As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption. In previous DG models, by generating virtual data to supplement observed source domains, the data augmentation based methods have shown its effectiveness. To simulate the possible unseen domains, most of them enrich the diversity of original data via image-level style transformation. However, we argue that the potential styles are hard to be exhaustively illustrated and fully augmented due to the limited referred styles, leading the diversity could not be always guaranteed. Unlike image-level augmentation, we in this paper develop a simple yet effective feature-based style randomization module to achieve feature-level augmentation, which can produce random styles via integrating random noise into the original style. Compared with existing image-level augmentation, our feature-level augmentation favors a more goal-oriented and sample-diverse way. Furthermore, to sufficiently explore the efficacy of the proposed module, we design a novel progressive training strategy to enable all parameters of the network to be fully trained. Extensive experiments on three standard benchmark datasets, i.e., PACS, VLCS and Office-Home, highlight the superiority of our method compared to the state-of-the-art methods.
翻译:作为最近一个值得注意的主题,域通用(DG)的目的是首先学习多源域的通用模型,然后直接推广到任意的无形目标域,而不作任何额外的调整。在以前的DG模型中,通过生成虚拟数据以补充观察到的来源域,数据增强方法显示了其有效性。模拟可能的无形域,其中多数通过图像级风格转换丰富原始数据的多样性。然而,我们争辩说,由于推荐的风格有限,潜在样式很难得到详尽的展示和充分扩展,因此不可能始终保证多样性。与图像级增强不同,我们本文开发了一个简单而有效的基于地貌的随机化模块,以实现地貌级增强,通过将随机噪音纳入原有的风格来产生随机风格。与现有的图像级增强相比,我们的特性级增强有利于更注重目标和样本化的方式。此外,为了充分探索拟议模块的功效,我们设计了一个新的渐进培训战略,使网络的所有参数都能得到充分培训。在三个标准基准数据集上进行广泛的实验,即:将随机噪音纳入原始风格。PACS-VCS-S-PACS-S-S-Servical-S-stalvical-stal-Pal-Pal-Pal-Serview-Pal-Pal-Pal-Pal-Pal-S-S-S-S-Pal-S-S-S-Pal-S-S-S-S-Pal-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-Prigal-S-S-Pality-S-S-S-Pal-Pal-S-S-S-S-S-S-S-PS-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-PL-S-S-PRatal-S-S-Servial-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-