A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts

By Jian Liang, Ran He, Tien-Ping Tan. International Journal of Computer Vision, 2023

561 citations recorded by the source corpus.

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 https://github.com/tim-learn/awesome-test-time-adaptation.

Subfields: Artificial Intelligence, Cancer Research, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/d8632779d4c292555c9c3e471f790169805dacc3

Citations in the corpus

• ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation (2023, unknown): “To tackle this problem, Continual Test-Time Adaptation (CTTA) has been proposed [59], which addresses a sequence of different distribution shifts over time rather than a single shift as in TTA.”