Deep learning techniques often perform poorly in the presence of domain shift, where the test data follows a different distribution than the training data. The most practically desirable approach to address this issue is Single Domain Generalization (S-DG), which aims to train robust models using data from a single source. Prior work on S-DG has primarily focused on using data augmentation techniques to generate diverse training data. In this paper, we explore an alternative approach by investigating the robustness of linear operators, such as convolution and dense layers commonly used in deep learning. We propose a novel operator called XCNorm that computes the normalized cross-correlation between weights and an input feature patch. This approach is invariant to both affine shifts and changes in energy within a local feature patch and eliminates the need for commonly used non-linear activation functions. We show that deep neural networks composed of this operator are robust to common semantic distribution shifts. Furthermore, our empirical results on single-domain generalization benchmarks demonstrate that our proposed technique performs comparably to the state-of-the-art methods.

翻译：深度学习技术通常在存在域偏移的情况下表现不佳，即测试数据与训练数据的分布不同。解决这一问题最实际的方法是单域泛化（S-DG），其目标是通过单一源数据训练鲁棒模型。先前关于S-DG的研究主要集中在使用数据增强技术生成多样化的训练数据。在本文中，我们探索了一种替代方法，通过研究深度学习常用运算（如卷积和密集层）的鲁棒性。我们提出了一种名为XCNorm的新型算子，该算子计算权重与输入特征块之间的归一化互相关。这种方法对局部特征块内的仿射偏移和能量变化具有不变性，并且消除了对常用非线性激活函数的需求。我们证明，由该算子组成的深度神经网络对常见的语义分布偏移具有鲁棒性。此外，我们在单域泛化基准上的实验结果证明，我们提出的技术性能与最先进的方法相当。