Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Efficient Uncertainty Estimation for Semantic Segmentation in Videos
Po-Yu Huang, Wan-Ting Hsu, Chun-Yueh Chiu, Ting-Fan Wu, Min Sun
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 |
|---|---|---|---|
| replace N=50 MC dropout sampling with temporal aggregation (TA-MC) | SegNet · CamVid | mean IoU: 63.7 -> 62.1 | Hurt |
| replace N=50 MC dropout sampling with temporal aggregation (TA-MC) | Tiramisu · CamVid | inference time (s): 11.72 -> 0.37 | Improved |
| reduce MC dropout samples from 50 to 5 | Tiramisu MC · CamVid | mean IoU: 64.0 -> 62.4 | Hurt |
| add region-based multiplying factor (RTA) to TA-MC (ablation) | SegNet · CamVid | mean IoU: 62.1 -> 62.5 | Improved |
| add region-based multiplying factor (RTA) to TA-MC (ablation) | Tiramisu · CamVid | mean IoU: 62.3 -> 62.4 | No clear effect |
| add region-based multiplying factor (RTA) to TA-MC (ablation) | SegNet · CamVid | Kendall tau (Entropy): 0.626 -> 0.662 | Improved |
| add region-based multiplying factor (RTA) to TA-MC (ablation) | SegNet · CamVid | Kendall tau (Variation Ratio): 0.631 -> 0.674 | Improved |
| add region-based multiplying factor (RTA) to TA-MC (ablation) | SegNet · CamVid | Kendall tau (Mean STD): 0.540 -> 0.627 | Improved |
| add region-based multiplying factor (RTA) to TA-MC (ablation) | Tiramisu · CamVid | Kendall tau (Entropy): 0.660 -> 0.664 | No clear effect |
| add region-based multiplying factor (RTA) to TA-MC (ablation) | Tiramisu · CamVid | Kendall tau (BALD): 0.626 -> 0.612 | Hurt |
| add region-based multiplying factor (RTA) to TA-MC (ablation) | SegNet · CamVid | Ranking IoU 30% (Variation Ratio): 63.8 -> 65.2 | Improved |
| use RTA-MC instead of MC dropout for uncertainty ranking | SegNet · CamVid | Kendall tau (Entropy): 0.647 -> 0.662 | Improved |
Closest papers by meaning
- Latent Discriminant Deterministic Uncertainty (ECCV 2022 · similarity 0.86)
- UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model (ICML 2025 · similarity 0.85)
- ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation (ICLR 2024 · similarity 0.85)
- Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function (ICLR 2025 · similarity 0.85)
- Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perception (CVPR 2025 · similarity 0.84)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · 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.
