Metraipolis › archive › dc_cff3aa3de0c3
Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds — arXiv:2611.05569
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05569
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:22:32.735Z
- SHA-256 of the archived text
ac4e66af1cc7a6021d2c98f271ae8116cf18d3a6d44a1345dd0df85891ff3098- Stable URL of this page
https://metraipolis.com/documento/dc_cff3aa3de0c3
How to cite
Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds — arXiv:2611.05569 — arXiv (en), https://arxiv.org/abs/2611.05569 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cff3aa3de0c3 (Metraipolis archive dc_cff3aa3de0c3, sha256 ac4e66af1cc7a6021d2c98f271ae8116cf18d3a6d44a1345dd0df85891ff3098)
BibTeX
@misc{dccff3aa3de0c3,
title = {Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds — arXiv:2611.05569},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05569},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cff3aa3de0c3; sha256 ac4e66af1cc7a6021d2c98f271ae8116cf18d3a6d44a1345dd0df85891ff3098},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05569. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Point cloud segmentation is a fundamental task in 3D data analysis, with applications across robotics, augmented and virtual reality, and remote sensing. However, the inherent sparsity, noise, and unordered nature of point clouds introduce significant challenges, particularly in achieving reliable classification. While the state-of-the-art rely on training models for explicit modeling of uncertainty, there is a gap in exploring different roles that estimated uncertainty using generative approaches can play. This work investigates the impact of deterministic uncertainty in point cloud segmentation by explicitly modeling epistemic uncertainty and using it in different roles, namely, as a feature and in loss function. We evaluate a baseline artificial neural network (ANN) and two uncertainty-aware variants (uncertainty as an additional input feature and as a per-sample confidence weight in the training loss) on four large-scale LiDAR benchmarks spanning airborne and mobile acquisition, namely ISPRS Vaihingen, AHN3, Paris-Lille-3D, and Toronto-3D, together with PointNet++ and RandLA-Net references and their uncertainty-augmented counterparts under canonical spatially disjoint train and test splits. Under this protocol, uncertainty-aware modeling improves mean Intersection over Union, recovers minority classes that the baseline ANN never predicts at all, and in half of the configurations improves the alignment between prediction error and estimated uncertainty as measured by Patch Accuracy versus Patch Uncertainty. Our findings indicate that uncertainty can play multiple roles in the segmentation pipeline rather than as a device for improving accuracy alone. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.05569 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:15:49.030Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).