In this paper, we address the problem of adapting models from a source domain to a target domain, a task that has become increasingly important due to the brittle generalization of deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic toolbox data augmentations in cases of limited target data availability. We consider the challenging setting of single-shot adaptation and explore the design of augmentation strategies. We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA, which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. Using experiments on a variety of benchmarks, distribution shifts and image corruptions, we find that SiSTA produces significantly improved generalization over existing baselines in face attribute detection and multi-class object recognition. Furthermore, SiSTA performs competitively to models obtained by training on larger target datasets. Our codes can be accessed at https://github.com/Rakshith-2905/SiSTA.

翻译：本文研究了从源域向目标域进行模型自适应的问题，该任务因深度神经网络脆弱的泛化能力而变得日益重要。尽管已有多种测试时自适应技术被提出，但在目标数据有限的情况下，这些方法通常依赖合成工具箱数据增强。我们考虑单样本自适应这一更具挑战性的场景，并探索增强策略的设计。我们认为现有方法使用的增强技术不足以应对大规模分布偏移，因此提出一种新方法SiSTA：该方法首先利用单样本目标数据对源域生成模型进行微调，然后采用新颖的采样策略来策划合成目标数据。通过在多种基准测试、分布偏移和图像损坏实验上的验证，我们发现SiSTA在人脸属性检测和多类别物体识别任务中相比现有基线方法取得了显著更好的泛化性能。此外，SiSTA在性能上与使用更大目标数据集训练得到的模型具有竞争力。我们的代码可在https://github.com/Rakshith-2905/SiSTA获取。