We tackle the domain generalisation (DG) problem by posing it as a domain adaptation (DA) task where we adversarially synthesise the worst-case target domain and adapt a model to that worst-case domain, thereby improving the model's robustness. To synthesise data that is challenging yet semantics-preserving, we generate Fourier amplitude images and combine them with source domain phase images, exploiting the widely believed conjecture from signal processing that amplitude spectra mainly determines image style, while phase data mainly captures image semantics. To synthesise a worst-case domain for adaptation, we train the classifier and the amplitude generator adversarially. Specifically, we exploit the maximum classifier discrepancy (MCD) principle from DA that relates the target domain performance to the discrepancy of classifiers in the model hypothesis space. By Bayesian hypothesis modeling, we express the model hypothesis space effectively as a posterior distribution over classifiers given the source domains, making adversarial MCD minimisation feasible. On the DomainBed benchmark including the large-scale DomainNet dataset, the proposed approach yields significantly improved domain generalisation performance over the state-of-the-art.

翻译：我们通过将域泛化（DG）问题视为域自适应（DA）任务来解决该问题，在该任务中，我们以对抗方式合成最坏情况的目标域，并将模型自适应到该最坏情况域，从而提升模型的鲁棒性。为了合成具有挑战性但保持语义不变的数据，我们生成傅里叶振幅图像，并将其与源域相位图像结合，利用信号处理领域广泛承认的猜想——振幅谱主要决定图像风格，而相位数据主要捕捉图像语义。为了合成用于自适应的最坏情况域，我们对分类器和振幅生成器进行对抗性训练。具体而言，我们利用域自适应中的最大分类器差异（MCD）原则，该原则将目标域性能与模型假设空间中分类器的差异联系起来。通过贝叶斯假设建模，我们将模型假设空间有效表示为给定源域条件下分类器的后验分布，从而使对抗性MCD最小化成为可行。在包含大规模DomainNet数据集的DomainBed基准测试上，所提出的方法相较于现有最优方法显著提升了域泛化性能。