i) Mismatch Between Training and Target Distributions, (ii) Overfitting of the Discriminator, and (iii) Imbalance Between Latent and Data Spaces. Although many augmentation and pre-training strategies have been proposed to alleviate these issues, there lacks a systematic survey to summarize the properties, challenges, and solutions of DE-GANs. In this paper, we revisit and define DE-GANs from the perspective of distribution optimization. We conclude and analyze the challenges of DE-GANs. Meanwhile, we propose a taxonomy, which classifies the existing methods into three categories: Data Selection, GANs Optimization, and Knowledge Sharing. Last but not the least, we attempt to highlight the current problems and the future directions.
翻译:在图像合成方面,GAN的成功依靠大规模数据集,费用太高。由于培训数据有限,如何稳定GAN的培训过程和产生现实的图像引起了更多的注意。数据高效GAN(DE-GAN)的挑战主要来自三个方面:(一) 培训与目标分布之间的误差,(二) 差异分配,(三) 隐藏空间与数据空间之间的不平衡。虽然提出了许多增强和训练前战略来缓解这些问题,但缺乏系统调查来总结DE-GAN的特性、挑战和解决办法。在本文件中,我们从分配优化的角度重新审视和界定DE-GAN(DE-GAN)的挑战。我们总结和分析DE-GAN的挑战。同时,我们建议一种分类法,将现有方法分为三类:数据选择、GAN的优化和知识分享。最后但并非最不重要的一点是,我们试图强调当前和未来的方向。