Machine learning methods strive to acquire a robust model during training that can generalize well to test samples, even under distribution shifts. However, these methods often suffer from a performance drop due to unknown test distributions. Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions. Recent progress in this paradigm highlights the significant benefits of utilizing unlabeled data for training self-adapted models prior to inference. In this survey, we divide TTA into several distinct categories, namely, test-time (source-free) domain adaptation, test-time batch adaptation, online test-time adaptation, and test-time prior adaptation. For each category, we provide a comprehensive taxonomy of advanced algorithms, followed by a discussion of different learning scenarios. Furthermore, we analyze relevant applications of TTA and discuss open challenges and promising areas for future research. A comprehensive list of TTA methods can be found at \url{https://github.com/tim-learn/awesome-test-time-adaptation}.
翻译:机器学习方法在训练期间力求获得一个稳健的模型,即使在分布转移情况下也能很好地推广到测试样本。然而,这些方法往往因未知的测试分布而遭受性能下降。测试时适应(Test-time adaptation,TTA),一个新兴的范例,在预测之前可以使预训练模型适应于未标记的数据。这种范例最近的进展突出了在推理之前利用未标记数据训练自适应模型的显著优势。在本调查中,我们将TTA分为几个不同的类别,即测试时间(无源)域自适应,测试时间批自适应,在线测试时间自适应和测试时间先验自适应。对于每个类别,我们提供先进算法的全面分类,然后讨论不同的学习场景。此外,我们还分析了TTA的相关应用,讨论了未来研究的挑战和有希望的领域。TTA方法的全面列表可以在\url{https://github.com/tim-learn/awesome-test-time-adaptation}中找到。