Single Domain Generalization via Normalised Cross-correlation Based Convolutions
This addresses domain shift issues for deep learning models trained on single-source data, offering an incremental improvement over prior augmentation-based approaches.
The paper tackles the problem of domain shift in deep learning by proposing a novel linear operator, XCNorm, which uses normalized cross-correlation to enhance robustness in Single Domain Generalization, achieving performance comparable to state-of-the-art methods on benchmarks.
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.