Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning

TL;DR

This paper introduces the ooDML benchmark to evaluate deep metric learning's ability to generalize across diverse out-of-distribution shifts, revealing performance degradation and proposing few-shot DML for improvement.

Contribution

The paper systematically constructs challenging train-test splits and presents the ooDML benchmark to analyze generalization in DML under diverse distribution shifts.

Findings

Generalization degrades with increased shift difficulty

Some DML methods better retain performance under shifts

Few-shot DML improves generalization across shifts

Abstract

Deep Metric Learning (DML) aims to find representations suitable for zero-shot transfer to a priori unknown test distributions. 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 a broad 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 under out-of-distribution shifts in DML. ooDML is designed to probe the generalization performance on much more challenging, diverse train-to-test distribution shifts. Based on our new benchmark, we conduct a thorough empirical analysis of state-of-the-art DML methods. We find that while generalization tends to consistently degrade with difficulty, some methods are better at retaining performance as the distribution shift increases. Finally, we propose few-shot DML as an efficient way to consistently improve generalization in response to unknown test shifts presented in ooDML. Code available here: https://github.com/CompVis/Characterizing_Generalization_in_DML.