Skip to yearly menu bar Skip to main content

Blue Sky Idea
Workshop: New Frontiers in Adversarial Machine Learning

Multi-step domain adaptation by adversarial attack to $\mathcal{H} \Delta \mathcal{H}$-divergence

Arip Asadulaev · Alexander Panfilov · Andrey Filchenkov

Abstract: Adversarial examples are transferable between different models. In our paper, we propose to use this property for multi-step domain adaptation. In unsupervised domain adaptation settings, we demonstrate that replacing the source domain with adversarial examples to $\mathcal{H} \Delta \mathcal{H}$-divergence can improve source classifier accuracy on the target domain. Our method can be connected with most domain adaptation techniques. We conducted a range of experiments and achieved improvement in accuracy on Digits and Office-Home datasets.

Chat is not available.