Multi-step domain adaptation by adversarial attack to $\mathcal{H} \Delta \mathcal{H}$-divergence. (arXiv:2207.08948v1 [cs.LG])

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 to most domain adaptation techniques. We
conducted a range of experiments and achieved improvement in accuracy on Digits
and Office-Home datasets.

adversarial attack delta domain lg