NetVLAD: CNN Architecture for Weakly Supervised Place Recognition

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...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on pattern analysis and machine intelligence 2018-06, Vol.40 (6), p.1437-1451
Main Authors:	Arandjelovic, Relja, Gronat, Petr, Torii, Akihiko, Pajdla, Tomas, Sivic, Josef
Format:	Article
Language:	eng
Subjects:	Artificial neural networks Back propagation Computer architecture computer vision Electronic mail feature representation Image management Image recognition Image representation Image retrieval image/video retrieval Neural nets Neural networks Object recognition Representations Retrieval Training vision and scene understanding
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
ISSN:	0162-8828 1939-3539