Domain generalization (DG) is a principal task to evaluate the robustness of computer vision models. Many previous studies have used normalization for DG. In normalization, statistics and normalized features are regarded as style and content, respectively. However, it has a content variation problem when removing style because the boundary between content and style is unclear. This study addresses this problem from the frequency domain perspective, where amplitude and phase are considered as style and content, respectively. First, we verify the quantitative phase variation of normalization through the mathematical derivation of the Fourier transform formula. Then, based on this, we propose a novel normalization method, PCNorm, which eliminates style only as the preserving content through spectral decomposition. Furthermore, we propose advanced PCNorm variants, CCNorm and SCNorm, which adjust the degrees of variations in content and style, respectively. Thus, they can learn domain-agnostic representations for DG. With the normalization methods, we propose ResNet-variant models, DAC-P and DAC-SC, which are robust to the domain gap. The proposed models outperform other recent DG methods. The DAC-SC achieves an average state-of-the-art performance of 65.6% on five datasets: PACS, VLCS, Office-Home, DomainNet, and TerraIncognita.
翻译:广域化( DG) 是评估计算机视觉模型稳健性的主要任务。 许多先前的研究都对 DG 采用了常规化方法。 在常规化中,统计和常规化特征被分别视为样式和内容。 但是,在去除样式时,由于内容和风格的界限不清楚,它的内容差异问题在于删除样式时。本研究从频率域的角度探讨这一问题,即振幅和阶段分别被视为风格和内容。首先,我们通过Fourier变换公式的数学衍生,来核实正常化的定量阶段差异。然后,我们在此基础上,我们提议一种新型的正常化方法,即PCNorm,它仅通过光谱分解去除保存内容的风格。此外,我们建议采用先进的PCNorm变式、CCNorm和SCNorm,分别调整内容和风格变化程度的大小。因此,他们可以学习DG的域域分解表达方式。我们建议采用ResNet-变量模型、DAC-P和DAC-SC-SC, 以这种模型取代了最近的DG-NE-NU-DG-I 方法。</s>