Research map / Learning theory and algorithms / Combinatorial and search optimization
Consensus Maximisation Using Influences of Monotone Boolean Functions
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use influence-guided MBF-MaxCon instead of A*-NAPA-DIBP | linearized fundamental matrix estimation · KITTI Odometry frames 104-108, 198-201, 417-420, 579-582, 738-742 | inliers: 289 -> 288.52; 296 -> 293.10; 366 -> 364.44; 523 -> 520.68; 462 -> 460.97 | Mixed |
| Use MBF-MaxCon instead of Lo-RANSAC with the same computation budget | linearized fundamental matrix estimation · breadcube, breadtoy, cubetoy | inliers: 63.66 -> 64.36; 107.23 -> 107.48; 56.14 -> 58.51 | Helped |
| Re-estimate influences after each removal rather than computing them only at the start (ablation) | MBF-MaxCon · synthetic 8-dimensional robust linear regression | inliers found compared with the global optimum | Helped |
| Recompute influences for all remaining points rather than only basis points (ablation) | MBF-MaxCon · synthetic 8-dimensional robust linear regression | computation time | Hurt |
| Remove local expansion (ablation) | MBF-MaxCon · synthetic 8-dimensional robust linear regression | inliers found compared with the global optimum | Hurt |
| Increase the number of samples used to estimate influence | MBF-MaxCon influence estimation · synthetic 2D line fitting | influence estimation error | Helped |
| Use a sampling probability q smaller than 0.5 | MBF-MaxCon influence estimation · synthetic 2D line fitting | inlier-outlier influence separation | Helped |
| Use a sampling probability q other than 0.5 | MBF-MaxCon influence estimation · synthetic 2D line fitting | influence estimation error | Hurt |
Closest papers by meaning
- Maximum Consensus by Weighted Influences of Monotone Boolean Functions (CVPR 2022 · similarity 0.93)
- Guaranteed Outlier Removal With Mixed Integer Linear Programs (CVPR 2016 · similarity 0.88)
- Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy Data (ICML 2025 · similarity 0.83)
- Decoupled Optimisation for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.83)
- Smooth Min-Max Monotonic Networks (ICML 2024 · similarity 0.83)
- MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures (ICLR 2025 · similarity 0.83)
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.