Invascal: Inverse-Vacuity Self-Calibration for Uncertainty-Aware LiDAR Range-View Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914619302346752 |
|---|---|
| author | Turacan, Kerim Reichert, Hannes Bolandut, Andrei Doll, Konrad |
| author_facet | Turacan, Kerim Reichert, Hannes Bolandut, Andrei Doll, Konrad |
| contents | LiDAR semantic segmentation is a core perception capability for autonomous vehicles and mobile robots. However, safe operation also depends on knowing when predictions are unreliable. Existing approaches typically rely on softmax confidence, which is often miscalibrated and overconfident, while stronger uncertainty estimates from Monte Carlo dropout or ensembles are often computationally expensive for real-time use. To this end, we introduce a novel, architecture-agnostic uncertainty-aware Adapter Head. It decomposes the prediction into a Preference Head for class ranking and a Strength Head that refines uncertainty assessment, thereby enabling a principled construction of evidential Dirichlet representations. Building on this design, we propose our inverse-vacuity self-calibration objective (Invascal), which directly supervises the strength signal to produce reliable and well-calibrated uncertainty estimates while preventing runaway evidence growth. We evaluate our framework across multiple LiDAR datasets and backbone architectures. We compare against deterministic training, Monte Carlo dropout and ensembles, and prior evidential methods. Our approach consistently improves uncertainty calibration over traditional deterministic methods with minimal computational overhead. At the same time, it preserves competitive segmentation accuracy, where prior evidential methods often suffer performance degradation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00069 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Invascal: Inverse-Vacuity Self-Calibration for Uncertainty-Aware LiDAR Range-View Semantic Segmentation Turacan, Kerim Reichert, Hannes Bolandut, Andrei Doll, Konrad Robotics Image and Video Processing LiDAR semantic segmentation is a core perception capability for autonomous vehicles and mobile robots. However, safe operation also depends on knowing when predictions are unreliable. Existing approaches typically rely on softmax confidence, which is often miscalibrated and overconfident, while stronger uncertainty estimates from Monte Carlo dropout or ensembles are often computationally expensive for real-time use. To this end, we introduce a novel, architecture-agnostic uncertainty-aware Adapter Head. It decomposes the prediction into a Preference Head for class ranking and a Strength Head that refines uncertainty assessment, thereby enabling a principled construction of evidential Dirichlet representations. Building on this design, we propose our inverse-vacuity self-calibration objective (Invascal), which directly supervises the strength signal to produce reliable and well-calibrated uncertainty estimates while preventing runaway evidence growth. We evaluate our framework across multiple LiDAR datasets and backbone architectures. We compare against deterministic training, Monte Carlo dropout and ensembles, and prior evidential methods. Our approach consistently improves uncertainty calibration over traditional deterministic methods with minimal computational overhead. At the same time, it preserves competitive segmentation accuracy, where prior evidential methods often suffer performance degradation. |
| title | Invascal: Inverse-Vacuity Self-Calibration for Uncertainty-Aware LiDAR Range-View Semantic Segmentation |
| topic | Robotics Image and Video Processing |
| url | https://arxiv.org/abs/2606.00069 |