Deep learning has made significant advancements in supervised learning. However, models trained in this setting often face challenges due to domain shift between training and test sets, resulting in a significant drop in performance during testing. To address this issue, several domain generalization methods have been developed to learn robust and domain-invariant features from multiple training domains that can generalize well to unseen test domains. Data augmentation plays a crucial role in achieving this goal by enhancing the diversity of the training data. In this paper, inspired by the observation that normalizing an image with different statistics generated by different batches with various domains can perturb its feature, we propose a simple yet effective method called NormAUG (Normalization-guided Augmentation). Our method includes two paths: the main path and the auxiliary (augmented) path. During training, the auxiliary path includes multiple sub-paths, each corresponding to batch normalization for a single domain or a random combination of multiple domains. This introduces diverse information at the feature level and improves the generalization of the main path. Moreover, our NormAUG method effectively reduces the existing upper boundary for generalization based on theoretical perspectives. During the test stage, we leverage an ensemble strategy to combine the predictions from the auxiliary path of our model, further boosting performance. Extensive experiments are conducted on multiple benchmark datasets to validate the effectiveness of our proposed method.

翻译：深度学习在监督学习领域取得了显著进展。然而，在此设定下训练的模型常因训练集与测试集之间的领域偏移而面临挑战，导致测试阶段性能大幅下降。为解决此问题，研究者提出了多种领域泛化方法，旨在从多个训练领域中学习鲁棒且领域不变的特征，从而有效泛化至未见过的测试领域。数据增强通过提升训练数据的多样性，在实现该目标中发挥着关键作用。本文受以下观察启发：使用来自不同领域的多个批次生成的不同统计量对图像进行归一化处理，能够扰动其特征。基于此，我们提出一种简洁而有效的方法——NormAUG（归一化引导增强）。该方法包含两条路径：主路径与辅助（增强）路径。在训练阶段，辅助路径包含多个子路径，每条子路径对应单个领域的批归一化或多个领域的随机组合归一化。这使模型在特征层面引入多样性信息，并提升主路径的泛化能力。此外，从理论视角看，NormAUG方法有效降低了现有的泛化性能上界。在测试阶段，我们利用集成策略融合模型辅助路径的预测结果，进一步提升了性能。我们在多个基准数据集上进行了大量实验，验证了所提方法的有效性。