• image classification
• focal modulation networks
• outdoor image geolocation

We handle the problem of estimating a photo’s geographical location. Success in this assessment enables many interesting and helpful applications, like facilitating Disaster Management circumstances. However, this is also a very challenging task. Due to the complexity of the problem, we restrict the area to geolocate to a single city, treating geolocation as a classification problem where the districts of a city are the classes to be discriminated. In this thesis, we exploit the Focal Modulation Network that is promising to perform effectively and efficiently in visual modeling for real-world applications. Experimental results, on two diverse crawled datasets, show the effectiveness of our approach, taking into account that it is possible to replicate the pipeline for any given city.