Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptation

• URL: http://arxiv.org/abs/2508.12643v1
• Date: Mon, 18 Aug 2025 06:08:56 GMT
• Title: Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptation
• Authors: Pinci Yang, Peisong Wen, Ke Ma, Qianqian Xu,
• Abstract summary: 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.
• Score: 42.08969745752455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual Test-Time Adaptation (CTTA) aims to adapt a source pre-trained model to continually changing target domains during inference. As a fundamental principle, an ideal CTTA method should rapidly adapt to new domains (exploration) while retaining and exploiting knowledge from previously encountered domains to handle similar domains in the future. Despite significant advances, balancing exploration and exploitation in CTTA is still challenging: 1) Existing methods focus on adjusting predictions based on deep-layer outputs of neural networks. However, domain shifts typically affect shallow features, which are inefficient to be adjusted from deep predictions, leading to dilatory exploration; 2) A single model inevitably forgets knowledge of previous domains during the exploration, making it incapable of exploiting historical knowledge to handle similar future domains. To address these challenges, this paper proposes a mean teacher framework that strikes an appropriate Balance between Exploration and Exploitation (BEE) during the CTTA process. For the former challenge, we introduce a Multi-level Consistency Regularization (MCR) loss that aligns the intermediate features of the student and teacher models, accelerating adaptation to the current domain. For the latter challenge, we employ a Complementary Anchor Replay (CAR) mechanism to reuse historical checkpoints (anchors), recovering complementary knowledge for diverse domains. Experiments show that our method significantly outperforms state-of-the-art methods on several benchmarks, demonstrating its effectiveness for CTTA tasks.

Related papers

• Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation [50.831196928686104]
  We propose a class-aware domain Knowledge Fusion and Fission method for continual test-time adaptation.<n>A domain Knowledge FIssion (KFI) module is designed to adaptively separate new domain knowledge from a paired class-aware domain prompt pool.<n>A domain Knowledge FUsion (KFU) module is further designed to merge the fissioned new knowledge into the existing knowledge pool with minimal cost.
  arXiv  Detail & Related papers  (2025-10-14T05:09:50Z)
• Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts [59.615381619866284]
  Domain-Incremental Learning (DIL) focuses on continual learning in non-stationary environments.<n>DIL faces two critical challenges in the context of imbalanced data: intra-domain class imbalance and cross-domain class distribution shifts.<n>We introduce the Dual-Balance Collaborative Experts (DCE) framework to overcome these challenges.
  arXiv  Detail & Related papers  (2025-07-09T17:57:07Z)
• Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation [67.80294336559574]
  Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios.<n>We propose a novel pipeline, Orthogonal Projection Subspace to aggregate online Prior-knowledge, dubbed OoPk.
  arXiv  Detail & Related papers  (2025-06-23T18:17:39Z)
• Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models [3.072340427031969]
  Few-shot action recognition (FSAR) aims to learn a model capable of identifying novel actions in videos using only a few examples. In assuming the base dataset seen during meta-training and novel dataset used for evaluation can come from different domains, cross-domain few-shot learning alleviates data collection and annotation costs. We systematically evaluate existing state-of-the-art single-domain, transfer-based, and cross-domain FSAR methods on new cross-domain tasks.
  arXiv  Detail & Related papers  (2024-06-03T07:48:18Z)
• Overcoming Domain Drift in Online Continual Learning [24.86094018430407]
  Online Continual Learning (OCL) empowers machine learning models to acquire new knowledge online across a sequence of tasks. OCL faces a significant challenge: catastrophic forgetting, wherein the model learned in previous tasks is substantially overwritten upon encountering new tasks. We propose a novel rehearsal strategy, Drift-Reducing Rehearsal (DRR), to anchor the domain of old tasks and reduce the negative transfer effects.
  arXiv  Detail & Related papers  (2024-05-15T06:57:18Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation [48.039156140237615]
  A Continual Test-Time Adaptation task is proposed to adapt the pre-trained model to continually changing target domains. We design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks.
  arXiv  Detail & Related papers  (2023-06-07T11:18:53Z)
• Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
  We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network. Our motivation is that models are expected to understand complex dynamics from different sources. Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
  arXiv  Detail & Related papers  (2020-09-24T15:40:55Z)

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.