NormAUG：面向领域泛化的归一化引导增强
NormAUG: Normalization-guided Augmentation for Domain Generalization
AI总结：
针对领域偏移导致的性能下降问题，本文提出NormAUG方法，通过归一化引导的多子路径增强特征多样性，降低泛化上界，并在测试时集成辅助路径预测，在多个基准数据集上验证了其有效性。
摘要：
深度学习在监督学习方面取得了显著进展。然而，在此设置下训练的模型常常因训练集与测试集之间的领域偏移而面临挑战，导致测试时性能大幅下降。为解决这一问题，已开发出多种领域泛化方法，旨在从多个训练域中学习鲁棒且域不变的特征，从而能够很好地泛化到未见过的测试域。数据增强通过提升训练数据的多样性，在实现这一目标中起着关键作用。本文中，受观察到使用来自不同批次、不同领域的统计量对图像进行归一化会扰动其特征这一现象的启发，我们提出了一种简单而有效的方法，称为NormAUG（归一化引导增强）。我们的方法包含两条路径：主路径和辅助（增强）路径。在训练期间，辅助路径包含多个子路径，每个子路径对应单个领域的批量归一化或多个领域的随机组合。这在特征层面引入了多样信息，并提升了主路径的泛化能力。此外，从理论角度看，我们的NormAUG方法有效降低了现有的泛化上界。在测试阶段，我们利用集成策略，结合模型辅助路径的预测，进一步提升性能。我们在多个基准数据集上进行了大量实验，以验证所提出方法的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
