Adaptation to out-of-distribution data is a meta-challenge for all statistical learning algorithms that strongly rely on the i.i.d. assumption. It leads to unavoidable labor costs and confidence crises in realistic applications. For that, domain generalization aims at mining domain-irrelevant knowledge from multiple source domains that can generalize to unseen target domains. In this paper, by leveraging the frequency domain of an image, we uniquely work with two key observations: (i) the high-frequency information of an image depicts object edge structure, which preserves high-level semantic information of the object is naturally consistent across different domains, and (ii) the low-frequency component retains object smooth structure, while this information is susceptible to domain shifts. Motivated by the above observations, we introduce (i) an encoder-decoder structure to disentangle high- and low-frequency feature of an image, (ii) an information interaction mechanism to ensure the helpful knowledge from both two parts can cooperate effectively, and (iii) a novel data augmentation technique that works on the frequency domain to encourage the robustness of frequency-wise feature disentangling. The proposed method obtains state-of-the-art performance on three widely used domain generalization benchmarks (Digit-DG, Office-Home, and PACS).
翻译:适应分配外数据是所有统计学习算法的元挑战,这些算法强烈依赖i.d.假设。它导致不可避免的人工成本和信任危机,在现实应用中造成不可避免的劳动成本和信心危机。为此,领域一般化的目的是从多种来源领域挖掘可推广到看不见目标领域的与域有关的知识。在本文件中,我们利用图像的频率领域,以两种关键观察方式开展了独特的工作:(一) 图像的高频信息描绘了目标边缘结构,这种结构保存了不同领域的高端语义信息,并且保存了该对象的高端语义信息,并且(二) 低频部分保留了目标的平稳结构,而这一信息容易发生域变换。受上述观察的驱动,我们引入了(一) 编码解密器解密图像的高频和低频特征结构,(二) 信息互动机制,以确保两个部分的有用知识能够有效合作,以及(三) 新的数据增强技术,在频域进行工作,鼓励频率特性稳定的特征分散性,并广泛使用PA-DG-G-G-G-广泛使用业绩方法。