We present Flow-Guided Density Ratio Learning (FDRL), a simple and scalable approach to generative modeling which builds on the stale (time-independent) approximation of the gradient flow of entropy-regularized f-divergences introduced in DGflow. In DGflow, the intractable time-dependent density ratio is approximated by a stale estimator given by a GAN discriminator. This is sufficient in the case of sample refinement, where the source and target distributions of the flow are close to each other. However, this assumption is invalid for generation and a naive application of the stale estimator fails due to the large chasm between the two distributions. FDRL proposes to train a density ratio estimator such that it learns from progressively improving samples during the training process. We show that this simple method alleviates the density chasm problem, allowing FDRL to generate images of dimensions as high as $128\times128$, as well as outperform existing gradient flow baselines on quantitative benchmarks. We also show the flexibility of FDRL with two use cases. First, unconditional FDRL can be easily composed with external classifiers to perform class-conditional generation. Second, FDRL can be directly applied to unpaired image-to-image translation with no modifications needed to the framework. Code is publicly available at https://github.com/ajrheng/FDRL.

翻译：我们提出流引导密度比学习（FDRL），这是一种简单且可扩展的生成建模方法，其建立在DGflow中引入的熵正则化f-散度梯度流的静态（时间无关）近似之上。在DGflow中，难以处理的时间相关密度比由GAN判别器给出的静态估计器近似。这种做法在样本精炼场景下是充分的，因为此时流的源分布与目标分布彼此接近。然而，该假设在生成任务中不成立，由于两个分布之间存在巨大鸿沟，直接应用静态估计器会导致失败。FDRL提出训练一个密度比估计器，使其能够在训练过程中从逐步改善的样本中学习。我们证明这种简单方法缓解了密度鸿沟问题，使FDRL能够生成高达$128\times128$维度的图像，并在定量基准测试中优于现有梯度流基线方法。我们还通过两个应用场景展示了FDRL的灵活性。第一，无条件FDRL可轻松与外部分类器组合实现类别条件生成。第二，FDRL可直接应用于无配对图像到图像翻译任务，而无需对框架进行任何修改。代码已在https://github.com/ajrheng/FDRL公开。