Recent self-supervised advances in medical computer vision exploit the global and local anatomical self-similarity for pretraining prior to downstream tasks suchassegmentation.

In this paper,we consider a setting where sensitive attributes indirectly manifest in an auxiliary representation graphrather than being directly observed.

In the context of localization, however, there is no natural definition of classes. Therefore, images areartificially separated intopositive/negativeclasses with respect to the chosen anchor images, based on some geometric proximity measure.