Adversarial Robustness for Unsupervised Domain Adaptation

09/02/2021
by   Muhammad Awais, et al.
14

Extensive Unsupervised Domain Adaptation (UDA) studies have shown great success in practice by learning transferable representations across a labeled source domain and an unlabeled target domain with deep models. However, previous works focus on improving the generalization ability of UDA models on clean examples without considering the adversarial robustness, which is crucial in real-world applications. Conventional adversarial training methods are not suitable for the adversarial robustness on the unlabeled target domain of UDA since they train models with adversarial examples generated by the supervised loss function. In this work, we leverage intermediate representations learned by multiple robust ImageNet models to improve the robustness of UDA models. Our method works by aligning the features of the UDA model with the robust features learned by ImageNet pre-trained models along with domain adaptation training. It utilizes both labeled and unlabeled domains and instills robustness without any adversarial intervention or label requirement during domain adaptation training. Experimental results show that our method significantly improves adversarial robustness compared to the baseline while keeping clean accuracy on various UDA benchmarks.

READ FULL TEXT

page 2

page 6

page 13

research
02/18/2022

Exploring Adversarially Robust Training for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) methods aim to transfer knowledge f...
research
12/12/2022

SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation

As acquiring manual labels on data could be costly, unsupervised domain ...
research
08/03/2018

Agnostic Domain Generalization

The ability to generalize across visual domains is crucial for the robus...
research
04/25/2018

Unsupervised Domain Adaptation with Adversarial Residual Transform Networks

Domain adaptation is widely used in learning problems lacking labels. Re...
research
08/26/2022

Domain Adaptation with Adversarial Training on Penultimate Activations

Enhancing model prediction confidence on unlabeled target data is an imp...
research
06/05/2021

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Unsupervised domain adaptation (UDA) involves a supervised loss in a lab...
research
03/01/2022

Global-Local Regularization Via Distributional Robustness

Despite superior performance in many situations, deep neural networks ar...

Please sign up or login with your details

Forgot password? Click here to reset