Zand Mohsen, Etemad Ali, Greenspan Michael
IEEE Trans Pattern Anal Mach Intell. 2023 Nov;45(11):13523-13535. doi: 10.1109/TPAMI.2023.3296446. Epub 2023 Oct 3.
Conditional Normalizing Flows (CNFs) are flexible generative models capable of representing complicated distributions with high dimensionality and large interdimensional correlations, making them appealing for structured output learning. Their effectiveness in modelling multivariates spatio-temporal structured data has yet to be completely investigated. We propose MotionFlow as a novel normalizing flows approach that autoregressively conditions the output distributions on the spatio-temporal input features. It combines deterministic and stochastic representations with CNFs to create a probabilistic neural generative approach that can model the variability seen in high-dimensional structured spatio-temporal data. We specifically propose to use conditional priors to factorize the latent space for the time dependent modeling. We also exploit the use of masked convolutions as autoregressive conditionals in CNFs. As a result, our method is able to define arbitrarily expressive output probability distributions under temporal dynamics in multivariate prediction tasks. We apply our method to different tasks, including trajectory prediction, motion prediction, time series forecasting, and binary segmentation, and demonstrate that our model is able to leverage normalizing flows to learn complicated time dependent conditional distributions.
条件归一化流（CNFs）是灵活的生成模型，能够表示具有高维度和大维度间相关性的复杂分布，这使得它们在结构化输出学习中颇具吸引力。其在对多变量时空结构化数据进行建模方面的有效性尚未得到充分研究。我们提出了MotionFlow，这是一种新颖的归一化流方法，它以时空输入特征为自回归条件来确定输出分布。它将确定性和随机表示与CNFs相结合，创建了一种概率神经生成方法，该方法可以对高维结构化时空数据中的变异性进行建模。我们特别提出使用条件先验对潜在空间进行因式分解，以用于时间相关建模。我们还利用掩码卷积作为CNFs中的自回归条件。因此，我们的方法能够在多变量预测任务的时间动态下定义任意表达性的输出概率分布。我们将我们的方法应用于不同任务，包括轨迹预测、运动预测、时间序列预测和二元分割，并证明我们的模型能够利用归一化流来学习复杂的时间相关条件分布。
