RDumb++: Drift-Aware Continual Test-Time Adaptation

• URL: http://arxiv.org/abs/2601.15544v1
• Date: Thu, 22 Jan 2026 00:20:23 GMT
• Title: RDumb++: Drift-Aware Continual Test-Time Adaptation
• Abstract summary: Continual Test-Time Adaptation seeks to update a pretrained model during deployment using only the incoming, unlabeled data stream.<n>We propose RDumb++, a principled extension of RDumb that introduces two drift-detection mechanisms.<n> RDumb++ consistently surpasses RDumb, yielding approx 3% absolute accuracy gains.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Continual Test-Time Adaptation (CTTA) seeks to update a pretrained model during deployment using only the incoming, unlabeled data stream. Although prior approaches such as Tent, EATA etc. provide meaningful improvements under short evolving shifts, they struggle when the test distribution changes rapidly or over extremely long horizons. This challenge is exemplified by the CCC benchmark, where models operate over streams of 7.5M samples with continually changing corruption types and severities. We propose RDumb++, a principled extension of RDumb that introduces two drift-detection mechanisms i.e entropy-based drift scoring and KL-divergence drift scoring, together with adaptive reset strategies. These mechanisms allow the model to detect when accumulated adaptation becomes harmful and to recover before prediction collapse occurs. Across CCC-medium with three speeds and three seeds (nine runs, each containing one million samples), RDumb++ consistently surpasses RDumb, yielding approx 3% absolute accuracy gains while maintaining stable adaptation throughout the entire stream. Ablation experiments on drift thresholds and reset strengths further show that drift-aware resetting is essential for preventing collapse and achieving reliable long-horizon CTTA.

Related papers

• Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting [4.775158008378889]
  We introduce Sensitivity-Guided Erasing Adaptation (SEGA), a method for strict online continual TTA (CTTA) on corruption-style streams.<n>SEGA uses a small number of structured erasures to probe how predictive entropy changes as information is removed.<n>In experiments on ImageNet-C, CIFAR10/100-C, and corruption-generated aquaculture streams treated as controlled corruption-style proxies, SEGA yields consistent robustness and stability gains.
  arXiv  Detail & Related papers  (2026-08-30T17:30:51Z)
• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• A Framework for Evaluating and Benchmarking Concept Drift Detection Methods [18.74827879168727]
  We benchmark 14 widely used drift detection methods on 7 realworld datasets across 4 drift types.<n>Our results provide insights into the strengths and weaknesses of current drift detection approaches.
  arXiv  Detail & Related papers  (2026-06-05T19:02:17Z)
• EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample [55.284129005947484]
  We study test-time model evolution under a strict two-forward budget.<n>We reveal three key obstacles in zeroth-order test-time optimization.<n>We propose EVA-0, a minimal zeroth-order adaptation framework.
  arXiv  Detail & Related papers  (2026-05-15T09:26:02Z)
• Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation [53.750389076941396]
  Diffusion-based visuomotor policies capture multimodal action distributions through iterative denoising, but their high inference latency limits real-time robotic control.<n>We propose Ada3Drift, which learns a training-time drifting field that attracts predicted actions toward expert demonstration modes.<n>Ada3Drift achieves state-of-the-art performance while requiring $10times$ fewer function evaluations than diffusion-based alternatives.
  arXiv  Detail & Related papers  (2026-03-12T14:36:53Z)
• When to Retrain after Drift: A Data-Only Test of Post-Drift Data Size Sufficiency [17.084943743566217]
  CALIPER is a detector- and model-agnostic, data-only test that estimates the post-drift data size required for stable retraining.<n>We show that CALIPER consistently matches or exceeds the best fixed data size for retraining while incurring negligible overhead and often outperforming incremental updates.
  arXiv  Detail & Related papers  (2026-03-09T23:43:56Z)
• Stable Video Infinity: Infinite-Length Video Generation with Error Recycling [76.91310169118408]
  We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming storylines.<n> SVI incorporates Error-Recycling Fine-Tuning, a new type of efficient training that recycles the Diffusion Transformer's self-generated errors into supervisory prompts.<n>We evaluate SVI on three benchmarks, including consistent, creative, and conditional settings, thoroughly verifying its versatility and state-of-the-art role.
  arXiv  Detail & Related papers  (2025-10-10T09:45:46Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Drift-Adapter: A Practical Approach to Near Zero-Downtime Embedding Model Upgrades in Vector Databases [0.0]
  This paper presents Drift-Adapter, a lightweight, learnable transformation layer designed to bridge embedding spaces between model versions.<n>By mapping new queries into the legacy embedding space, Drift-Adapter enables the continued use of the existing ANN index.<n>Compared to operational strategies like full re-indexing or dual-index serving, Drift-Adapter reduces recompute costs by over 100 times and facilitates upgrades with near-zero operational interruption.
  arXiv  Detail & Related papers  (2025-09-27T19:47:19Z)
• Improving Real-Time Concept Drift Detection using a Hybrid Transformer-Autoencoder Framework [0.0]
  In applied machine learning, concept drift can significantly reduce model performance.<n>Our study proposes a hybrid framework consisting of Transformers and Autoencoders to model complex temporal dynamics.<n>Our results support that the Transformation-Autoencoder detected drift earlier and with more sensitivity than the autoencoders commonly used in the literature.
  arXiv  Detail & Related papers  (2025-08-09T19:39:33Z)
• Enhancing Test Time Adaptation with Few-shot Guidance [62.49199492255226]
  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)
• Unsupervised Concept Drift Detection from Deep Learning Representations in Real-time [5.999777817331315]
  Concept drift is the phenomenon in which the underlying data distributions and statistical properties of a target domain change over time.<n>textscDriftLens is an unsupervised framework for real-time concept drift detection and characterization.
  arXiv  Detail & Related papers  (2024-06-24T23:41:46Z)
• Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adapt [37.98336090671441]
  Concept textbfDrift textbfDetection antextbfD textbfAdaptation (D3A) It first detects drifting conception and then aggressively adapts the current model to the drifted concepts after the detection for rapid adaption. It helps mitigate the data distribution gap, a critical factor contributing to train-test performance inconsistency.
  arXiv  Detail & Related papers  (2024-03-22T04:44:43Z)
• Efficient Test-Time Model Adaptation without Forgetting [60.36499845014649]
  Test-time adaptation seeks to tackle potential distribution shifts between training and testing data. We propose an active sample selection criterion to identify reliable and non-redundant samples. We also introduce a Fisher regularizer to constrain important model parameters from drastic changes.
  arXiv  Detail & Related papers  (2022-04-06T06:39:40Z)
• Detecting Concept Drift With Neural Network Model Uncertainty [0.0]
  Uncertainty Drift Detection (UDD) is able to detect drifts without access to true labels. In contrast to input data-based drift detection, our approach considers the effects of the current input data on the properties of the prediction model. We show that UDD outperforms other state-of-the-art strategies on two synthetic as well as ten real-world data sets for both regression and classification tasks.
  arXiv  Detail & Related papers  (2021-07-05T08:56:36Z)
• Consistency Guided Scene Flow Estimation [159.24395181068218]
  CGSF is a self-supervised framework for the joint reconstruction of 3D scene structure and motion from stereo video. We show that the proposed model can reliably predict disparity and scene flow in challenging imagery. It achieves better generalization than the state-of-the-art, and adapts quickly and robustly to unseen domains.
  arXiv  Detail & Related papers  (2020-06-19T17:28:07Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)

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.