Research map / Label-efficient and robust learning / Recognition and long-tail
Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them
Michael Hubbertz, Qi Han, Tobias Meisen
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 geographically disjoint split instead of original | MapTRv2 · nuScenes | mAP: 60.95 -> 24.96 (geo. [19]), 28.53 (geo. [37]) | Hurt |
| Use geographically disjoint split instead of original | MapTRv2 · Argoverse 2 (2 Hz) | mAP: 63.97 -> 49.53 (geo. [19]), 57.61 (geo. [37]) | Hurt |
| Use geometry-maximizing split instead of original | MapTRv2 · Argoverse 2 (2 Hz) | mAP: 63.97 -> 34.13 | Hurt |
| Higher geometric diversity of training set (geo. [37] vs [19]) | MapTRv2 · nuScenes | mAP: 24.96 -> 28.53; geomdiv(T) 80.6 km -> 90.2 km | Improved |
| MST-based sparsification with low threshold (0.1-1) (ablation) | MapTRv2 · nuScenes/Argoverse 2 validation | mAP | Improved |
| MST-based sparsification with high threshold (2-10) (ablation) | MapTRv2 · nuScenes/Argoverse 2 validation | mAP | Hurt |
| Random subsampling instead of MST sparsification (ablation) | MapTRv2 · nuScenes/Argoverse 2 original | mAP | Hurt |
| Architecture choice MapQR vs MapTRv2 | MapQR · nuScenes original | Oloc (%): 24.73 -> 57.07 | Hurt |
| Fréchet-based median M instead of mAP on small subsets | evaluation measure · nuScenes | metric validity | Improved |
Closest papers by meaning
- Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping (ICLR 2026 · similarity 0.87)
- Beyond Chamfer Distance: Granular Order-aware Evaluation Metric For Online Mapping (NeurIPS 2026 · similarity 0.86)
- Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It (CVPR 2024 · similarity 0.84)
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset (NeurIPS 2026 · similarity 0.84)
- MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert (AAAI 2025 · similarity 0.84)
- Producing and Leveraging Online Map Uncertainty in Trajectory Prediction (CVPR 2024 · similarity 0.84)
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.
