Semantic bottleneck for computer vision tasks - Archive ouverte HAL Access content directly
Conference Papers Year :

Semantic bottleneck for computer vision tasks

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Identifiers

Cite

Maxime Bucher, Stéphane Herbin, Frédéric Jurie. Semantic bottleneck for computer vision tasks. Asian Conference on Computer Vision (ACCV), Dec 2018, Perth, Australia. ⟨hal-01909665⟩
192 View
132 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More