Which country is this picture from? New data and methods for DNN-based country recognition
This work addresses the need for country recognition in applications like fake news identification and disinformation prevention, offering an incremental improvement over existing geo-coordinate estimation methods.
The paper tackles the problem of recognizing the country where a picture was taken, introducing the VIPPGeo dataset with 3.8 million geo-tagged images and training a model that outperforms current state-of-the-art methods by framing it as a classification task.
Recognizing the country where a picture has been taken has many potential applications, such as identification of fake news and prevention of disinformation campaigns. Previous works focused on the estimation of the geo-coordinates where a picture has been taken. Yet, recognizing in which country an image was taken could be more critical, from a semantic and forensic point of view, than estimating its spatial coordinates. In the above framework, this paper provides two contributions. First, we introduce the VIPPGeo dataset, containing 3.8 million geo-tagged images. Secondly, we used the dataset to train a model casting the country recognition problem as a classification problem. The experiments show that our model provides better results than the current state of the art. Notably, we found that asking the network to identify the country provides better results than estimating the geo-coordinates and then tracing them back to the country where the picture was taken.