arXiv subjects

Bruno Viti

Publications and source records attributed to Bruno Viti.

4 recordsLinked to original sources

arXiv2026

Finite-sample Calibration Guarantees for Binary Segmentation

Machine learning based segmentation models are frequently miscalibrated, producing for each pixel a label prediction whose associated confidence does not accurately reflect the true underlying probability. This limitation is particularly critical in high-stakes applications such as medical image segmentation. Although several calibration methods have been proposed, only a small subset of them provides theoretical guarantees on the calibration error, i.e., they do not typically ensure that, with high probability, the model exhibits a low calibration error. In this work, we develop a post-hoc calibration method for which formal calibration guarantees can be established. To achieve this, we derive from standard concentration inequalities an improved theoretical bound that explicitly accounts for the spatial dependence inherent in binary segmentation outputs. We empirically demonstrate that the proposed calibrator satisfies the derived guarantee and outperforms existing post-hoc calibration approaches.

cs.CV↗

arXiv2026

Robust lane-change intention anticipation under uncertainty based on a recursive Bayesian filtering approach

In this paper we discuss and analyze a method for lane-change intention anticipation of drivers on highways based on kinematic features and surrounding observations. The approach makes use of a recursive Bayesian filtering strategy, which can be interpreted as a hidden Markov model. We present two models for the likelihood term and show how they can handle missing observations. An additional focus of the work lies on calibrating the obtained probabilities in order to obtain reliable predictions. The introduced approach is evaluated in practice on the highD dataset and compared to several other baseline methods. Particular emphasize is put on evaluating the robustness and temporal consistency as well as calibration of the developed algorithm. Extensive numerical experiments allow for a careful performance assessment and detailed discussion of advantages and limitations of the different methodologies.

eess.SY↗

arXiv2026

CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition

Most machine learning-based image segmentation models produce pixel-wise confidence scores that represent the model's predicted probability for each class label at every pixel. While this information can be particularly valuable in high-stakes domains such as medical imaging, these scores are heuristic in nature and do not constitute rigorous quantitative uncertainty estimates. Conformal prediction (CP) provides a principled framework for transforming heuristic confidence scores into statistically valid uncertainty estimates. However, applying CP directly to image segmentation ignores the spatial correlations between pixels, a fundamental characteristic of image data. This can result in overly conservative and less interpretable uncertainty estimates. To address this, we propose CONSIGN (Conformal Segmentation Informed by Spatial Groupings via Decomposition), a CP-based method that incorporates spatial correlations to improve uncertainty quantification in image segmentation. Our method generates meaningful prediction sets that come with user-specified, high-probability error guarantees. It is compatible with any pre-trained segmentation model capable of generating multiple sample outputs. We evaluate CONSIGN against two CP baselines across three medical imaging datasets and two COCO dataset subsets, using three different pre-trained segmentation models. Results demonstrate that accounting for spatial structure significantly improves performance across multiple metrics and enhances the quality of uncertainty estimates.

cs.CV↗

arXiv2024

Gaussian Process Emulators for Few-Shot Segmentation in Cardiac MRI

Segmentation of cardiac magnetic resonance images (MRI) is crucial for the analysis and assessment of cardiac function, helping to diagnose and treat various cardiovascular diseases. Most recent techniques rely on deep learning and usually require an extensive amount of labeled data. To overcome this problem, few-shot learning has the capability of reducing data dependency on labeled data. In this work, we introduce a new method that merges few-shot learning with a U-Net architecture and Gaussian Process Emulators (GPEs), enhancing data integration from a support set for improved performance. GPEs are trained to learn the relation between the support images and the corresponding masks in latent space, facilitating the segmentation of unseen query images given only a small labeled support set at inference. We test our model with the M&Ms-2 public dataset to assess its ability to segment the heart in cardiac magnetic resonance imaging from different orientations, and compare it with state-of-the-art unsupervised and few-shot methods. Our architecture shows higher DICE coefficients compared to these methods, especially in the more challenging setups where the size of the support set is considerably small.

cs.CV↗