Deep neural networks (DNNs) usually fail to generalize well to outside of distribution (OOD) data, especially in the extreme case of single domain generalization (single-DG) that transfers DNNs from single domain to multiple unseen domains. Existing single-DG techniques commonly devise various data-augmentation algorithms, and remould the multi-source domain generalization methodology to learn domain-generalized (semantic) features. Nevertheless, these methods are typically modality-specific, thereby being only applicable to one single modality (e.g., image). In contrast, we target a versatile Modality-Agnostic Debiasing (MAD) framework for single-DG, that enables generalization for different modalities. Technically, MAD introduces a novel two-branch classifier: a biased-branch encourages the classifier to identify the domain-specific (superficial) features, and a general-branch captures domain-generalized features based on the knowledge from biased-branch. Our MAD is appealing in view that it is pluggable to most single-DG models. We validate the superiority of our MAD in a variety of single-DG scenarios with different modalities, including recognition on 1D texts, 2D images, 3D point clouds, and semantic segmentation on 2D images. More remarkably, for recognition on 3D point clouds and semantic segmentation on 2D images, MAD improves DSU by 2.82\% and 1.5\% in accuracy and mIOU.

翻译：深度神经网络（DNNs）通常难以在分布外（OOD）数据上实现良好泛化，尤其在单域泛化（single-DG）这一极端场景中，该场景要求将DNN从单个领域迁移至多个未见过的领域。现有单域泛化技术通常设计各种数据增强算法，并改造多源域泛化方法以学习领域泛化（语义）特征。然而，这类方法普遍具有模态特异性，仅能适用于单一模态（如图像）。与此不同，我们提出一种面向单域泛化的通用模态无关去偏（MAD）框架，能够支持不同模态的泛化。技术层面，MAD引入一种新颖的双分支分类器：偏置分支促使分类器识别领域特定（浅层）特征，而通用分支则基于偏置分支的知识捕捉领域泛化特征。我们的MAD框架具备良好的可插拔性，可适配大多数单域泛化模型。我们在不同模态的多种单域泛化场景中验证了MAD的优越性，包括1D文本识别、2D图像识别、3D点云识别以及2D图像语义分割。尤为显著的是，在3D点云识别和2D图像语义分割任务中，MAD将DSU方法的准确率分别提升2.82%和平均交并比（mIOU）提升1.5%。