We propose a data structure obtained by hierarchically averaging bag-of-word descriptors during a sequence of views that achieves average speedups in large-scale loop closure applications ranging from 4 to 20 times on benchmark datasets. Although simple, the method works as well as sophisticated agglomerative schemes at a fraction of the cost with minimal loss of performance.
Cite
@article{arxiv.1511.06489,
title = {A Simple Hierarchical Pooling Data Structure for Loop Closure},
author = {Xiaohan Fei and Konstantine Tsotsos and Stefano Soatto},
journal= {arXiv preprint arXiv:1511.06489},
year = {2018}
}