PFGM ++：释放物理启发生成模型的潜力
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
摘要：
我们介绍了一个新的家庭的物理启发生成模型称为PFGM++，统一扩散模型和泊松流生成模型（PFGM）。这些模型通过在$N{+}D$维空间中嵌入路径来实现$N$维数据的生成轨迹，同时仍然用$D$附加变量的简单标量范数来控制进展。当$D{=}1$和$D{\to}\infty$时，新模型分别简化为PFGM和扩散模型.选择$D$的灵活性使我们能够权衡稳健性和刚性，因为增加$D$会导致数据和附加变量范数之间的耦合更加集中。我们免除了有偏见的大批量场PFGM中使用的目标，而是提供了一个无偏的扰动为基础的目标类似于扩散模型。为了探索不同的选择$D$，我们提供了一个直接对齐的方法，从扩散模型（$D{\to} \infty$），以任何有限的$D$值良好调整的超参数。我们的实验表明，具有有限$D$的模型在CIFAR-10/FFHQ $64{\times}64$数据集上优于先前最先进的扩散模型，当$D{=}2048/128$时，具有$1.91/2.43$的FID分数。在类条件设置中，$D{=}2048$在CIFAR-10上产生当前最先进的FID $1.74$。此外，我们证明了具有较小$D$的模型对建模误差具有更好的鲁棒性。代码可在https://github.com/Newbeeer/pfgmpp上获得
英文摘要：
We introduce a new family of physics-inspired generative models termed PFGM++ that unifies diffusion models and Poisson Flow Generative Models (PFGM). These models realize generative trajectories for $N$ dimensional data by embedding paths in $N{+}D$ dimensional space while still controlling the progression with a simple scalar norm of the $D$ additional variables. The new models reduce to PFGM when $D{=}1$ and to diffusion models when $D{\to}\infty$. The flexibility of choosing $D$ allows us to trade off robustness against rigidity as increasing $D$ results in more concentrated coupling between the data and the additional variable norms. We dispense with the biased large batch field targets used in PFGM and instead provide an unbiased perturbation-based objective similar to diffusion models. To explore different choices of $D$, we provide a direct alignment method for transferring well-tuned hyperparameters from diffusion models ($D{\to} \infty$) to any finite $D$ values. Our experiments show that models with finite $D$ can be superior to previous state-of-the-art diffusion models on CIFAR-10/FFHQ $64{\times}64$ datasets, with FID scores of $1.91/2.43$ when $D{=}2048/128$. In class-conditional setting, $D{=}2048$ yields current state-of-the-art FID of $1.74$ on CIFAR-10. In addition, we demonstrate that models with smaller $D$ exhibit improved robustness against modeling errors. Code is available at https://github.com/Newbeeer/pfgmpp
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
