CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher

• URL: http://arxiv.org/abs/2512.18321v1
• Date: Sat, 20 Dec 2025 11:39:21 GMT
• Title: CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher
• Authors: Tianlun Liu, Zhiliang Tian, Zhen Huang, Xingzhi Zhou, Wanlong Yu, Tianle Liu, Feng Liu, Dongsheng Li,
• Abstract summary: Text understanding often suffers from domain shifts.<n> domain adaptation (DA) is trained to adapt to a fixed and observed testing domain.<n>Test-time adaptation (TTA) cannot access the testing domain during training.
• Score: 31.083359760635243
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challenging paradigm, test-time adaptation (TTA), cannot access the testing domain during training and online adapts to the testing samples during testing, where the samples are from a fixed domain. We aim to explore a more practical and underexplored scenario, continual test-time adaptation (CTTA) for text understanding, which involves a sequence of testing (unobserved) domains in testing. Current CTTA methods struggle in reducing error accumulation over domains and enhancing generalization to handle unobserved domains: 1) Noise-filtering reduces accumulated errors but discards useful information, and 2) accumulating historical domains enhances generalization, but it is hard to achieve adaptive accumulation. In this paper, we propose a CTTA-T (continual test-time adaptation for text understanding) framework adaptable to evolving target domains: it adopts a teacher-student framework, where the teacher is domain-aware and generalized for evolving domains. To improve teacher predictions, we propose a refine-then-filter based on dropout-driven consistency, which calibrates predictions and removes unreliable guidance. For the adaptation-generalization trade-off, we construct a domain-aware teacher by dynamically accumulating cross-domain semantics via incremental PCA, which continuously tracks domain shifts. Experiments show CTTA-T excels baselines.

Related papers

• Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptation [42.08969745752455]
  Continual Test-Time Adaptation (CTTA) aims to adapt a source pre-trained model to continually changing target domains during inference.<n>This paper proposes a mean teacher framework that strikes an appropriate balance between Exploration and Exploitation.
  arXiv  Detail & Related papers  (2025-08-18T06:08:56Z)
• TestDG: Test-time Domain Generalization for Continual Test-time Adaptation [39.7909410173315]
  This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing.<n>We present a novel online test-time domain generalization framework for CTTA, dubbed TestDG.<n>TestDG aims to learn features invariant to both current and previous test domains on the fly during testing, improving the potential for effective generalization to future domains.
  arXiv  Detail & Related papers  (2025-04-07T12:09:18Z)
• IT$^3$: Idempotent Test-Time Training [95.78053599609044]
  Deep learning models often struggle when deployed in real-world settings due to distribution shifts between training and test data.<n>We present Idempotent Test-Time Training (IT$3$), a novel approach that enables on-the-fly adaptation to distribution shifts using only the current test instance.<n>Our results suggest that idempotence provides a universal principle for test-time adaptation that generalizes across domains and architectures.
  arXiv  Detail & Related papers  (2024-10-05T15:39:51Z)
• BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation [59.1863462632777]
  Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. This paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We validate that our method outperforms multiple CTTA scenarios, including disjoint and gradual domain shits, while only requiring 98% fewer trainable parameters.
  arXiv  Detail & Related papers  (2024-02-13T18:37:53Z)
• Better Practices for Domain Adaptation [62.70267990659201]
  Domain adaptation (DA) aims to provide frameworks for adapting models to deployment data without using labels. Unclear validation protocol for DA has led to bad practices in the literature. We show challenges across all three branches of domain adaptation methodology.
  arXiv  Detail & Related papers  (2023-09-07T17:44:18Z)
• Unsupervised Domain Adaptation for Anatomical Landmark Detection [5.070344284426738]
  We propose a novel framework for anatomical landmark detection under the setting of unsupervised domain adaptation (UDA) The framework leverages self-training and domain adversarial learning to address the domain gap during adaptation. Our experiments on cephalometric and lung landmark detection show the effectiveness of the method, which reduces the domain gap by a large margin and outperforms other UDA methods consistently.
  arXiv  Detail & Related papers  (2023-08-25T10:22:13Z)
• DomainAdaptor: A Novel Approach to Test-time Adaptation [33.770970763959355]
  DomainAdaptor aims to adapt a trained CNN model to unseen domains during the test. AdaMixBN addresses the domain shift by adaptively fusing training and test statistics in the normalization layer. Experiments show that DomainAdaptor consistently outperforms the state-of-the-art methods on four benchmarks.
  arXiv  Detail & Related papers  (2023-08-20T15:37:01Z)
• Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation [71.77083272602525]
  UDA attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain. We propose a contrastive learning approach that adapts category-wise centroids across domains. We extend our method with self-training, where we use a memory-efficient temporal ensemble to generate consistent and reliable pseudo-labels.
  arXiv  Detail & Related papers  (2021-05-05T11:55:53Z)
• Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning [62.7588467386166]
  We leverage contrastive learning to bridge the domain gap by aligning the features of structurally similar label patches across domains. Our approach consistently outperforms state-of-the-art unsupervised and semi-supervised methods on two challenging domain adaptive segmentation tasks.
  arXiv  Detail & Related papers  (2021-04-22T13:39:12Z)
• Adaptive Risk Minimization: Learning to Adapt to Domain Shift [109.87561509436016]
  A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. In this work, we consider the problem setting of domain generalization, where the training data are structured into domains and there may be multiple test time shifts. We introduce the framework of adaptive risk minimization (ARM), in which models are directly optimized for effective adaptation to shift by learning to adapt on the training domains.
  arXiv  Detail & Related papers  (2020-07-06T17:59:30Z)

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.