English

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

Machine Learning 2022-07-20 v1 Cryptography and Security Computer Vision and Pattern Recognition

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 HΔH\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.

Keywords

Cite

@article{arxiv.2207.08948,
  title  = {Multi-step domain adaptation by adversarial attack to $\mathcal{H} \Delta \mathcal{H}$-divergence},
  author = {Arip Asadulaev and Alexander Panfilov and Andrey Filchenkov},
  journal= {arXiv preprint arXiv:2207.08948},
  year   = {2022}
}
R2 v1 2026-06-25T01:02:01.718Z