Uncertainty evaluation of segmentation models for Earth observation

2025/10/22 by Mélanie Rey, Rey, Melanie, Andriy Mnih +7 · 1 citation
Computer Science · Engineering · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Remote-Sensing Image Classification

paper · pdf · doi:10.48550/arxiv.2510.19586

openalex publication_date 2025/10/22 · openalex created_date 2025/10/24 · openalex updated_date 2026/07/28

Abstract

This paper investigates methods for estimating uncertainty in semantic segmentation predictions derived from satellite imagery. Estimating uncertainty for segmentation presents unique challenges compared to standard image classification, requiring scalable methods producing per-pixel estimates. While most research on this topic has focused on scene understanding or medical imaging, this work benchmarks existing methods specifically for remote sensing and Earth observation applications. Our evaluation focuses on the practical utility of uncertainty measures, testing their ability to identify prediction errors and noise-corrupted input image regions. Experiments are conducted on two remote sensing datasets, PASTIS and ForTy, selected for their differences in scale, geographic coverage, and label confidence. We perform an extensive evaluation featuring several models, such as Stochastic Segmentation Networks and ensembles, in combination with a number of neural architectures and uncertainty metrics. We make a number of practical recommendations based on our findings.

Citations

• Not Every Tree Is a Forest: Benchmarking Forest Types from Satellite Remote Sensing
• Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation
• Regression coefficient estimation from remote sensing maps
• ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
• Uncertainty quantification for probabilistic machine learning in earth observation using conformal prediction
• Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation
• ViTs for SITS: Vision Transformers for Satellite Image Time Series
• On Calibrating Semantic Segmentation Models: Analyses and An Algorithm
• A high-resolution canopy height model of the Earth
• Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation
• Calibrating Deep Neural Networks using Focal Loss
• Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
• Verified Uncertainty Calibration
• Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Measuring Calibration in Deep Learning
• Uncertainty Gated Network for Land Cover Segmentation
• On Calibration of Modern Neural Networks
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Cited by

• SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation

Related

• How Certain are Uncertainty Estimates? Three Novel Earth Observation Datasets for Benchmarking Uncertainty Quantification in Machine Learning
• On the Generalization of Representation Uncertainty in Earth Observation
• Improving EO Foundation Models with Confidence Assessment for enhanced Semantic segmentation
• Uncertainty Measures and Prediction Quality Rating for the Semantic\n Segmentation of Nested Multi Resolution Street Scene Images
• Uncertainty Gated Network for Land Cover Segmentation