2023/04/12 by Chengchao Xu, Xinmei Tian, Xu, Chengchao +1 · 1 citation
Computer Science · Earth and Planetary Sciences · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Seismic Imaging and Inversion Techniques
paper · pdf · doi:10.48550/arxiv.2304.05675
openalex publication_date 2023/04/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep neural networks (DNNs) have shown exciting performance in various tasks, yet suffer generalization failures when meeting unknown target domains. One of the most promising approaches to achieve domain generalization (DG) is generating unseen data, e.g., mixup, to cover the unknown target data. However, existing works overlook the challenges induced by the simultaneous appearance of changes in both the semantic and distribution space. Accordingly, such a challenge makes source distributions hard to fit for DNNs. To mitigate the hard-fitting issue, we propose to perform a semantic-aware mixup (SAM) for domain generalization, where whether to perform mixup depends on the semantic and domain information. The feasibility of SAM shares the same spirits with the Fourier-based mixup. Namely, the Fourier phase spectrum is expected to contain semantics information (relating to labels), while the Fourier amplitude retains other information (relating to style information). Built upon the insight, SAM applies different mixup strategies to the Fourier phase spectrum and amplitude information. For instance, SAM merely performs mixup on the amplitude spectrum when both the semantic and domain information changes. Consequently, the overwhelmingly large change can be avoided. We validate the effectiveness of SAM using image classification tasks on several DG benchmarks.