Supplementary: CharacterizingGeneralizationunder Out-Of-DistributionShiftsinDeepMetricLearning

Subsequently, we select train-test splits from the same iteration steps. These settings are used throughout our study. For the few-shot experiments, the same pipeline parameters were utilized with changes noted in the respectivesection. However,thefactthatFIDscores are relatively close to another despite large semantic differences between datasets may indicate that FID based on our utilised FID estimator (Sec. Beyond these limits, generic representations learned byself-supervised learning may offerbetter zero-shot generalization,asalsodiscussedonSec.