论文标题
对抗分数匹配和改进图像生成的采样
Adversarial score matching and improved sampling for image generation
论文作者
论文摘要
与退火的Langevin采样（DSM-ALS）的去核得分匹配最近发现了生成建模的成功。该方法通过首先训练神经网络来估计分布的得分，然后使用langevin Dynamics从分数网络假定的数据分布中进行采样。尽管样本的视觉质量令人信服，但这种方法的性能似乎比FréchetInception Inception距离下的生成对抗网络（GAN）差，这是生成模型的标准指标。 我们表明，当使用得分网络降解最终的langevin样品时，这种明显的差距消失了。此外，我们提出了对DSM-ALS的两种改进：1）一致的退火抽样作为退火Langevin采样的更稳定的替代方案，以及2）混合训练表格，由deNo的得分匹配和对抗性目标组成。通过组合这两种技术并探索不同的网络体系结构，我们提高了得分匹配方法，并获得了与CIFAR-10上最新图像生成的结果竞争。
Denoising Score Matching with Annealed Langevin Sampling (DSM-ALS) has recently found success in generative modeling. The approach works by first training a neural network to estimate the score of a distribution, and then using Langevin dynamics to sample from the data distribution assumed by the score network. Despite the convincing visual quality of samples, this method appears to perform worse than Generative Adversarial Networks (GANs) under the Fréchet Inception Distance, a standard metric for generative models. We show that this apparent gap vanishes when denoising the final Langevin samples using the score network. In addition, we propose two improvements to DSM-ALS: 1) Consistent Annealed Sampling as a more stable alternative to Annealed Langevin Sampling, and 2) a hybrid training formulation, composed of both Denoising Score Matching and adversarial objectives. By combining these two techniques and exploring different network architectures, we elevate score matching methods and obtain results competitive with state-of-the-art image generation on CIFAR-10.
