Sequential Conformal Risk Control for Safe Railway Signaling Detection

Léo Andéol, Thomas Masséna
Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 266:771-774, 2025.

Abstract

As machine learning becomes a more common tool in industry, its needs for certification increase. Conformal Prediction, a framework for construction of prediction sets with tight coverage guarantees at any desired error rate, is an ideal tool for this purpose. However, adapting conformal methods to complex computer vision pipelines and providing appropriate guarantees is still a challenging task. Indeed, conformal approaches to object detection are often restricted to subtasks: often localization, and sometimes classification. In this study, we apply the comprehensive framework from (Andeol, 2025) to the safety-critical task of railway signaling detection.

Cite this Paper

BibTeX
@InProceedings{pmlr-v266-andeol25a, title = {Sequential Conformal Risk Control for Safe Railway Signaling Detection}, author = {And\'{e}ol, L\'{e}o and Mass\'{e}na, Thomas}, booktitle = {Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {771--774}, year = {2025}, editor = {Nguyen, Khuong An and Luo, Zhiyuan and Papadopoulos, Harris and Löfström, Tuwe and Carlsson, Lars and Boström, Henrik}, volume = {266}, series = {Proceedings of Machine Learning Research}, month = {10--12 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v266/main/assets/andeol25a/andeol25a.pdf}, url = {https://proceedings.mlr.press/v266/andeol25a.html}, abstract = {As machine learning becomes a more common tool in industry, its needs for certification increase. Conformal Prediction, a framework for construction of prediction sets with tight coverage guarantees at any desired error rate, is an ideal tool for this purpose. However, adapting conformal methods to complex computer vision pipelines and providing appropriate guarantees is still a challenging task. Indeed, conformal approaches to object detection are often restricted to subtasks: often localization, and sometimes classification. In this study, we apply the comprehensive framework from (Andeol, 2025) to the safety-critical task of railway signaling detection.} }
Endnote
%0 Conference Paper %T Sequential Conformal Risk Control for Safe Railway Signaling Detection %A Léo Andéol %A Thomas Masséna %B Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2025 %E Khuong An Nguyen %E Zhiyuan Luo %E Harris Papadopoulos %E Tuwe Löfström %E Lars Carlsson %E Henrik Boström %F pmlr-v266-andeol25a %I PMLR %P 771--774 %U https://proceedings.mlr.press/v266/andeol25a.html %V 266 %X As machine learning becomes a more common tool in industry, its needs for certification increase. Conformal Prediction, a framework for construction of prediction sets with tight coverage guarantees at any desired error rate, is an ideal tool for this purpose. However, adapting conformal methods to complex computer vision pipelines and providing appropriate guarantees is still a challenging task. Indeed, conformal approaches to object detection are often restricted to subtasks: often localization, and sometimes classification. In this study, we apply the comprehensive framework from (Andeol, 2025) to the safety-critical task of railway signaling detection.
APA
Andéol, L. & Masséna, T.. (2025). Sequential Conformal Risk Control for Safe Railway Signaling Detection. Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 266:771-774 Available from https://proceedings.mlr.press/v266/andeol25a.html.

Related Material