The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation

• URL: http://arxiv.org/abs/2603.21928v1
• Date: Mon, 23 Mar 2026 12:48:38 GMT
• Title: The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation
• Abstract summary: Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data.<n>We propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP.
• Score: 86.83038620308423
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data. Existing CTTA methods face an efficiency-generalization trade-off: updating more parameters improves adaptation but severely reduces online inference efficiency. An ideal solution is to achieve comparable adaptation with minimal feature updates; we call this minimal subspace the golden subspace. We prove its existence in a single-step adaptation setting and show that it coincides with the row space of the pretrained classifier. To enable online maintenance of this subspace, we introduce the sample-wise Average Gradient Outer Product (AGOP) as an efficient proxy for estimating the classifier weights without retraining. Building on these insights, we propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP. Extensive experiments on classification and segmentation benchmarks, including autonomous-driving scenarios, demonstrate that GOLD attains superior efficiency, stability, and overall performance. Our code is available at https://github.com/AIGNLAI/GOLD.

Related papers

• LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning [13.12609725011405]
  Low-Rank Adaptation is widely used for parameter-efficient fine-tuning.<n>We show theoretically and empirically that uniform rank allocation is fundamentally suboptimal.<n>We propose LAARA, a search-free framework that dynamically allocates ranks.
  arXiv  Detail & Related papers  (2026-07-02T19:01:59Z)
• No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation [12.572951926839309]
  Test-time adaptation updates model parameters online using pseudo-label supervision.<n>Uniform updates on globally shared parameters can inject unstable gradients and destabilize adaptation.<n>We propose a geometry-constrained test-time prompt tuning framework for LiDAR semantic segmentation.
  arXiv  Detail & Related papers  (2026-06-29T21:40:10Z)
• iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models [14.623213614166259]
  iGSP is a novel framework that achieves efficient adaptation via implicit gradient subspace projection.<n>Experiments on the MTIL benchmark demonstrate that iGSP achieves state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2026-05-19T03:22:14Z)
• Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping [66.25536973294726]
  Post-training methods for text-to-image (T2I) models are prone to reward hacking.<n>Super-Linear Advantage Shaping (SLAS) reshapes the local policy space.<n>SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks.
  arXiv  Detail & Related papers  (2026-05-11T17:59:25Z)
• Open-World Test-Time Adaptation with Hierarchical Feature Aggregation and Attention Affine [17.151364853811128]
  Test-time adaptation (TTA) refers to adjusting the model during the testing phase to cope with changes in sample distribution.<n>We propose a Hierarchical Ladder Network that extracts OOD features from class tokens aggregated across all Transformer layers.<n>We also introduce an Attention Affine Network (AAN) that adaptively refines the self-attention mechanism conditioned on the token information to better adapt to domain drift.
  arXiv  Detail & Related papers  (2025-11-16T14:05:23Z)
• Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment [16.352863226512984]
  Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference.<n>Most methods rely on backpropagation or iterative optimization, which limits scalability and hinders real-time deployment.<n>We propose ADAPT, an Advanced Distribution-Aware and back propagation-free Test-time adaptation method.
  arXiv  Detail & Related papers  (2025-08-21T13:42:49Z)
• Regularizing Subspace Redundancy of Low-Rank Adaptation [54.473090597164834]
  We propose ReSoRA, a method that explicitly models redundancy between mapping subspaces and adaptively Regularizes Subspace redundancy of Low-Rank Adaptation.<n>Our proposed method consistently facilitates existing state-of-the-art PETL methods across various backbones and datasets in vision-language retrieval and standard visual classification benchmarks.<n>As a training supervision, ReSoRA can be seamlessly integrated into existing approaches in a plug-and-play manner, with no additional inference costs.
  arXiv  Detail & Related papers  (2025-07-28T11:52:56Z)
• 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)
• Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence [60.37934652213881]
  Domain Adaptation (DA) facilitates knowledge transfer from a source domain to a related target domain. This paper investigates a practical DA paradigm, namely Source data-Free Active Domain Adaptation (SFADA), where source data becomes inaccessible during adaptation. We present learn from the learnt (LFTL), a novel paradigm for SFADA to leverage the learnt knowledge from the source pretrained model and actively iterated models without extra overhead.
  arXiv  Detail & Related papers  (2024-07-26T17:51:58Z)
• 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)
• Efficient Semantic Image Synthesis via Class-Adaptive Normalization [116.63715955932174]
  Class-adaptive normalization (CLADE) is a lightweight but equally-effective variant that is only adaptive to semantic class. We introduce intra-class positional map encoding calculated from semantic layouts to modulate the normalization parameters of CLADE. The proposed CLADE can be generalized to different SPADE-based methods while achieving comparable generation quality compared to SPADE.
  arXiv  Detail & Related papers  (2020-12-08T18:59:32Z)

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.