Distributed message passing for large scale graphical models

By Alexander Gerhard Schwing, Tamir Hazan, Marc Pollefeys, Raquel Urtasun. 2011

83 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Hardware and Architecture

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Raquel Urtasun
2. Sanja Fidler
3. Tamir Hazan
4. Alexander Gerhard Schwing
5. Francesc Moreno-Noguer
6. David A. McAllester
7. Marc Pollefeys
8. Lise Getoor

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Raquel Urtasun
3. Jitendra Malik
4. Dacheng Tao
5. Abhinav Kumar Gupta
6. Sanja Fidler
7. Xiaogang Wang
8. Trevor Darrell

In Hardware and Architecture

1. Raquel Urtasun
2. Sanja Fidler
3. Tamir Hazan
4. Alexander Gerhard Schwing
5. Lise Getoor

Citations in the corpus

• A High Performance CRF Model for Clothes Parsing (2014, methodology): “We use a message passing algorithm, distributed convex belief propagation [29] to perform inference.”
• Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs (2013, background): “Inference is performed via message passing [31] and so it places no restrictions (e.”
• Deep Structured Prediction with Nonlinear Output Transformations (2018, background): “Several works studied the learning problem when inference is hard [13, 26, 40, 17, 33, 23, 43, 35], designing effective approximations.”
• Blending Learning and Inference in Conditional Random Fields (2016, methodology): “In practice, block coordinate descent with analytic steps provides a significant speedup over conventional gradient methods and can be parallelized and distributed easily, as shown by Schwing et al. (2011).”
• AD3: alternating directions dual decomposition for MAP inference in graphical models (2015, unknown): “This has been shown to be very useful for large-scale message-passing inference in graphical models (Felzenszwalb and Huttenlocher, 2006; Low et al., 2010; Schwing et al., 2011).”
• Holistic Scene Understanding for 3D Object Detection with RGBD Cameras (2013, methodology): “We resort to the approximated algorithm of [21], which combines LP relaxations and dual decomposition to obtained a parallel algorithm which is guaranteed to converge.”
• Efficient Structured Prediction with Latent Variables for General Graphical Models (2012, methodology): “To parallelize message passing one could employ (Schwing et al., 2011).”
• The Benefits of Learning with Strongly Convex Approximate Inference (2015, methodology): “For all variational inference algorithms, we use our own implementation of counting number belief propagation (CBP), based on Schwing et al.’s (2011) message updates; this can optimize any variational method whose entropy can be expressed with counting numbers.”
• Continuous Markov Random Fields for Robust Stereo Estimation (2012, methodology): “In our implementation, we use the distributed message passing algorithm of [43] to solve the discretized MRF at each iteration.”