Research map / Detection and segmentation / 3D detection and driving
MapUQ: Map with Uncertainty Quantification for Robust BEV Vectorized Construction
Shaoyuan Mo, Qi Ma, leng rui, Bohan Li, Ke Wang
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 |
|---|---|---|---|
| add Negative Sample Classifier (Unc-cls) (ablation) | MapTRv2 baseline · nuScenes val (24 epochs) | mean AP: 61.5 -> 62.1 | Improved |
| add Progressive ROI Scale Adapter (Unc-reg) (ablation) | MapTRv2 baseline · nuScenes val (24 epochs) | mean AP: 61.5 -> 62.0 | Improved |
| add Multi-task Semantic Uncertainty Head (Unc-seg) (ablation) | MapTRv2 baseline · nuScenes val (24 epochs) | mean AP: 61.5 -> 61.8 | Improved |
| combine Unc-cls and Unc-seg (ablation) | MapTRv2 baseline · nuScenes val (24 epochs) | mean AP: 61.5 -> 62.6 | Improved |
| combine all three UQ modules (ablation) | MapTRv2 baseline · nuScenes val (24 epochs) | mean AP: 61.5 -> 63.0 | Improved |
| add all three UQ modules at 110 epochs | MapTRv2 · nuScenes val (110 epochs) | mean AP: 68.7 -> 69.7 | Improved |
| add all three UQ modules (ablation) | MapTRv2 · nuScenes val (24 epochs) | pedestrian crossing AP: 59.8 -> 62.3 | Improved |
| add uncertainty modules | MapTRv2 · nuScenes inference speed | FPS: 14.1 -> 13.9 | No clear effect |
| add uncertainty modules | MapTRv2 · nuScenes calibration | ECE: 13.1 -> 9.3 | Improved |
| add uncertainty modules | MapTRv2 · nuScenes calibration | NLL: 2.89 -> 1.96 | Improved |
| add uncertainty modules | MapTRv2 · nuScenes failure detection | false positive rate: 15.7 -> 8.4 | Improved |
| add uncertainty modules | MapTRv2 · nuScenes failure detection | AUROC: 87.6 -> 91.8 | Improved |
Closest papers by meaning
- LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving (ICLR 2024 · similarity 0.88)
- Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection (AAAI 2024 · similarity 0.87)
- VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization (NeurIPS 2024 · similarity 0.87)
- Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction (CVPR 2025 · similarity 0.87)
- MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert (AAAI 2025 · similarity 0.86)
- Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function (ICLR 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.
