> I disagree with the conclusion that with a bit of work AI could take down the best Geoguessrs. The best players already take into account all the metadata like camera quality and distinctive features of the Google car.
Isn’t this exactly what an AI might do even better, though? There might be statistical variations in image quality between cameras and processing that are imperceptible to a human but easy for machine learning to pick up?
True, but less than half of world countries are covered by street view and it's possible for a human to learn the distinctive metadata features of every single one, together with all the common roadside features like poles, road markings, and vegetation. So I don't know if the level of granularity where statistical variations are noticed is required to succeed at least in determining the country.
But in terms of picking the closest point within a country,
perhaps with a large enough dataset the AI would be able to distinguish based on local weather conditions when the Google car was driving through certain regions. And this would trump the player's ability to read place names and signage.
Isn’t this exactly what an AI might do even better, though? There might be statistical variations in image quality between cameras and processing that are imperceptible to a human but easy for machine learning to pick up?