top of page
Image of a deep-sea environment showing various forms of marine life and geological features, with multiple highlighted sections, indicating objects of interest.

Schmidt Ocean Institute

New object detector model trained on FathomVerse data

We recently deployed a new object detector model in FathomVerse. Object detector models predict where in the image an object of interest is located, without trying to classify it. This model is used for generating AI proposals in Bound.

Jun 19, 2025

By

Joost Daniels

This new model was trained exclusively on consensus data that FathomVerse players generated by playing Bound. That includes about 50,000 localizations in 10,000 unique images, including the “urchin fields” and “coral cliffs” that have been a popular topic of discussion on the FathomVerse Discord.


Read more

bottom of page