Adaptive-Attentive Geolocalization from few queries: a hybrid approach [article]

Gabriele Moreno Berton, Valerio Paolicelli, Carlo Masone, Barbara Caputo
2020 arXiv   pre-print
We address the task of cross-domain visual place recognition, where the goal is to geolocalize a given query image against a labeled gallery, in the case where the query and the gallery belong to different visual domains. To achieve this, we focus on building a domain robust deep network by leveraging over an attention mechanism combined with few-shot unsupervised domain adaptation techniques, where we use a small number of unlabeled target domain images to learn about the target distribution.
more » ... ith our method, we are able to outperform the current state of the art while using two orders of magnitude less target domain images. Finally we propose a new large-scale dataset for cross-domain visual place recognition, called SVOX. Upon acceptance of the paper, code and dataset will be released.
arXiv:2010.06897v1 fatcat:nq5rjrc4qfcn3jixbxsa3r7wgu