Research map / Learning theory and algorithms / Combinatorial and search optimization
Bottleneck Potentials in Markov Random Fields
Ahmed Abbas, Paul Swoboda
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add bottleneck potential to the MRF (ablation) | MRF · F3-Netherlands-I | Mean absolute deviation: 7.1435 -> 0.8881 | Improved |
| add bottleneck potential to the MRF (ablation) | MRF · F3-Netherlands-III | Mean absolute deviation: 3.2169 -> 0.0889 | Improved |
| add bottleneck potential to the MRF (ablation) | MRF · F3-Netherlands-II | Mean absolute deviation: 6.2105 -> 0.2644 | Improved |
| add bottleneck potential to the MRF (ablation) | MRF · Waka-3D-II | Mean absolute deviation: 0.0221 -> 0.0116 | Improved |
| add bottleneck potential to the MRF (ablation) | MRF · F3-Netherlands-V | Mean absolute deviation: 0.0896 -> 0.0894 | No clear effect |
| add bottleneck potential to the MRF (ablation) | MRF · Opunake-3D-I | Mean absolute deviation: 0.4786 -> 0.4887 | Hurt |
| add bottleneck potential to the MRF (ablation) | MRF · F3-Netherlands-VI | Mean absolute deviation: 2.4498 -> 1.6049 | Hurt |
| use B-MRF instead of greedy MST heuristic | MST · F3-Netherlands-VI | Mean absolute deviation: 1.5319 -> 1.6049 | Hurt |
| use B-MRF instead of greedy MST heuristic | MST · F3-Netherlands-I | Mean absolute deviation: 1.6212 -> 0.8881 | Improved |
| add bottleneck potential to the MRF (runtime cost) (ablation) | MRF · F3-Netherlands-I | Runtime (seconds): 673 -> 1820 | Hurt |
| add bottleneck potential to the MRF (runtime cost) (ablation) | MRF · Waka-3D-IV | Runtime (seconds): 781 -> 8158 | Hurt |
Closest papers by meaning
- Relaxation-Based Preprocessing Techniques for Markov Random Field Inference (CVPR 2016 · similarity 0.87)
- Continuous Relaxation of MAP Inference: A Nonconvex Perspective (CVPR 2018 · similarity 0.87)
- Efficient semidefinite-programming-based inference for binary and multi-class MRFs (NeurIPS 2020 · similarity 0.86)
- Partial Optimality by Pruning for MAP-Inference with General Graphical Models (TPAMI 2016 · similarity 0.85)
- Newton-Type Methods for Inference in Higher-Order Markov Random Fields (CVPR 2017 · similarity 0.85)
- Scalable Inference of Sparsely-changing Gaussian Markov Random Fields (NeurIPS 2021 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
