Adaptive-Attentive Geolocalization from few queries: a hybrid approach
This addresses geolocalization challenges for applications like robotics or autonomous systems where visual domains differ, representing an incremental improvement with a novel hybrid approach.
The paper tackles cross-domain visual place recognition by developing a domain-robust deep network using attention and few-shot unsupervised domain adaptation, achieving state-of-the-art results with two orders of magnitude fewer target domain images and introducing a new large-scale dataset called SVOX.
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. With 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. The pytorch code is available at https://github.com/valeriopaolicelli/AdAGeo .