NetVLAD: CNN architecture for weakly supervised place recognition

Relja Arandjelović 1, 2 Petr Gronat 1, 2 Akihiko Torii 3 Tomas Pajdla 4 Josef Sivic 1, 2
1 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : We tackle the problem of large scale visual place recognition , where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the " Vector of Locally Aggregated Descriptors " image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture obtains a large improvement in performance over non-learnt image representations as well as significantly outperforms off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and outperforms current state-of-the-art compact image representations on standard image retrieval benchmarks.
Type de document :
Communication dans un congrès
CVPR 2016 - 29th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2016, Las Vegas, United States. Proceedings IEEE Conference on Computer Vision & Pattern Recognition
Liste complète des métadonnées

Littérature citée [88 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01242052
Contributeur : Relja Arandjelović <>
Soumis le : lundi 23 mai 2016 - 17:38:16
Dernière modification le : mardi 24 avril 2018 - 17:20:13

Fichier

cvpr16_place.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01242052, version 3
  • ARXIV : 1511.07247

Collections

Citation

Relja Arandjelović, Petr Gronat, Akihiko Torii, Tomas Pajdla, Josef Sivic. NetVLAD: CNN architecture for weakly supervised place recognition. CVPR 2016 - 29th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2016, Las Vegas, United States. Proceedings IEEE Conference on Computer Vision & Pattern Recognition. 〈hal-01242052v3〉

Partager

Métriques

Consultations de la notice

398

Téléchargements de fichiers

477