Verification for Object Detection – IBP IoU - ANITI - Artificial and Natural Intelligence Toulouse Institute
Pré-Publication, Document De Travail Année : 2024

Verification for Object Detection – IBP IoU

Mélanie Ducoffe
Ryma Boumazouza
  • Fonction : Auteur
Christophe Gabreau
  • Fonction : Auteur
  • PersonId : 1102007
Audrey Galametz
  • Fonction : Auteur

Résumé

We introduce a novel Interval Bound Propagation (IBP) approach for the formal verification of object detection models, specifically targeting the Intersection over Union (IoU) metric. The approach has been implemented in an open source code, named IBP IoU, compatible with popular abstract interpretation based verification tools. The resulting verifier is evaluated on landing approach runway detection and handwritten digit recognition case studies. Comparisons against a baseline (Vanilla IBP IoU) highlight the superior performance of IBP IoU in ensuring accuracy and stability, contributing to more secure and robust machine learning applications.
Fichier principal
Vignette du fichier
main.pdf (6.71 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04405518 , version 1 (26-01-2024)

Identifiants

  • HAL Id : hal-04405518 , version 1

Citer

Noémie Cohen, Mélanie Ducoffe, Ryma Boumazouza, Christophe Gabreau, Claire Pagetti, et al.. Verification for Object Detection – IBP IoU. 2024. ⟨hal-04405518⟩
147 Consultations
102 Téléchargements

Partager

More