Regional biases in image geolocation estimation: a case study with the SenseCity Africa dataset
This highlights regional biases in AI models for image geolocation, showing they may fail in underrepresented areas like Africa, which is an incremental but important finding for fairness in computer vision.
The study applied a state-of-the-art image geolocation model to an African dataset and found it over-predicts locations in high-income Western countries, with accuracy notably decreasing compared to the Western benchmark, especially for low-income regions like Sub-Saharan Africa.
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), and then explore the regional and socioeconomic biases underlying the model's predictions. Our findings show that the ISNs model tends to over-predict image locations in high-income countries of the Western world, which is consistent with the geographic distribution of its training data, i.e., the IM2GPS3k dataset. Accordingly, when compared to the IM2GPS3k benchmark, the accuracy of the ISNs model notably decreases at all scales. Additionally, we cluster images of the SCA100 dataset based on how accurately they are predicted by the ISNs model and show the model's difficulties in correctly predicting the locations of images in low income regions, especially in Sub-Saharan Africa. Therefore, our results suggest that using IM2GPS3k as a training set and benchmark for image geolocation estimation and other computer vision models overlooks its potential application in the African context.