Conformal Object Detection by Sequential Risk Control

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: andéol, Léo, Mossina, Luca, Mazoyer, Adrien, Gerchinovitz, Sébastien
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915588004118528
author andéol, Léo
Mossina, Luca
Mazoyer, Adrien
Gerchinovitz, Sébastien
author_facet andéol, Léo
Mossina, Luca
Mazoyer, Adrien
Gerchinovitz, Sébastien
contents Recent advances in object detectors have led to their adoption for industrial uses. However, their deployment in safety-critical applications is hindered by the inherent lack of reliability of neural networks and the complex structure of object detection models. To address these challenges, we turn to Conformal Prediction, a post-hoc predictive uncertainty quantification procedure with statistical guarantees that are valid for any dataset size, without requiring prior knowledge on the model or data distribution. Our contribution is manifold. First, we formally define the problem of Conformal Object Detection (COD). We introduce a novel method, Sequential Conformal Risk Control (SeqCRC), that extends the statistical guarantees of Conformal Risk Control to two sequential tasks with two parameters, as required in the COD setting. Then, we present old and new loss functions and prediction sets suited to applying SeqCRC to different cases and certification requirements. Finally, we present a conformal toolkit for replication and further exploration of our method. Using this toolkit, we perform extensive experiments that validate our approach and emphasize trade-offs and other practical consequences.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24038
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conformal Object Detection by Sequential Risk Control
andéol, Léo
Mossina, Luca
Mazoyer, Adrien
Gerchinovitz, Sébastien
Machine Learning
Computer Vision and Pattern Recognition
Recent advances in object detectors have led to their adoption for industrial uses. However, their deployment in safety-critical applications is hindered by the inherent lack of reliability of neural networks and the complex structure of object detection models. To address these challenges, we turn to Conformal Prediction, a post-hoc predictive uncertainty quantification procedure with statistical guarantees that are valid for any dataset size, without requiring prior knowledge on the model or data distribution. Our contribution is manifold. First, we formally define the problem of Conformal Object Detection (COD). We introduce a novel method, Sequential Conformal Risk Control (SeqCRC), that extends the statistical guarantees of Conformal Risk Control to two sequential tasks with two parameters, as required in the COD setting. Then, we present old and new loss functions and prediction sets suited to applying SeqCRC to different cases and certification requirements. Finally, we present a conformal toolkit for replication and further exploration of our method. Using this toolkit, we perform extensive experiments that validate our approach and emphasize trade-offs and other practical consequences.
title Conformal Object Detection by Sequential Risk Control
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.24038