Object-Level Explanations for Image Geolocation Models: a GeoGuessr use-case
For researchers and practitioners needing interpretability in geolocation models, this work provides a method to link model predictions to specific objects, though it is incremental as it applies existing attribution and segmentation techniques.
The paper proposes an object-centric pipeline to analyze visual evidence used by image geolocation models, showing that attribution-guided crops retain more predictive information than random crops on a three-country benchmark.
When humans play geolocation games such as GeoGuessr, they rely on concrete visual cues, such as road markings, vegetation, or architectural details, to infer where an image was captured. Whether image geolocation models rely on similar object-level evidence remains difficult to determine, as attribution methods like Grad-CAM typically highlight diffuse regions rather than coherent visual entities, making it difficult to link model predictions to specific objects or perceptible patterns. In this work, we propose an object-centric analysis pipeline to investigate the visual evidence used by geolocation models. Starting from attribution maps, we extract salient regions and segment them into object-like elements. We evaluate their predictive relevance through deletion and insertion tests, comparing attributionguided crops to randomly selected regions with similar coverage. Experiments on a three-country benchmark show that attribution-guided crops consistently retain more information for the model's prediction than random crops. These results suggest that attribution maps can be decomposed into interpretable, perceptible elements, providing a step toward object-level analysis of geolocation models.