To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent successes have come from methods that pre-specify the types of diversity that a model is exposed to during training, so that it can ultimately generalize well to new domains. However, na\"ive diversity based augmentations do not work effectively for domain generalization either because they cannot model large domain shift, or because the span of transforms that are pre-specified do not cover the types of shift commonly occurring in domain generalization. To address this issue, we present a novel framework that uses adversarially learned transformations (ALT) using a neural network to model plausible, yet hard image transformations that fool the classifier. This network is randomly initialized for each batch and trained for a fixed number of steps to maximize classification error. Further, we enforce consistency between the classifier's predictions on the clean and transformed images. With extensive empirical analysis, we find that this new form of adversarial transformations achieve both objectives of diversity and hardness simultaneously, outperforming all existing techniques on competitive benchmarks for single source domain generalization. We also show that ALT can naturally work with existing diversity modules to produce highly distinct, and large transformations of the source domain leading to state-of-the-art performance.

翻译：为了在单一源域上取得成功,将综合域的多样化最大化已成为最有效的战略之一。最近取得的许多成功来自预先确定模型在培训期间所接触的多样化类型的方法,以便最终能够向新域推广。然而,基于质量和多样性的增强对于域的概括化效果并不有效,要么因为它们不能模拟大域变换,要么因为预先指定的变换范围不包括在域变换中常见的变换类型。为了解决这个问题,我们提出了一个新的框架,利用对抗性学习的变换(ALT)使用神经网络来模拟可信的、但硬图像变换,使分类者愚弄的变形。这个网络为每个批次随机初始化,并训练了固定步骤,以尽量扩大分类误差。此外,我们加强分类者对清洁和变形图像的预测的一致性。通过广泛的经验分析,我们发现这种新的对抗性变形形式既能实现多样性和硬性两个目标,又能超越现有关于竞争性变形技术的神经网络来模拟表面变形,而使分类师格变形师则能产生一种完全不同的简单化的功能。我们还展示了现有单一源域变形。