Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems
This work addresses the problem of creating efficient and regularized composite models for dense prediction tasks like stereo and segmentation, offering a novel integration method that is incremental in combining existing techniques.
The authors tackled the challenge of integrating graphical models with deep neural networks by developing a BP-Layer that combines truncated max-product Belief Propagation with backpropagation for learning, resulting in a hierarchical model that improves performance in stereo, optical flow, and semantic segmentation with parameter-efficient and robust solutions.
It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models. The main difficulties in implementing this in practice are associated with a discrepancy in suitable learning objectives as well as with the necessity of approximations for the inference. In this work we take one of the simplest inference methods, a truncated max-product Belief Propagation, and add what is necessary to make it a proper component of a deep learning model: We connect it to learning formulations with losses on marginals and compute the backprop operation. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs), allowing us to design a hierarchical model composing BP inference and CNNs at different scale levels. The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.