The benefit of distraction: Denoising camera-based physiological measurements using inverse attention

Ewa Nowara

Abstract: Predicting the geographic location (geo-localization) from a single ground-level RGB image taken anywhere in the world is a very challenging problem. The challenges include huge diversity of images due to different en- vironmental scenarios, drastic variation in the appearance of the same location depending on the time of the day, weather, season, and more importantly, the prediction is made from a single image possibly having only a few geo-locating cues. For these reasons, most existing works are restricted to specific cities, im- agery, or worldwide landmarks. In this work, we focus on developing an efficient solution to planet-scale single-image geo-localization. To this end, we propose TransLocator, a unified dual-branch transformer network that attends to tiny details over the entire image and produces robust feature representation under extreme appearance variations. TransLocator takes an RGB image and its semantic seg- mentation map as inputs, interacts between its two parallel branches after each transformer layer and simultaneously performs geo-localization and scene recogni- tion in a multi-task fashion. We evaluate TransLocator on four benchmark datasets - Im2GPS, Im2GPS3k, YFCC4k, YFCC26k and obtain 5.5%, 14.1%, 4.9%, 9.9% continent-level accuracy improvement over the state-of-the-art. TransLocator is also validated on real-world test images and found to be more effective than previous methods