Research map / Detection and segmentation / CNN features
On Calibrating Semantic Segmentation Models: Analyses and an Algorithm
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 |
|---|---|---|---|
| Apply selective scaling, separating correct and incorrect predictions and smoothing misprediction logits | Segmenter-L · ADE20K | ECE: 0.087 -> 0.069 | Helped |
| Apply selective scaling, separating correct and incorrect predictions and smoothing misprediction logits | Segmenter-L · COCO-164K | ECE: 0.152 -> 0.109 | Helped |
| Apply selective scaling, separating correct and incorrect predictions and smoothing misprediction logits | Segmenter-L · BDD100K | ECE: 0.055 -> 0.031 | Helped |
| Apply selective scaling | Segmenter-L · ADE20K → COCO-164K | ECE: 0.395 -> 0.259 | Helped |
| Apply selective scaling | Segmenter-L · BDD100K → CityScapes | ECE: 0.062 -> 0.048 | Helped |
| Apply selective scaling | Segmenter-B · DAVIS-train → DAVIS-test | ECE: 0.080 -> 0.049 | Helped |
| Apply selective scaling | Segmenter-B · SN-7-SP-train → SN-7-SP-test | ECE: 0.766 -> 0.687 | Helped |
| Apply selective scaling | Segmenter-B · SN-7-TS-train → SN-7-TS-test | ECE: 0.769 -> 0.624 | Helped |
| Apply selective scaling | Segmenter-B · BraTS-train → BraTS-test | ECE: 0.154 -> 0.124 | Helped |
| Apply selective scaling | Segmenter-L · SYNTHIA → CityScapes | ECE: 0.254 -> 0.203 | Helped |
| Increase misprediction-detection accuracy of the selector (ablation) | Selective scaling · segmentation calibration (figure experiment) | ECE | Helped |
| Combine selective scaling with existing calibrators (ablation) | Selective scaling and existing calibrators · segmentation calibration (figure experiment) | ECE | Helped |
Closest papers by meaning
- ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation (ICLR 2024 · similarity 0.88)
- SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.87)
- MaSS13K: A Matting-level Semantic Segmentation Benchmark (CVPR 2025 · similarity 0.86)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.86)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · similarity 0.86)
- Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity (CVPR 2025 · similarity 0.86)
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.