A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from performance degradation 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 has highlighted the significant benefits of using unlabeled data to train self-adapted models prior to inference. In this survey, we categorize TTA into several distinct groups based on the form of test data, namely, test-time domain adaptation, test-time batch adaptation, and online test-time adaptation. For each category, we provide a comprehensive taxonomy of advanced algorithms and discuss various learning scenarios. Furthermore, we analyze relevant applications of TTA and discuss open challenges and promising areas for future research. For a comprehensive list of TTA methods, kindly refer to \url{https://github.com/tim-learn/awesome-test-time-adaptation}.
Code (1)
Tasks
Domain AdaptationSource-Free Domain AdaptationSurveyTest-time AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Beyond Model Adaptation at Test Time: A Survey
Machine learning algorithms have achieved remarkable success across various disciplines, use cases and applications, under the prevailing assumption that training and test samples are drawn from the same distribution. Co…
Domain AdaptationDomain GeneralizationSurveyTest-time AdaptationUnsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey
Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. Yet, the state-of-the-art models rely on large amount…
Domain AdaptationDomain Generalizationimage-classificationImage Classification+7Adapting Vision-Language Models Without Labels: A Comprehensive Survey
Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when directly applied to specific downstream scenar…
Test-time AdaptationFoundation Models for Time Series Analysis: A Tutorial and Survey
Time series analysis stands as a focal point within the data mining community, serving as a cornerstone for extracting valuable insights crucial to a myriad of real-world applications. Recent advances in Foundation Model…
SurveyTime SeriesTime Series AnalysisTransfer Adaptation Learning: A Decade Survey
The world we see is ever-changing and it always changes with people, things, and the environment. Domain is referred to as the state of the world at a certain moment. A research problem is characterized as transfer adapt…
Survey