NetVLAD: CNN architecture for weakly supervised place recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

NetVLAD: CNN architecture for weakly supervised place recognition

Résumé

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.
Fichier principal
Vignette du fichier
cvpr16_place.pdf (4.5 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01242052 , version 1 (12-12-2015)
hal-01242052 , version 2 (10-03-2016)
hal-01242052 , version 3 (23-05-2016)

Identifiants

Citer

Relja Arandjelovic, 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. ⟨hal-01242052v3⟩
536 Consultations
1034 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More