We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of pre-trained deep generative networks DGNs). Leveraging the fact that DGNs are, or can be approximated by, continuous piecewise affine splines, we derive the analytical DGN output space distribution as a function of the product of the DGN's Jacobian singular values raised to a power $\rho$. We dub $\rho$ the $\textbf{polarity}$ parameter and prove that $\rho$ focuses the DGN sampling on the modes ($\rho < 0$) or anti-modes ($\rho > 0$) of the DGN output-space distribution. We demonstrate that nonzero polarity values achieve a better precision-recall (quality-diversity) Pareto frontier than standard methods, such as truncation, for a number of state-of-the-art DGNs. We also present quantitative and qualitative results on the improvement of overall generation quality (e.g., in terms of the Frechet Inception Distance) for a number of state-of-the-art DGNs, including StyleGAN3, BigGAN-deep, NVAE, for different conditional and unconditional image generation tasks. In particular, Polarity Sampling redefines the state-of-the-art for StyleGAN2 on the FFHQ Dataset to FID 2.57, StyleGAN2 on the LSUN Car Dataset to FID 2.27 and StyleGAN3 on the AFHQv2 Dataset to FID 3.95. Demo: bit.ly/polarity-samp
翻译:我们提出极地采样,这是理论上合理的控制经过训练的深层基因网络DGNS的生成质量和多样性的插件和游戏方法。 利用DGNS是或可以被连续的片段折合的样条样条,我们得出分析性的DGN输出空间分布,作为DGG的Jacobian单数值提升到一个功率的产物的函数。 我们用美元计算出美元,这是控制经过训练的深层基因网络DGNS质量和多样性的一种理论上合理的插件方法。 利用DGN输出空间分布的模型(rho < 0$)或反模式(\rho > 0$)。 我们证明,非零极地值比标准方法(例如电解码)更精确地点(例如,对于一些最先进的DGNGNS) 参数,我们用美元来显示GNGNG样本质量的改进的数量和质量结果(eg-ral2, 以BGGGGS Stal-ral-ralS 数据为BQ,以BGGGS-deal-deal-deal- dal- dalal- dal- dal) 数字。