Research map / Probabilistic and scientific modeling / Variational and generative sampling
Multi-Modal Mean-Fields via Cardinality-Based Clamping
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 |
|---|---|---|---|
| Replace MF with MMMF and use temporal consistency | MPI video segmentation · MPI video segmentation | Mean IOU: 44.9% -> 47.3% | Helped |
| Select the best MMMF mode | MMMF · MPI video segmentation | Mean IOU: 44.9% -> 53.2% | Helped |
| Use cardinality clamping on groups instead of clamping one variable (ablation) | MMMF on VOC 2012 validation · Pascal VOC 2012 validation | average intersection over union (IU): 2.5% | Helped |
| Clamp only the variable with the maximum entropy gap at each step (ablation) | MMMF on VOC 2012 validation · Pascal VOC 2012 validation | average intersection over union (IU) | No clear effect |
| Replace MMMF with adapted DivMBest (ablation) | Semantic segmentation on VOC 2012 validation · Pascal VOC 2012 validation | average intersection over union (IU): 1.5% | Hurt |
| Use temporal consistency to select among modes (ablation) | MMMF on MPI video segmentation · MPI video segmentation | IU score: around 2.4% | Helped |
Closest papers by meaning
- Principled Parallel Mean-Field Inference for Discrete Random Fields (CVPR 2016 · similarity 0.89)
- The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks (ICML 2020 · similarity 0.87)
- Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues (NeurIPS 2018 · similarity 0.87)
- Flexible mean field variational inference using mixtures of non-overlapping exponential families (NeurIPS 2020 · similarity 0.86)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.85)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.84)
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.