Multi-step domain adaptation by adversarial attack to $\mathcal{H} Δ\mathcal{H}$-divergence
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackDomain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Test-Time Adaptation and Adversarial Robustness
This paper studies test-time adaptation in the context of adversarial robustness. We first formulate an adversarial threat model for test-time adaptation, where the defender may have a unique advantage as the adversarial…
Adversarial RobustnessDomain AdaptationTest-time AdaptationUnsupervised Domain AdaptationLearn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks
Recent work in black-box adversarial attacks for NLP systems has attracted much attention. Prior black-box attacks assume that attackers can observe output labels from target models based on selected inputs. In this work…
Adversarial AttackDomain AdaptationMeta-LearningMulti-Domain Sentiment Classification+2RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised lear…
Domain AdaptationUnsupervised Domain AdaptationUnsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts. Most UDA approaches emphasize transfer ability, but often overloo…
Unsupervised Domain AdaptationAdversarial RobustnessImproving the Generalization of Adversarial Training with Domain Adaptation
By injecting adversarial examples into training data, adversarial training is promising for improving the robustness of deep learning models. However, most existing adversarial training approaches are based on a specific…
Adversarial AttackDomain Adaptation