In this paper, we introduce a novel framework for the challenging problem of One-Shot Unsupervised Domain Adaptation (OSUDA), which aims to adapt to a target domain with only a single unlabeled target sample. Unlike existing approaches that rely on large labeled source and unlabeled target data, our Target-driven One-Shot UDA (TOS-UDA) approach employs a learnable augmentation strategy guided by the target sample's style to align the source distribution with the target distribution. Our method consists of three modules: an augmentation module, a style alignment module, and a classifier. Unlike existing methods, our augmentation module allows for strong transformations of the source samples, and the style of the single target sample available is exploited to guide the augmentation by ensuring perceptual similarity. Furthermore, our approach integrates augmentation with style alignment, eliminating the need for separate pre-training on additional datasets. Our method outperforms or performs comparably to existing OS-UDA methods on the Digits and DomainNet benchmarks.

翻译：本文针对一次性无监督域适应（OS-UDA）这一具有挑战性的问题提出了一种新颖框架，该问题的目标是在仅有一个未标注目标样本的情况下实现向目标域的适应。与依赖大量标注源数据和未标注目标数据的现有方法不同，我们的目标驱动一次性无监督域适应（TOS-UDA）方法采用一种由目标样本风格引导的可学习增强策略，以对齐源分布与目标分布。我们的方法包含三个模块：增强模块、风格对齐模块和分类器。与现有方法不同的是，我们的增强模块允许对源样本进行强变换，并利用单个可用目标样本的风格，通过确保感知相似性来引导增强过程。此外，我们的方法将增强与风格对齐相结合，无需在额外数据集上进行单独的预训练。在Digits和DomainNet基准测试上，我们的方法性能优于或与现有OS-UDA方法相当。