Domain Generalization using Ensemble Learning

TL;DR

This paper proposes an ensemble learning approach to improve the generalization ability of models trained on a single source domain, addressing a key challenge in domain generalization.

Contribution

It introduces a novel ensemble method that combines deep learning models trained on one domain to enhance cross-domain generalization performance.

Findings

Ensemble models outperform individual base learners in domain generalization.

The approach shows promising improvements over single-source training.

Results indicate better adaptation to unseen target domains.

Abstract

Domain generalization is a sub-field of transfer learning that aims at bridging the gap between two different domains in the absence of any knowledge about the target domain. Our approach tackles the problem of a model's weak generalization when it is trained on a single source domain. From this perspective, we build an ensemble model on top of base deep learning models trained on a single source to enhance the generalization of their collective prediction. The results achieved thus far have demonstrated promising improvements of the ensemble over any of its base learners.