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 learning) as the
supervised source loss has clear domain gap and the unsupervised target loss is
often noisy due to the lack of annotations. This paper presents RDA, a robust
domain adaptation technique that introduces adversarial attacking to mitigate
overfitting in UDA. We achieve robust domain adaptation by a novel Fourier
adversarial attacking (FAA) method that allows large magnitude of perturbation
noises but has minimal modification of image semantics, the former is critical
to the effectiveness of its generated adversarial samples due to the existence
of 'domain gaps'. Specifically, FAA decomposes images into multiple frequency
components (FCs) and generates adversarial samples by just perturbating certain
FCs that capture little semantic information. With FAA-generated samples, the
training can continue the 'random walk' and drift into an area with a flat loss
landscape, leading to more robust domain adaptation. Extensive experiments over
multiple domain adaptation tasks show that RDA can work with different computer
vision tasks with superior performance.

本文提出了一种基于 Fourier 对抗攻击的鲁棒域自适应技术 (RDA)，可用于解决多个计算机视觉任务中的域自适应问题，其生成的对抗样本可以在使图像特征保持不变的情况下，减小由于域偏移带来的噪声问题，从而使模型的鲁棒性增强。

基于傅里叶对抗攻击的鲁棒领域自适应

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Recent works on domain adaptation exploit adversarial training to obtain
domain-invariant feature representations from the joint learning of feature
extractor and domain discriminator networks. However, domain adversarial
methods render suboptimal performances since they attempt to match the
distributions among the domains without considering the task at hand. We
propose Drop to Adapt (DTA), which leverages adversarial dropout to learn
strongly discriminative features by enforcing the cluster assumption.
Accordingly, we design objective functions to support robust domain adaptation.
We demonstrate efficacy of the proposed method on various experiments and
achieve consistent improvements in both image classification and semantic
segmentation tasks. Our source code is available at
this https URL

通过利用 Drop to Adapt (DTA) 中的对抗丢失来学习具有判别力的特征，从而在多个实验中实现了稳健的域自适应，提高了图像分类和语义分割任务的一致性性能。