论文标题
自然图像中的通用性挽救了gan：使用通用和无隐私的合成数据预处理剂量
Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data
论文作者
论文摘要
在低射门制度下，gan的转移学习成功地改善了发电性能。但是，现有的研究表明，使用单个基准数据集的经过审计的模型并未推广到各种目标数据集。更重要的是，随着成员推理攻击的进步，预审最终的模型可能容易受到版权或隐私风险的影响。为了解决这两个问题，我们提出了一个有效且无偏的数据合成器，即原始ps，灵感来自自然图像的通用特征。具体而言，我们利用1）频率频谱上的通用统计数据，2）基本形状（即通过基本形状的图像组成）来表示结构信息，以及3）显着存在。由于我们的合成器仅考虑自然图像的通用属性，因此在我们数据集上预处理的单个模型可以始终转移到各种目标数据集中，甚至超过了以前的方法，从FR'Echet Inception Intection距离方面预处理了自然图像。广泛的分析，消融研究和评估表明，我们的数据合成器的每个组成部分都是有效的，并提供了有关牙GAN可转移性的理想模型的理想性质的见解。
Transfer learning for GANs successfully improves generation performance under low-shot regimes. However, existing studies show that the pretrained model using a single benchmark dataset is not generalized to various target datasets. More importantly, the pretrained model can be vulnerable to copyright or privacy risks as membership inference attack advances. To resolve both issues, we propose an effective and unbiased data synthesizer, namely Primitives-PS, inspired by the generic characteristics of natural images. Specifically, we utilize 1) the generic statistics on the frequency magnitude spectrum, 2) the elementary shape (i.e., image composition via elementary shapes) for representing the structure information, and 3) the existence of saliency as prior. Since our synthesizer only considers the generic properties of natural images, the single model pretrained on our dataset can be consistently transferred to various target datasets, and even outperforms the previous methods pretrained with the natural images in terms of Fr'echet inception distance. Extensive analysis, ablation study, and evaluations demonstrate that each component of our data synthesizer is effective, and provide insights on the desirable nature of the pretrained model for the transferability of GANs.
