CharacterizingGeneralizationunder Out-Of-DistributionShiftsinDeepMetricLearning

However, common evaluation protocols only test a single, fixed data split in which train and test classes are assigned randomly. More realistic evaluations should consider abroad spectrum of distribution shifts with potentially varying degree and difficulty. In this work, we systematically construct train-test splits of increasing difficulty and present the ooDML benchmark to characterize generalization underout-of-distribution shifts inDML.ooDMLis