Domain generalization (DG) aims to generalize a model trained on multiple source (i.e., training) domains to a distributionally different target (i.e., test) domain. In contrast to the conventional DG that strictly requires the availability of multiple source domains, this paper considers a more realistic yet challenging scenario, namely Single Domain Generalization (Single-DG), where only one source domain is available for training. In this scenario, the limited diversity may jeopardize the model generalization on unseen target domains. To tackle this problem, we propose a style-complement module to enhance the generalization power of the model by synthesizing images from diverse distributions that are complementary to the source ones. More specifically, we adopt a tractable upper bound of mutual information (MI) between the generated and source samples and perform a two-step optimization iteratively: (1) by minimizing the MI upper bound approximation for each sample pair, the generated images are forced to be diversified from the source samples; (2) subsequently, we maximize the MI between the samples from the same semantic category, which assists the network to learn discriminative features from diverse-styled images. Extensive experiments on three benchmark datasets demonstrate the superiority of our approach, which surpasses the state-of-the-art single-DG methods by up to 25.14%.

翻译：域泛化（Domain Generalization, DG）旨在将基于多个源域（即训练域）训练的模型泛化至分布不同的目标域（即测试域）。与传统DG严格依赖多个源域不同，本文考虑一个更具现实意义但也更具挑战性的场景——单域泛化（Single-DG），即仅有一个源域可用于训练。在该场景下，有限的多样性可能损害模型在未知目标域的泛化能力。为解决此问题，我们提出一种风格补全模块，通过合成与源域互补的多样化分布图像来增强模型泛化能力。具体而言，我们采用生成样本与源样本之间互信息（Mutual Information, MI）的可处理上界，并迭代执行两步优化：首先，最小化每个样本对的MI上界近似值，迫使生成图像与源样本实现多样化；其次，最大化同一语义类别样本间的MI，帮助网络从多样化风格图像中学习判别性特征。在三个基准数据集上的大量实验表明，所提方法性能优越，将现有最先进单域泛化方法的效果提升高达25.14%。