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 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…

• AN
  Agence Nationale de la Recherche
• IA
  Intelligence Advanced Research Projects Activity
• JS
  Japan Society for the Promotion of Science
• AF
  Air Force Research Laboratory