论文标题
对图像生成中数据效率gan的全面调查
A Comprehensive Survey on Data-Efficient GANs in Image Generation
论文作者
论文摘要
生成对抗网络（GAN）在图像合成中取得了显着的成就。这些甘斯的成功取决于大规模数据集，需要太多的成本。借助有限的培训数据，如何稳定gan的训练过程并产生逼真的图像引起了更多的关注。数据效率gan（de-gan）的挑战主要来自三个方面：（i）训练和目标分布之间的不匹配，（ii）歧视者过度拟合，以及（iii）潜在空间和数据空间之间的不平衡。尽管已经提出了许多减轻这些问题的增强和培训策略，但缺乏系统的调查来总结De-Gans的财产，挑战和解决方案。在本文中，我们从分布优化的角度重新访问和定义了de-gan。我们总结并分析了De-Gans的挑战。同时，我们提出了一种分类法，该分类法将现有方法分为三类：数据选择，gans优化和知识共享。最后但并非最不重要的一点是，我们试图强调当前的问题和未来的方向。
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.
