Differentiable Nonparametric Belief Propagation
This work addresses the need for more automated and data-driven inference in graphical models, particularly for pose tracking, but it is incremental as it builds on existing nonparametric belief propagation methods.
The paper tackles the problem of learning probabilistic factors for nonparametric belief propagation by replacing hand-crafted factors with differentiable neural networks, enabling end-to-end training from labeled data. Results on articulated pose tracking tasks show effectiveness, with practical advantages over hand-crafted approaches.
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 a recurrent neural network. Results from this comparison demonstrate the effectiveness of using learned factors for tracking and suggest the practical advantage over hand-crafted approaches. The project webpage is available at: progress.eecs.umich.edu/projects/dnbp.