Search papers, labs, and topics across Lattice.
This paper surveys Continual Test-Time Adaptation (CTTA) in computer vision, addressing the challenge of adapting pretrained models to dynamic target distributions without access to source data or labeled targets. It categorizes existing CTTA methods into three families鈥攐ptimization-based, parameter-efficient, and architecture-based鈥攁nd provides comparative benchmarks to evaluate their performance under various continual domain shifts. The findings reveal critical limitations in current approaches and outline future research directions, particularly in adapting foundation models and black-box systems for robust performance in real-world applications.
Adapting pretrained models on-the-fly to ever-changing data distributions could redefine how we deploy AI in dynamic environments.
Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons. In this comprehensive survey, we formally define the CTTA problem, analyze the diverse continual domain shift patterns that characterize different evaluation protocols, and propose a hierarchical taxonomy that categorizes existing methods into three families: optimization-based strategies (entropy minimization, pseudo-labeling, parameter restoration), parameter-efficient methods (normalization layer adaptation, adaptive parameter selection), and architecture-based approaches (teacher-student frameworks, adapters, visual prompting, masked modeling). We systematically review representative methods within each category and present comparative benchmarks and experimental results across standard evaluation settings. Finally, we discuss limitations of current approaches and highlight emerging research directions, including adaptation of foundation models and black-box systems, providing a roadmap for future research in robust continual test-time adaptation. We encourage visiting our repository at [https://github.com/sarthaxxxxx/Awesome-Continual-Test-Time-Adaptation](https://github.com/sarthaxxxxx/Awesome-Continual-Test-Time-Adaptation)
