Skip to yearly menu bar Skip to main content


Poster
in
Workshop: INTERPOLATE — First Workshop on Interpolation Regularizers and Beyond

Improving Domain Generalization with Interpolation Robustness

Ragja Palakkadavath · Thanh Nguyen-Tang · Sunil Gupta · Svetha Venkatesh

Keywords: [ invariant representation ] [ Limited data ] [ interpolation ] [ 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.

Chat is not available.