We propose a novel domain generalization technique, referred to as Randomized Adversarial Style Perturbation (RASP), which is motivated by the observation that the characteristics of each domain are captured by the feature statistics corresponding to style. The proposed algorithm perturbs the style of a feature in an adversarial direction towards a randomly selected class, and makes the model learn against being misled by the unexpected styles observed in unseen target domains. While RASP is effective to handle domain shifts, its naive integration into the training procedure might degrade the capability of learning knowledge from source domains because it has no restriction on the perturbations of representations. This challenge is alleviated by Normalized Feature Mixup (NFM), which facilitates the learning of the original features while achieving robustness to perturbed representations via their mixup during training. We evaluate the proposed algorithm via extensive experiments on various benchmarks and show that our approach improves domain generalization performance, especially in large-scale benchmarks.
翻译:本文提出了一种新颖的域泛化技术,称为随机对抗样式扰动(RASP),该技术受到的启发来自于对每个域的特征统计量进行样式提取。该算法将特征的样式向随机选择的类别的对抗方向进行扰动,并使模型在学习中抵制被未见过的目标域中观察到的意外样式所误导。然而,RASP的干扰可能会降低该算法从源域中学习知识的能力,因为它对表示的扰动没有任何限制。这个挑战通过标准化特征混合(NFM)来缓解,NFM通过训练期间的混合来促进原始特征的学习,同时实现对被扰动表示的强鲁棒性。我们在各种基准测试中进行了广泛的实验证明了我们提出的算法的有效性和改进了域泛化性能,特别是在大规模基准测试中。