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：本文提出了一种新颖的框架，用于解决具有挑战性的一次性无监督域适应（OSUDA）问题，该问题旨在仅使用单个无标注目标样本适应目标域。与依赖大量有标注源域和无标注目标域数据的现有方法不同，我们提出的面向目标的一次性无监督域适应（TOS-UDA）方法采用了一种可学习的增强策略，该策略以目标样本的风格为指导，将源分布与目标分布对齐。我们的方法包含三个模块：一个增强模块、一个风格对齐模块和一个分类器。与现有方法不同，我们的增强模块允许对源样本进行强变换，并且利用单个目标样本的风格来指导增强过程，确保感知相似性。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基准数据集上，我们的方法优于或与现有OSUDA方法性能相当。