NetVLAD: CNN architecture for weakly supervised place recognition

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 four 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 create a new weakly supervised ranking loss, which enables end-to-end learning of the architecture's parameters from images depicting the same places over time downloaded from Google Street View Time Machine. Third, we develop an efficient training procedure which can be applied on very large-scale weakly labelled tasks. Finally, we show that the proposed architecture and training procedure significantly outperform non-learnt image representations and off-the-shelf CNN descriptors on challenging place recognition and image retrieval benchmarks.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2017, XX
Liste complète des métadonnées

Littérature citée [112 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01557234
Contributeur : Relja Arandjelović <>
Soumis le : jeudi 6 juillet 2017 - 01:06:39
Dernière modification le : mardi 27 mars 2018 - 16:06:22
Document(s) archivé(s) le : mardi 23 janvier 2018 - 21:48:36

Fichier

pami17_arandjelovic17a_netvlad...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01557234, version 1

Collections

Citation

Relja Arandjelović, Petr Gronat, Akihiko Torii, Tomas Pajdla, Josef Sivic. NetVLAD: CNN architecture for weakly supervised place recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2017, XX. 〈hal-01557234〉

Partager

Métriques

Consultations de la notice

375

Téléchargements de fichiers

162