Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems
| Autor: | Christian Sormann, Friedrich Fraundorfer, Patrick Knöbelreiter, Alexander Shekhovtsov, Thomas Pock |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Artificial neural network Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Deep learning Computer Science - Computer Vision and Pattern Recognition Inference 02 engineering and technology 010501 environmental sciences Belief propagation 01 natural sciences Convolutional neural network Machine Learning (cs.LG) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Graphical model Artificial intelligence business 0105 earth and related environmental sciences Block (data storage) |
| Zdroj: | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) CVPR |
| DOI: | 10.1109/cvpr42600.2020.00792 |
| Popis: | 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. CVPR 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|