ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains

• URL: http://arxiv.org/abs/2505.14511v1
• Date: Tue, 20 May 2025 15:39:20 GMT
• Title: ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
• Authors: Guillaume Vray, Devavrat Tomar, Xufeng Gao, Jean-Philippe Thiran, Evan Shelhamer, Behzad Bozorgtabar,
• Abstract summary: ReservoirTTA is a novel plug-in framework designed for prolonged test-time adaptation.<n>At its core, ReservoirTTA maintains a reservoir of domain-specialized models.<n>Our theoretical analysis reveals key components that bound parameter variance and prevent model collapse.
• Score: 17.357842682605185
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper introduces ReservoirTTA, a novel plug-in framework designed for prolonged test-time adaptation (TTA) in scenarios where the test domain continuously shifts over time, including cases where domains recur or evolve gradually. At its core, ReservoirTTA maintains a reservoir of domain-specialized models -- an adaptive test-time model ensemble -- that both detects new domains via online clustering over style features of incoming samples and routes each sample to the appropriate specialized model, and thereby enables domain-specific adaptation. This multi-model strategy overcomes key limitations of single model adaptation, such as catastrophic forgetting, inter-domain interference, and error accumulation, ensuring robust and stable performance on sustained non-stationary test distributions. Our theoretical analysis reveals key components that bound parameter variance and prevent model collapse, while our plug-in TTA module mitigates catastrophic forgetting of previously encountered domains. Extensive experiments on the classification corruption benchmarks, including ImageNet-C and CIFAR-10/100-C, as well as the Cityscapes$\rightarrow$ACDC semantic segmentation task, covering recurring and continuously evolving domain shifts, demonstrate that ReservoirTTA significantly improves adaptation accuracy and maintains stable performance across prolonged, recurring shifts, outperforming state-of-the-art methods.

Related papers

• BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis [41.09181390655176]
  Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but degrade significantly under textittemporally evolving distribution shifts common in real-world scenarios.<n>We formalize this practical problem as textitContinual-Temporal Test-Time Adaptation (CT-TTA), where test distributions evolve gradually over time.<n>We propose textitBayesTTA, a Bayesian adaptation framework that enforces temporally consistent predictions and dynamically aligns visual representations.
  arXiv  Detail & Related papers  (2025-07-11T14:02:54Z)
• 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)
• SPARNet: Continual Test-Time Adaptation via Sample Partitioning Strategy and Anti-Forgetting Regularization [16.5927083825258]
  Test-time Adaptation (TTA) aims to improve model performance when the model encounters domain changes after deployment.<n>Noisy pseudo-labels produced by simple self-training methods can cause error accumulation and catastrophic forgetting.<n>We propose a new framework named SPARNet which consists of two parts, sample partitioning strategy and anti-forgetting regularization.
  arXiv  Detail & Related papers  (2025-01-01T12:19:17Z)
• 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)
• Enhancing Test Time Adaptation with Few-shot Guidance [35.13317598777832]
  Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data.<n>Test Time Adaptation (TTA) methods have been proposed to adapt pre-trained source model to handle out-of-distribution streaming target data.<n>We develop Few-Shot Test Time Adaptation (FS-TTA), a novel and practical setting that utilizes a few-shot support set on top of TTA.
  arXiv  Detail & Related papers  (2024-09-02T15:50:48Z)
• Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation [49.53202761595912]
  Continual Test-Time Adaptation involves adapting a pre-trained source model to continually changing unsupervised target domains. We analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic forgetting. We propose an uncertainty-aware buffering approach to identify and aggregate significant samples with high certainty from the unsupervised, single-pass data stream.
  arXiv  Detail & Related papers  (2024-07-12T15:48:40Z)
• A Layer Selection Approach to Test Time Adaptation [0.2968738145616401]
  Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference.<n>We propose GALA, a novel layer selection criterion to identify the most beneficial updates to perform during TTA.
  arXiv  Detail & Related papers  (2024-04-04T19:55:11Z)
• Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank [24.096250529224914]
  We propose a practical test-time adaptation (ResiTTA) method focused on parameter resilience and data quality. We use an entropy-driven memory bank that accounts for timeliness, the persistence of over-confident samples, and sample uncertainty for high-quality data in adaptation. We empirically validate ResiTTA across various benchmark datasets, demonstrating state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-01-26T03:24:55Z)
• AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation [1.4530711901349282]
  We propose to validate test-time adaptation methods using datasets for autonomous driving, namely CLAD-C and SHIFT. We observe that current test-time adaptation methods struggle to effectively handle varying degrees of domain shift. We enhance the well-established self-training framework by incorporating a small memory buffer to increase model stability.
  arXiv  Detail & Related papers  (2023-09-18T19:34:23Z)
• Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management [75.86903206636741]
  Test-time adaptation (TTA) allows the model to adapt itself to novel environments and improve its performance during test time. Several works for TTA have shown promising adaptation performances in continuously changing environments. This paper first presents a robust TTA framework with compound domain knowledge management. We then devise novel regularization which modulates the adaptation rates using domain-similarity between the source and the current target domain.
  arXiv  Detail & Related papers  (2022-12-16T09:02:01Z)
• Semantic Self-adaptation: Enhancing Generalization with a Single Sample [45.111358665370524]
  We propose a self-adaptive approach for semantic segmentation. It fine-tunes the parameters of convolutional layers to the input image using consistency regularization. Our empirical study suggests that self-adaptation may complement the established practice of model regularization at training time.
  arXiv  Detail & Related papers  (2022-08-10T12:29:01Z)
• Unsupervised Domain Adaptation for Spatio-Temporal Action Localization [69.12982544509427]
  S-temporal action localization is an important problem in computer vision. We propose an end-to-end unsupervised domain adaptation algorithm. We show that significant performance gain can be achieved when spatial and temporal features are adapted separately or jointly.
  arXiv  Detail & Related papers  (2020-10-19T04:25:10Z)
• 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.