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：本文提出一种新颖的领域泛化技术，称为随机对抗风格扰动（Randomized Adversarial Style Perturbation, RASP），其动机源于对领域特性可通过对应风格的统计特征进行捕捉这一观察。该算法将特征风格沿对抗方向朝着随机选择的类别进行扰动，使模型学习抵御在未知目标域中遇到的意外风格所导致的误导。尽管RASP能有效应对领域偏移，但将其直接融入训练流程可能会削弱从源域中获取知识的能力，因为该方法对表征扰动未施加约束。通过引入归一化特征混合（Normalized Feature Mixup, NFM）可缓解这一挑战，该方法在训练过程中通过混合原始与扰动表征，既促进对原始特征的学习，又实现对扰动表征的鲁棒性。我们在多个基准数据集上开展了广泛实验评估，结果表明所提方法显著提升了领域泛化性能，尤其在大型基准测试中表现突出。