Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

• URL: http://arxiv.org/abs/2607.08164v2
• Date: Sun, 12 Jul 2026 22:43:21 GMT
• Title: Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
• Abstract summary: Deep neural nets achieve remarkable performance when training and test data share the same distribution.<n>But this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts.<n>Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly.
• Score: 43.33274519035607
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 the limitations of current approaches and highlight emerging research directions, including the adaptation of foundation models and black-box systems, thereby providing a roadmap for future research in robust continual test-time adaptation.

Related papers

• Continual Model Merging with Test-Time Adaptation for Whole-Slide Image Analysis [4.934678371009237]
  Model merging offers a practical alternative to conventional continual learning.<n>Recent state-of-the-art model merging methods employ test-time adaptation (TTA-guided merging) to address distribution shifts.<n>We present a benchmark study that maps this family of methods to rehearsal-free continual Whole Slide Image classification.
  arXiv  Detail & Related papers  (2026-07-06T07:48:00Z)
• On the Interconnections of Calibration, Quantification, and Classifier Accuracy Prediction under Dataset Shift [58.91436551466064]
  This paper investigates the interconnections among three fundamental problems, calibration, and quantification, under dataset shift conditions.<n>We show that access to an oracle for any one of these tasks enables the resolution of the other two.<n>We propose new methods for each problem based on direct adaptations of well-established methods borrowed from the other disciplines.
  arXiv  Detail & Related papers  (2025-05-16T15:42:55Z)
• Beyond Model Adaptation at Test Time: A Survey [43.03129492126422]
  Machine learning algorithms struggle when samples in the test distribution start to deviate from the ones observed during training. Test-time adaptation combines the benefits of domain adaptation and domain generalization by training models only on source data. We provide a comprehensive and systematic review on test-time adaptation, covering more than 400 recent papers.
  arXiv  Detail & Related papers  (2024-11-06T06:13:57Z)
• Adaptive Cascading Network for Continual Test-Time Adaptation [12.718826132518577]
  We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations.
  arXiv  Detail & Related papers  (2024-07-17T01:12:57Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• On Pitfalls of Test-Time Adaptation [82.8392232222119]
  Test-Time Adaptation (TTA) has emerged as a promising approach for tackling the robustness challenge under distribution shifts. We present TTAB, a test-time adaptation benchmark that encompasses ten state-of-the-art algorithms, a diverse array of distribution shifts, and two evaluation protocols.
  arXiv  Detail & Related papers  (2023-06-06T09:35:29Z)
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts [117.72709110877939]
  Test-time adaptation (TTA) has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.<n>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.
  arXiv  Detail & Related papers  (2023-03-27T16:32:21Z)
• TeST: Test-time Self-Training under Distribution Shift [99.68465267994783]
  Test-Time Self-Training (TeST) is a technique that takes as input a model trained on some source data and a novel data distribution at test time. We find that models adapted using TeST significantly improve over baseline test-time adaptation algorithms.
  arXiv  Detail & Related papers  (2022-09-23T07:47:33Z)
• A Multi-stage Framework with Mean Subspace Computation and Recursive Feedback for Online Unsupervised Domain Adaptation [9.109788577327503]
  We propose a novel framework to solve real-world situations when the target data are unlabeled and arriving online sequentially in batches. To project the data from the source and the target domains to a common subspace and manipulate the projected data in real-time, our proposed framework institutes a novel method. Experiments on six datasets were conducted to investigate in depth the effect and contribution of each stage in our proposed framework.
  arXiv  Detail & Related papers  (2022-06-24T03:50:34Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Learning Neural Models for Natural Language Processing in the Face of Distributional Shift [10.990447273771592]
  The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications. It builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. It is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime
  arXiv  Detail & Related papers  (2021-09-03T14:29:20Z)
• BREEDS: Benchmarks for Subpopulation Shift [98.90314444545204]
  We develop a methodology for assessing the robustness of models to subpopulation shift. We leverage the class structure underlying existing datasets to control the data subpopulations that comprise the training and test distributions. Applying this methodology to the ImageNet dataset, we create a suite of subpopulation shift benchmarks of varying granularity.
  arXiv  Detail & Related papers  (2020-08-11T17:04:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.