Semantic bottleneck for computer vision tasks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Semantic bottleneck for computer vision tasks

Résumé

This paper introduces a novel method for the representation of images that is semantic by nature, addressing the question of computation intelligibility in computer vision tasks. More specifically, our proposition is to introduce what we call a semantic bottleneck in the processing pipeline, which is a crossing point in which the representation of the image is entirely expressed with natural language , while retaining the efficiency of numerical representations. We show that our approach is able to generate semantic representations that give state-of-the-art results on semantic content-based image retrieval and also perform very well on image classification tasks. Intelligibility is evaluated through user centered experiments for failure detection.
Fichier principal
Vignette du fichier
main.pdf (5.62 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01909665 , version 1 (05-11-2018)

Identifiants

Citer

Maxime Bucher, Stéphane Herbin, Frédéric Jurie. Semantic bottleneck for computer vision tasks. Asian Conference on Computer Vision (ACCV), Dec 2018, Perth, Australia. ⟨hal-01909665⟩
226 Consultations
138 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More