Neighborhood Sampling Confidence Metric for Object Detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Neighborhood Sampling Confidence Metric for Object Detection

Résumé

Object detection using deep learning has recently gained significant attention due to its impressive results in a variety of applications, such as autonomous vehicles, surveillance, and image and video analysis. State-of-the-art models, such as YOLO, Faster-RCNN, and SSD, have achieved impressive performance on various benchmarks. However, it is crucial to ensure that the results produced by deep learning models are trustworthy, as they can have serious consequences, especially in an industrial context. In this paper, we introduce a novel confidence metric for object detection using neighborhood sampling.We evaluate our approach on MS-COCO and demonstrate that it significantly improves the trustworthiness of deep learning models for object detection. We also compare our approach against attribution-guided neighborhood sampling and show that such a heuristic does not yield better results.
Fichier principal
Vignette du fichier
Neighborhood_Sampling_Confidence_Metric_for_Object_Detection (1).pdf (433.68 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : Copyright (Tous droits réservés)

Dates et versions

hal-04264020 , version 1 (29-10-2023)

Identifiants

  • HAL Id : hal-04264020 , version 1

Citer

Christophe Gouguenheim, Ahmad Berjaoui. Neighborhood Sampling Confidence Metric for Object Detection. Workshop AITA AI Trustworthiness Assessment - AAAI Spring Symposium, Mar 2023, Palo Alto CA, United States. ⟨hal-04264020⟩
38 Consultations
27 Téléchargements

Partager

Gmail Facebook X LinkedIn More