Out-of-Distribution Detection in LiDAR Semantic Segmentation Using Epistemic Uncertainty from Hierarchical GMMs

• URL: http://arxiv.org/abs/2510.08631v1
• Date: Wed, 08 Oct 2025 14:40:17 GMT
• Title: Out-of-Distribution Detection in LiDAR Semantic Segmentation Using Epistemic Uncertainty from Hierarchical GMMs
• Authors: Hanieh Shojaei Miandashti, Claus Brenner,
• Abstract summary: Out-of-distribution (OOD) objects, instances not encountered during training, are essential to prevent the incorrect assignment of unknown objects to known classes.<n>We present an unsupervised OOD detection approach that employs epistemic uncertainty derived from hierarchical Bayesian modeling of Gaussian Mixture Model (GMM) parameters in the feature space of a deep neural network.<n>Our approach achieves an 18% improvement in AUROC, 22% increase in AUPRC, and 36% reduction in FPR95, compared to the predictive entropy approach used in prior works.
• Score: 3.333967282951669
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: In addition to accurate scene understanding through precise semantic segmentation of LiDAR point clouds, detecting out-of-distribution (OOD) objects, instances not encountered during training, is essential to prevent the incorrect assignment of unknown objects to known classes. While supervised OOD detection methods depend on auxiliary OOD datasets, unsupervised methods avoid this requirement but typically rely on predictive entropy, the entropy of the predictive distribution obtained by averaging over an ensemble or multiple posterior weight samples. However, these methods often conflate epistemic (model) and aleatoric (data) uncertainties, misclassifying ambiguous in distribution regions as OOD. To address this issue, we present an unsupervised OOD detection approach that employs epistemic uncertainty derived from hierarchical Bayesian modeling of Gaussian Mixture Model (GMM) parameters in the feature space of a deep neural network. Without requiring auxiliary data or additional training stages, our approach outperforms existing uncertainty-based methods on the SemanticKITTI dataset, achieving an 18\% improvement in AUROC, 22\% increase in AUPRC, and 36\% reduction in FPR95 (from 76\% to 40\%), compared to the predictive entropy approach used in prior works.

Related papers

• Distributional Uncertainty for Out-of-Distribution Detection [10.100430371132463]
  We propose a novel framework that jointly models distributional uncertainty and identifying OoD and misclassified regions using free energy.<n>By integrating our approach with the residual prediction branch (RPL) framework, the proposed method goes beyond post-hoc energy thresholding.<n>We validate the effectiveness of our method on challenging real-world benchmarks, including Fishyscapes, RoadAnomaly, and Segment-Me-If-You-Can.
  arXiv  Detail & Related papers  (2025-07-24T05:35:49Z)
• Out-of-Distribution Detection Methods Answer the Wrong Questions [42.28447793943742]
  Many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained on in-distribution data.<n>We find that uncertainty-based methods incorrectly conflate high uncertainty with being OOD, while feature-based methods incorrectly conflate far feature-space distance.<n>We show how these pathologies manifest as irreducible errors in OOD detection and identify common settings where these methods are ineffective.
  arXiv  Detail & Related papers  (2025-07-02T15:45:17Z)
• Uncertainty Estimation and Out-of-Distribution Detection for LiDAR Scene Semantic Segmentation [0.6144680854063939]
  Safe navigation in new environments requires autonomous vehicles and robots to accurately interpret their surroundings. We propose a method to distinguish in-distribution (ID) from out-of-distribution (OOD) samples. We quantify both epistemic and aleatoric uncertainties using the feature space of a single deterministic model.
  arXiv  Detail & Related papers  (2024-10-11T10:19:24Z)
• Can input reconstruction be used to directly estimate uncertainty of a regression U-Net model? -- Application to proton therapy dose prediction for head and neck cancer patients [0.8343441027226364]
  We present an alternative direct uncertainty estimation method and apply it for a regression U-Net architecture. For the proof-of-concept, our method is applied to proton therapy dose prediction in head and neck cancer patients.
  arXiv  Detail & Related papers  (2023-10-30T16:04:34Z)
• Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
  In safety-critical applications of machine learning, it is often desirable for a model to be conservative. We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
  arXiv  Detail & Related papers  (2023-06-08T07:05:36Z)
• Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty [58.144520501201995]
  Bi-Lipschitz regularization of neural network layers preserve relative distances between data instances in the feature spaces of each layer. With the use of an attentive set encoder, we propose to meta learn either diagonal or diagonal plus low-rank factors to efficiently construct task specific covariance matrices. We also propose an inference procedure which utilizes scaled energy to achieve a final predictive distribution.
  arXiv  Detail & Related papers  (2021-10-12T22:04:19Z)
• Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
  Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters. We show that our method improves both accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2021-09-27T01:09:08Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts [33.45069308137142]
  Posterior Network (PostNet) predicts an individual closed-form posterior distribution over predicted probabilites for any input sample. PostNet achieves state-of-the art results in OOD detection and in uncertainty calibration under dataset shifts.
  arXiv  Detail & Related papers  (2020-06-16T15:16:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.