Domain generalization (DG) aims to learn a robust model from source domains that generalize well on unseen target domains. Recent studies focus on generating novel domain samples or features to diversify distributions complementary to source domains. Yet, these approaches can hardly deal with the restriction that the samples synthesized from various domains can cause semantic distortion. In this paper, we propose an online one-stage Cross Contrasting Feature Perturbation (CCFP) framework to simulate domain shift by generating perturbed features in the latent space while regularizing the model prediction against domain shift. Different from the previous fixed synthesizing strategy, we design modules with learnable feature perturbations and semantic consistency constraints. In contrast to prior work, our method does not use any generative-based models or domain labels. We conduct extensive experiments on a standard DomainBed benchmark with a strict evaluation protocol for a fair comparison. Comprehensive experiments show that our method outperforms the previous state-of-the-art, and quantitative analyses illustrate that our approach can alleviate the domain shift problem in out-of-distribution (OOD) scenarios.

翻译：领域泛化（Domain Generalization, DG）旨在从源领域学习一个鲁棒模型，使其在未见过的目标领域中具有良好泛化能力。近期研究聚焦于生成新颖的领域样本或特征，以多样化分布作为源领域的补充。然而，这些方法难以应对从不同领域合成的样本可能导致语义失真这一限制。本文提出了一种在线单阶段交叉对比特征扰动（Cross Contrasting Feature Perturbation, CCFP）框架，通过在潜在空间中生成扰动特征来模拟领域偏移，同时正则化模型预测以对抗领域偏移。与先前固定的合成策略不同，我们设计了具有可学习特征扰动和语义一致性约束的模块。与以往工作相比，本方法不使用任何基于生成的模型或领域标签。我们在标准DomainBed基准上进行了广泛实验，并采用严格的评估协议以确保公平比较。综合实验显示，本方法超越了先前的最优性能，而定量分析表明，我们的方法能有效缓解分布外（Out-of-Distribution, OOD）场景中的领域偏移问题。