Object Detection With Probabilistic Guarantees - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Object Detection With Probabilistic Guarantees

Abstract

Providing reliable uncertainty quantification for complex visual tasks such as object detection is of utmost importance for safety-critical applications such as autonomous driving, tumor detection, etc. Conformal prediction methods offer simple yet practical means to build uncertainty estimations that come with probabilistic guarantees. In this paper we apply such methods to the task of object localization and illustrate our analysis on a pedestrian detection use-case. We highlight both theoretical and practical implications of our analysis.
Fichier principal
Vignette du fichier
waise-conformalobjectdetection-submitted.pdf (790.2 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03769683 , version 1 (05-09-2022)

Identifiers

  • HAL Id : hal-03769683 , version 1

Cite

Florence de Grancey, Jean-Luc Adam, Lucian Alecu, Sébastien Gerchinovitz, Franck Mamalet, et al.. Object Detection With Probabilistic Guarantees: a Conformal Prediction Approach. Fifth International Workshop on Artificial Intelligence Safety Engineering (WAISE 2022), Sep 2022, München, Germany. ⟨hal-03769683⟩
573 View
403 Download

Share

Gmail Mastodon Facebook X LinkedIn More