Keywords: domain generalization, limited data, interpolation, invariant representation
TL;DR: We devise an algorithm to learn a representation that is robustly invariant under interpolation operation for domain generalization.
Abstract: We address domain generalization (DG) by viewing the underlying distributional shift as performing interpolation between domains. We devise an algorithm to learn a representation that is robustly invariant under such interpolation and term it as interpolation robustness. We investigate the failure aspect of DG algorithms when availability of training data is scarce. Through extensive experiments, we show that our approach significantly outperforms the recent state-of-the-art algorithm DIRT and the baseline DeepAll on average across different sizes of data on PACS and VLCS datasets.