Regional biases in image geolocation estimation: a case study with the SenseCity Africa dataset

arXiv:2404.02558v1 Announce Type: new
Abstract: Advances in Artificial Intelligence are challenged by the biases rooted in the datasets used to train the models. In image geolocation estimation, models are mostly trained using data from specific geographic regions, notably the Western world, and as a result, they may struggle to comprehend the complexities of underrepresented regions. To assess this issue, we apply a state-of-the-art image geolocation estimation model (ISNs) to a crowd-sourced dataset of geolocated images from the African continent (SCA100), …

abstract advances africa artificial artificial intelligence arxiv biases case case study cs.cv data dataset datasets geolocation image intelligence regional study train type world