Unsupervised object discovery for instance recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2017

Unsupervised object discovery for instance recognition

Résumé

Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discrim-inative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The descriptors derived from the salient regions improve particular object retrieval, most noticeably in a large collections containing small objects.
Fichier principal
Vignette du fichier
1709.04725.pdf (3 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02370223 , version 1 (19-11-2019)

Identifiants

Citer

Oriane Siméoni, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum. Unsupervised object discovery for instance recognition. 2017. ⟨hal-02370223⟩
59 Consultations
93 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More