We present a differentiable approach to learn the probabilistic factors used for inference by a nonparametric belief propagation algorithm. Existing nonparametric belief propagation methods rely on domain-specific features encoded in the probabilistic factors of a graphical model. In this work, we replace each crafted factor with a differentiable neural network enabling the factors to be learned using an efficient optimization routine from labeled data. By combining differentiable neural networks with an efficient belief propagation algorithm, our method learns to maintain a set of marginal posterior samples using end-to-end training. We evaluate our differentiable nonparametric belief propagation (DNBP) method on a set of articulated pose tracking tasks and compare performance with learned baselines. Results from these experiments demonstrate the effectiveness of using learned factors for tracking and suggest the practical advantage over hand-crafted approaches. The project webpage is available at: https://progress.eecs.umich.edu/projects/dnbp/ .

翻译：我们提出一种可微方法，用于学习非参数信念传播算法推理所使用的概率因子。现有非参数信念传播方法依赖于编码在图模型概率因子中的领域特定特征。本研究用可微神经网络替代每个手工构建的因子，使因子能够通过有标签数据的有效优化过程进行学习。通过将可微神经网络与高效信念传播算法相结合，我们的方法利用端到端训练来学习维护一组边缘后验样本。我们在多个关节姿态追踪任务上评估了可微非参数信念传播（DNBP）方法，并与学习基线进行了性能比较。实验结果表明，使用学习得到的因子进行追踪具有有效性，并显示出相较于手工构建方法的实际优势。项目网页见：https://progress.eecs.umich.edu/projects/dnbp/ 。