Timezone: »

Improving Domain Generalization with Interpolation Robustness
Ragja Palakkadavath · Thanh Nguyen-Tang · Sunil Gupta · Svetha Venkatesh
Event URL: https://openreview.net/forum?id=Yl_4LpR_3Z »

We address domain generalization by viewing the underlying distributional shift as interpolation between domains and subsequently devise an algorithm to learn a representation that is robustly invariant under such interpolation, which we coin our approach as \textit{interpolation robustness}. Through extensive experiments, we show that our approach outperforms significantly the recent state-of-the-art algorithm \citet{NEURIPS2021_2a271795} and the baseline DeepAll in a limited data setting on PACS and VLCS datasets.

Author Information

Ragja Palakkadavath (Deakin University)
Thanh Nguyen-Tang (Johns Hopkins University)
Sunil Gupta (Deakin University)
Svetha Venkatesh (Deakin University)

More from the Same Authors