Learning a Complete Image Indexing Pipeline - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Learning a Complete Image Indexing Pipeline

Résumé

To work at scale, a complete image indexing system comprises two components: An inverted file index to restrict the actual search to only a subset that should contain most of the items relevant to the query; An approximate distance computation mechanism to rapidly scan these lists. While supervised deep learning has recently enabled improvements to the latter, the former continues to be based on unsupervised clustering in the literature. In this work, we propose a first system that learns both components within a unifying neural framework of structured binary encoding.
Fichier principal
Vignette du fichier
1712.04480.pdf (559.97 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04517974 , version 1 (22-03-2024)

Licence

Paternité

Identifiants

Citer

Himalaya Jain, Joaquin Zepeda, Patrick Perez, Rémi Gribonval. Learning a Complete Image Indexing Pipeline. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2018, Salt Lake City, France. pp.4933-4941, ⟨10.1109/CVPR.2018.00518⟩. ⟨hal-04517974⟩
2 Consultations
1 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More