We propose a discrete latent distribution for Generative Adversarial Networks (GANs). Instead of drawing latent vectors from a continuous prior, we sample from a finite set of learnable latents. However, a direct parametrization of such a distribution leads to an intractable linear increase in memory in order to ensure sufficient sample diversity. We address this key issue by taking inspiration from the encoding of information in biological organisms. Instead of learning a separate latent vector for each sample, we split the latent space into a set of genes. For each gene, we train a small bank of gene variants. Thus, by independently sampling a variant for each gene and combining them into the final latent vector, our approach can represent a vast number of unique latent samples from a compact set of learnable parameters. Interestingly, our gene-inspired latent encoding allows for new and intuitive approaches to latent-space exploration, enabling conditional sampling from our unconditionally trained model. Moreover, our approach preserves state-of-the-art photo-realism while achieving better disentanglement than the widely-used StyleMapping network.
翻译:我们为生成对抗网络(GANs)提出了一种离散的潜在分布。我们不是从连续的先验分布中绘制潜在向量,而是从可学习的有限潜在集合中进行抽样。但是,直接参数化这种分布会导致内存呈线性增长,以确保足够的样本多样性变得不可解决。我们通过从生物体的信息编码中汲取灵感来解决这个关键问题。我们将潜在空间分割为一组基因,为每个基因训练一小组基因变体。因此,通过独立地为每个基因采样变体并将它们组合成最终的潜在向量,我们的方法可以从一组紧凑的可学习参数中表示大量唯一的潜在样本。有趣的是,我们的基因启发的潜在编码允许对潜在空间进行新颖直观的探索,实现从我们的无条件训练模型中进行有条件的采样。此外,我们的方法在保持最先进的照片逼真度的同时,实现了比广泛使用的 StyleMapping 网络更好的解缠结。