Research map / Probabilistic and scientific modeling / Molecules and proteins
Inference in Higher Order MRF-MAP Problems With Small and Large Cliques
Read the paperCheck 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 the hybrid flow-based and polyhedral inference framework instead of SOSMNP | MRF-MAP inference with mixed small and large cliques · Synthetic count-based cliques, 50×50 image; small clique 2×1 | runtime (seconds): 274.27 -> 11.54 | Helped |
| Use the hybrid flow-based and polyhedral inference framework instead of SOSMNP | MRF-MAP inference with mixed small and large cliques · Synthetic edge-based cliques, 50×50 image; small clique 2×1 | runtime (seconds): 250.67 -> 17.41 | Helped |
| Use the hybrid flow-based and polyhedral inference framework instead of SOSMNP | MRF-MAP inference with mixed small and large cliques · Synthetic count-based cliques; 2500 pixels, 40 big cliques | runtime (seconds): 295.73 -> 31.28 | Helped |
| Use the hybrid flow-based and polyhedral inference framework instead of SOSMNP | MRF-MAP inference with mixed small and large cliques · Synthetic count-based cliques; 6400 pixels, 50 big cliques | runtime (seconds): 349.71 -> 32.50 | Helped |
| Increase the small-clique window size from 2×2 to 4×3 | HybridMNGC · Synthetic count-based cliques, 50×50 image; 25 big cliques | runtime (seconds): 9.42 -> 58.48 | Hurt |
| Increase the number of big cliques from 40 to 120 | HybridMNGC · Synthetic count-based cliques; 2500 pixels | runtime (seconds): 31.28 -> 94.66 | Hurt |
| Increase image size from 2500 to 6400 pixels | HybridMNGC · Synthetic count-based cliques; 50 big cliques | runtime (seconds): 34.69 -> 32.50 | Mixed |
| Combine small pairwise cliques with large region-level cliques | HybridMNGC object segmentation · Pascal VOC object segmentation with Gaussian noise | segmentation quality | Helped |
Closest papers by meaning
- Min Norm Point Algorithm for Higher Order MRF-MAP Inference (CVPR 2016 · similarity 0.93)
- Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions (CVPR 2023 · similarity 0.88)
- Efficient semidefinite-programming-based inference for binary and multi-class MRFs (NeurIPS 2020 · similarity 0.88)
- MFP: Making Full Use of Probability Maps for Interactive Image Segmentation (CVPR 2024 · similarity 0.83)
- Memory-Scalable and Simplified Functional Map Learning (CVPR 2024 · similarity 0.83)
- unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning (ICML 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.