Research map / Detection and segmentation / Open-set and few-shot detection
Reliability in Semantic Segmentation: Are We on the Right Track?
Pau de Jorge, Riccardo Volpi, Philip H.S. Torr, Grégory Rogez
Read the paperCheck your idea against 137,217 papers
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 Local Temperature Scaling (LTS) instead of temperature scaling (TS) | Segmentation models calibrated on Cityscapes · ACDC | ECE | Improved |
| Calibrate with LTS | Segmentation models · ACDC | PRR | Improved |
| Calibrate with clustering TS or LTS | Segmentation models · IDD and ACDC | AUROC | Improved |
| Use clustering calibration with Cityscapes-only examples | Segmentation models · IDD and ACDC | ECE | No clear effect |
| Add naive data augmentation to the Cityscapes calibration set (ablation) | Clustering TS and LTS · OOD calibration | ECE | No clear effect |
| Use all datasets for calibration rather than Cityscapes only (ablation) | Clustering TS · IDD and ACDC | ECE | Improved |
| Increase the number of clustering groups (ablation) | Adaptive clustering TS · Calibration set and OOD test datasets | ECE | Mixed |
| Use per-class instead of per-image clustering (ablation) | Adaptive clustering calibration · Segmentation calibration | ECE | No clear effect |
| Use only image input instead of only logits as LTS input (ablation) | LTS · ACDC | ECE | Improved |
| Use only logits rather than both image and logits as LTS input (ablation) | LTS · Cityscapes (CS) | ECE | Improved |
| Use max probability rather than negative entropy as confidence score (ablation) | Misclassification and OOD detection · Cityscapes, IDD, and ACDC | Detection performance | No clear effect |
| Increase sampled calibration pixels to more than 10k per image (ablation) | Calibration metric estimation · Semantic segmentation calibration | ECE stability | No clear effect |
Closest papers by meaning
- ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation (ICLR 2024 · similarity 0.92)
- Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off (ECCV 2024 · similarity 0.91)
- UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model (ICML 2025 · similarity 0.88)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · similarity 0.88)
- Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation (NeurIPS 2025 · similarity 0.87)
- Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation (NeurIPS 2025 · similarity 0.87)
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.
