Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Structuring Uncertainty for Fine-Grained Sampling in Stochastic Segmentation Networks
Frank Nussbaum, Jakob Gawlikowski, Julia Niebling
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 |
|---|---|---|---|
| use flow-probability (FP) rotations instead of classic rotations | SSN factors · LIDC | row sparsity: 48.2 -> 82.8 | Improved |
| use FP rotations instead of classic rotations | SSN factors · SEN12MS | row sparsity: 52.7 -> 74.1 | Improved |
| use FP rotations instead of classic rotations | SSN factors · CamVid | row sparsity: 30.4 -> 50.1 | Improved |
| apply classic rotation (Varimax) to unrotated factors | SSN factors · LIDC | row sparsity: 29.3 -> 48.2 | Improved |
| use FP-Quartimax instead of FP-Varimax | SSN factors · SEN12MS | row sparsity: 74.1 -> 77.7 | Improved |
| use FP-Quartimax instead of FP-Varimax | SSN factors · LIDC | row sparsity: 82.8 -> 82.7 | No clear effect |
| use FP rotations instead of classic rotations | SSN factors · CamVid | number of relevant factors | Improved |
| use classic rotations instead of unrotated factors | SSN factors · LIDC, SEN12MS, CamVid | number of relevant factors | No clear effect |
| use FP rotations instead of classic rotations | SSN factors · LIDC, SEN12MS, CamVid | AUC of factor separation | Improved |
| use classic rotations instead of unrotated factors | SSN factors · LIDC, SEN12MS, CamVid | AUC of factor separation | Improved |
Closest papers by meaning
- Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty (NeurIPS 2020 · similarity 0.91)
- Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance (CVPR 2026 · similarity 0.89)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · similarity 0.88)
- ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation (ICLR 2024 · similarity 0.88)
- UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype Discovery (CVPR 2025 · similarity 0.85)
- Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function (ICLR 2025 · 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.
