NetVLAD: CNN architecture for weakly supervised place recognition
This work addresses the problem of quickly and accurately recognizing locations from photographs for applications like robotics and mapping, representing an incremental advancement in compact image representations.
The authors tackled large-scale visual place recognition by developing NetVLAD, a CNN architecture trainable end-to-end with a weakly supervised ranking loss, which significantly outperformed non-learnt representations and off-the-shelf CNN descriptors on place recognition benchmarks and improved over state-of-the-art compact image representations on retrieval benchmarks.
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 significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current state-of-the-art compact image representations on standard image retrieval benchmarks.